WO2024075749A1

WO2024075749A1 - Cooling system, cooling execution device, cooling device, cooling execution method, cooling method, program, cooling execution program, and cooling program

Info

Publication number: WO2024075749A1
Application number: PCT/JP2023/036112
Authority: WO
Inventors: 正義孫
Original assignee: ソフトバンクグループ株式会社
Priority date: 2022-10-04
Filing date: 2023-10-03
Publication date: 2024-04-11

Abstract

Provided is a cooling execution device which is equipped with: a prediction unit for predicting a change in the temperature of a control device which is installed in a vehicle and controls the automated driving of the vehicle, and a cooling execution unit for starting cooling of the control device on the basis of the temperature change predicted by the prediction unit. Provided is a cooling execution method executed by a computer, said method being provided with: a prediction step for predicting a change in the temperature of a control device which is installed in a vehicle and controls the automated driving of the vehicle, and a cooling execution step for starting to cool the control device on the basis of the temperature change predicted by the prediction unit.

Description

COOLING SYSTEM, COOLING EXECUTION DEVICE, COOLING DEVICE, COOLING EXECUTION METHOD, COOLING METHOD, PROGRAM, COOLING EXECUTION PROGRAM, AND COOLING PROGRAM

The present invention relates to a cooling system, a cooling execution device, a cooling device, a cooling execution method, a cooling method, a program, a cooling execution program, and a cooling program.

Patent document 1 describes a vehicle with an autonomous driving function.

JP 2022-035198 A

There is a need for a cooling system, a cooling execution device, a cooling device, a cooling execution method, a cooling method, a program, a cooling execution program, and a cooling program that perform efficient cooling in response to temperature changes in a control device possessed by a vehicle.

According to one embodiment of the present invention, a cooling execution device is provided. The cooling execution device may include a prediction unit that predicts a temperature change in a control device mounted on the vehicle that controls the automatic driving of the vehicle. The cooling execution device may include a cooling execution unit that starts cooling the control device based on the temperature change predicted by the prediction unit.

In the cooling execution device, the cooling execution unit may start cooling the control device in response to a prediction that the temperature of the control device will be higher than a predetermined threshold value.

In any of the cooling execution devices, the prediction unit may predict the temperature change of the control device by AI. The cooling execution device may further include a model storage unit that stores a learning model that uses information acquired by the control device as input and a temperature change of the control device as output, the learning model being generated by machine learning using information acquired by the control device and the temperature change of the control device when the control device acquired the information as learning data, and an information acquisition unit that acquires the information acquired by the control device, and the prediction unit may predict the temperature change of the control device by inputting the information acquired by the information acquisition unit into the learning model. The information acquisition unit may acquire sensor information acquired by the control device from a sensor mounted on the vehicle from the sensor or the control device. The information acquisition unit may acquire from the control device an analysis result of an image captured by the control device analyzed by a camera mounted on the vehicle. The information acquisition unit may acquire external information received by the control device from an external device from the external device or the control device. The information acquisition unit may acquire traffic information for the road on which the vehicle is located, which the control device receives from the external device, from the external device or the control device.

In any of the cooling execution devices, the cooling execution unit may start cooling the control device using one or more cooling means selected from a plurality of types of cooling means depending on the temperature of the control device predicted by the prediction unit. The plurality of types of cooling means may include a plurality of air cooling means, water cooling means, and liquid nitrogen cooling means. The prediction unit may predict temperature changes in each of a plurality of parts of the control device, and the cooling execution unit may start cooling the control device using a cooling means selected from a plurality of cooling means that cool each of a plurality of parts of the control device based on the prediction result by the prediction unit. The control device may have a plurality of processing chips, each of which is arranged at a different position on the control device, and each of the plurality of cooling means may be arranged at a position corresponding to each of the plurality of processing chips.

According to one embodiment of the present invention, a program is provided for causing a computer to function as the cooling execution device.

According to one embodiment of the present invention, there is provided a cooling execution method executed by a computer. The cooling execution method may include a prediction step of predicting a temperature change in a control device mounted on the vehicle that controls the automatic driving of the vehicle. The cooling execution method may include a cooling execution step of starting cooling of the control device based on the temperature change predicted in the prediction step.

According to an embodiment, a cooling system is provided. The cooling system includes a server and a cooling execution device, and the server includes an information acquisition unit that acquires, from the cooling execution device, location information of a vehicle having the cooling execution device and temperature information of a control device of the vehicle, and a prediction unit that predicts a temperature change of the control device based on the location information of the vehicle having the cooling execution device acquired by the information acquisition unit and the temperature information of the control device of the vehicle, and the cooling execution device may include an information acquisition unit that acquires, from the server, a prediction result of the temperature change of the control device predicted by the prediction unit of the server, and a cooling execution unit that starts cooling of the control device based on the prediction result of the temperature change of the control device acquired by the information acquisition unit.

The server may further have a creation unit that creates a map showing the relationship between the position of the vehicle having the cooling execution device and the temperature of the control device from the position information of the vehicle having the cooling execution device acquired by the information acquisition unit and temperature information of the control device of the vehicle, and the prediction unit may predict a temperature change of the control device based on the position information of the vehicle having the cooling execution device acquired by the information acquisition unit, the temperature information of the control device of the vehicle, and the map created by the creation unit showing the relationship between the position of the vehicle and the temperature of the control device.

The information acquisition unit of the server may acquire location information of the vehicle having the cooling execution device, temperature information of a control device possessed by the vehicle, and information regarding the type of the vehicle from the cooling execution device, and the creation unit may create a map representing the relationship between the location of the vehicle and the temperature of the control device for the vehicle type from the location information of the vehicle having the cooling execution device, temperature information of the control device possessed by the vehicle, and information regarding the type of vehicle acquired by the information acquisition unit, and the prediction unit of the server may predict a temperature change of the control device based on the location information of the vehicle having the cooling execution device acquired by the information acquisition unit, temperature information of the control device possessed by the vehicle, and the map representing the relationship between the location of the vehicle and the temperature of the control device for the vehicle type created by the creation unit.

The cooling execution unit may use the predicted temperature change of the control device acquired by the information acquisition unit to start cooling the control device a predetermined time before the control device starts to generate heat.

The cooling execution unit may use the predicted temperature change of the control device acquired by the information acquisition unit to start cooling the control device using one or more cooling means selected from multiple types of cooling means in accordance with the temperature change of the control device.

The multiple types of cooling means may include multiple of one or more types of air cooling means, one or more types of water cooling means, and liquid nitrogen cooling means.

According to an embodiment, a cooling execution method is provided which is executed by a server and a cooling execution device. The cooling execution method may include an information acquisition step in which the server acquires, from the cooling execution device, location information of a vehicle having the cooling execution device and temperature information of a control device possessed by the vehicle. The cooling execution method may include a prediction step in which the server predicts a temperature change of the control device based on the location information of the vehicle having the cooling execution device and the temperature information of the control device possessed by the vehicle acquired by the information acquisition step. The cooling execution method may include an information acquisition step in which the cooling execution device acquires, from the server, a prediction result of the temperature change of the control device predicted by the prediction step of the server. The cooling execution method may include a cooling execution step in which the cooling execution device starts cooling of the control device based on the prediction of the temperature change of the control device acquired by the information acquisition step.

According to an embodiment, a cooling program is provided that includes a program executed by a server and a program executed by a cooling execution device. The cooling program may cause the server to execute an information acquisition step of acquiring, from the cooling execution device, location information of a vehicle having the cooling execution device and temperature information of a control device possessed by the vehicle, and a prediction step of predicting a temperature change of the control device based on the location information of the vehicle having the cooling execution device and the temperature information of the control device possessed by the vehicle acquired by the information acquisition step, and cause the cooling execution device to execute an information acquisition step of acquiring, from the server, a prediction result of the temperature change of the control device predicted by the prediction step of the server, and a cooling execution step of starting cooling of the control device based on the prediction result of the temperature change of the control device acquired by the information acquisition step.

According to an embodiment, a cooling system is provided. The cooling system is a cooling system including a server and a cooling execution device, and the server includes an information acquisition unit that acquires from the cooling execution device location information of a vehicle having the cooling execution device, temperature information of a control device of the vehicle, information on traffic conditions, and weather information, and a prediction unit that predicts a temperature change of the control device based on the location information of the vehicle having the cooling execution device acquired by the information acquisition unit, the temperature information of the control device of the vehicle, the information on the traffic conditions, and the weather information, and the cooling execution device may include an information acquisition unit that acquires from the server a prediction result of the temperature change of the control device predicted by the prediction unit of the server, and a cooling execution unit that starts cooling of the control device based on the prediction result of the temperature change of the control device acquired by the information acquisition unit.

The server may further have a creation unit that creates a map showing the relationship between the vehicle's position, the information about the traffic conditions, the weather information, and the temperature of the control device from the position information of the vehicle having the cooling execution device acquired by the information acquisition unit, the temperature information of the control device of the vehicle, the information about the traffic conditions, and the weather information, and the prediction unit may predict a temperature change of the control device based on the position information of the vehicle having the cooling execution device acquired by the information acquisition unit, the temperature information of the control device of the vehicle, the information about the traffic conditions, the weather information, and the map created by the creation unit showing the relationship between the vehicle's position, the information about the traffic conditions, the weather information, and the temperature of the control device.

The creation unit may create a map showing the relationship between the position of the vehicle and the temperature of the control device for each of the information on the traffic conditions and the weather information, based on the position information of the vehicle having the cooling execution device acquired by the information acquisition unit, the temperature information of the control device of the vehicle, the information on the traffic conditions, and the weather information.

The information acquisition unit of the server may further acquire information relating to the type of the vehicle from the cooling execution device, and the creation unit may create a map showing the relationship between the position of the vehicle, the information relating to the traffic conditions, the weather information, the type of the vehicle, and the temperature of the control device from the position information of the vehicle having the cooling execution device, the temperature information of the control device of the vehicle, the information relating to the traffic conditions, the weather information, and the information relating to the type of the vehicle.

According to an embodiment, a cooling execution method is provided that is executed by a server and a cooling execution device. The cooling execution method may include an information acquisition step in which the server acquires, from the cooling execution device, location information of a vehicle having the cooling execution device, temperature information of a control device possessed by the vehicle, information on the traffic conditions, and the weather information. The server may include a prediction step in which the server predicts a temperature change of the control device based on the location information of the vehicle having the cooling execution device, temperature information of a control device possessed by the vehicle, information on the traffic conditions, and the weather information acquired by the information acquisition step. The cooling execution device may include an information acquisition step in which the server acquires, from the server, a prediction result of the temperature change of the control device predicted by the prediction step of the server. The cooling execution device may include a cooling execution step in which the cooling execution device starts cooling of the control device based on the prediction of the temperature change of the control device acquired by the information acquisition step.

According to an embodiment, a cooling program is provided that includes a program executed by a server and a program executed by a cooling execution device. The program causes the server to execute an information acquisition step of acquiring, from the cooling execution device, location information of a vehicle having the cooling execution device and temperature information of a control device of the vehicle, and a prediction step of predicting a temperature change of the control device based on the location information of the vehicle having the cooling execution device acquired by the information acquisition step, the temperature information of the control device of the vehicle, information on the traffic conditions, and the weather information, and may cause the cooling execution device to execute an information acquisition step of acquiring, from the server, a prediction result of the temperature change of the control device predicted by the prediction step of the server, and a cooling execution step of starting cooling of the control device based on the prediction result of the temperature change of the control device acquired by the information acquisition step.

According to an embodiment, a cooling system is provided. The cooling system is a cooling system including a server and a cooling execution device, the server includes an information acquisition unit that acquires from the cooling execution device position information of each integrated circuit in the control device, information related to the processing of each integrated circuit, and information related to the driving status of the vehicle, and a prediction unit that predicts temperature changes at each position of the control device from the position information of each integrated circuit in the control device, information related to the processing of each integrated circuit, and information related to the driving status of the vehicle acquired by the information acquisition unit, and the cooling execution device may include an information acquisition unit that acquires from the server a prediction result of the temperature change at each position of the control device predicted by the prediction unit of the server, and a cooling execution unit that starts cooling the control device based on the prediction result of the temperature change at each position of the control device acquired by the information acquisition unit.

The prediction unit may predict temperature changes over time at each position of the control device from position information of each integrated circuit in the control device acquired by the information acquisition unit, information related to the processing of each integrated circuit, and information related to the driving status of the vehicle.

The cooling execution unit may use the predicted results of temperature changes at each position of the control device acquired by the information acquisition unit to start cooling at positions where heat is generated in the control device.

The cooling execution unit may use the predicted temperature change at each position of the control device acquired by the information acquisition unit to start cooling the position where the control device generates heat a predetermined time before the control device starts to generate heat.

The cooling execution unit may use the predicted results of the temperature change at each position of the control device acquired by the information acquisition unit, and start cooling the control device using one or more cooling means selected from multiple types of cooling means according to the temperature change at each position of the control device.

According to an embodiment, a cooling execution method is provided which is executed by a server and a cooling execution device. The server may include an information acquisition step of acquiring position information of each integrated circuit in the control device, information related to the processing of each integrated circuit, and information related to the driving status of the vehicle from the cooling execution device. The server may include a prediction step of predicting temperature changes at each position of the control device from the position information of each integrated circuit in the control device, information related to the processing of each integrated circuit, and information related to the driving status of the vehicle acquired by the information acquisition step. The cooling execution device may include an information acquisition step of acquiring from the server a prediction result of the temperature change at each position of the control device predicted by the prediction step of the server. The cooling execution device may include a cooling execution step of starting cooling of the control device based on the prediction result of the temperature change at each position of the control device acquired by the information acquisition step.

According to an embodiment, a cooling program is provided that includes a program executed by a server and a program executed by a cooling execution device. The program causes the server to execute an information acquisition step of acquiring, from the cooling execution device, position information of each integrated circuit in the control device, information related to the processing of each integrated circuit, and information related to the driving status of the vehicle, and a prediction step of predicting a temperature change at each position of the control device from the position information of each integrated circuit in the control device, information related to the processing of each integrated circuit, and information related to the driving status of the vehicle acquired by the information acquisition step, and may cause the cooling execution device to execute an information acquisition step of acquiring, from the server, a prediction result of the temperature change at each position of the control device predicted by the prediction step of the server, and a cooling execution step of starting cooling of the control device based on the prediction result of the temperature change at each position of the control device acquired by the information acquisition step.

According to an embodiment, a cooling execution device is provided. The cooling execution device may have a detection unit that detects the temperature of a control device mounted on a vehicle that controls the automatic driving of the vehicle, and a cooling execution unit that executes cooling of the control device using a predetermined cooling means based on the time that the temperature detected by the detection unit continues to be equal to or higher than a predetermined temperature.

In the cooling execution device, the cooling execution unit may execute cooling using the cooling means, which may include one or more types of air cooling means, one or more types of water cooling means, and liquid nitrogen cooling means, when the time during which the temperature remains above the predetermined temperature exceeds a predetermined threshold.

In the cooling execution device, the cooling execution unit may execute rapid cooling when the temperature exceeds a predetermined threshold.

The cooling execution device may further include a prediction unit that predicts a temperature change in a control device mounted on the vehicle that controls the automatic driving of the vehicle, and the cooling execution unit may execute cooling using the cooling means based on the time that the temperature change predicted by the prediction unit continues to be equal to or higher than the predetermined temperature.

The cooling execution device may further include a prediction unit that predicts temperature changes in each of the multiple parts of the control device, and the cooling execution unit may start cooling the control device using a cooling means selected from multiple cooling means that cool each of the multiple parts of the control device based on the prediction result by the prediction unit.

The control device may have a plurality of processing chips, each of which is arranged at a different position on the control device, and each of the plurality of cooling means may be arranged at a position corresponding to each of the plurality of processing chips.

According to one embodiment of the present invention, a program is provided for causing a computer to function as a cooling execution device.

According to one embodiment of the present invention, a cooling execution method executed by a computer may include a detection step of detecting the temperature of a control device mounted on a vehicle that controls the automatic driving of the vehicle, and a cooling execution step of cooling the control device using a predetermined cooling means based on the time that the temperature detected in the detection step continues to be equal to or higher than a predetermined temperature.

According to an embodiment, a cooling execution device is provided. The cooling execution device may have an estimation unit that estimates switching between automatic driving and manual driving based on a preset driving route, a creation unit that creates a cooling schedule in which cooling conditions based on a predetermined cooling means are set based on the estimation result of the estimation unit, and a cooling execution unit that executes cooling of a control device mounted on a vehicle that controls the automatic driving of the vehicle based on the cooling schedule created by the creation unit.

In the cooling execution device, the estimation unit may estimate whether or not switching from the automatic driving to the manual driving will occur based on road conditions on the driving route.

In the cooling execution device, when the estimation unit estimates that the automatic driving will be switched to the manual driving, the creation unit may create the cooling schedule in which a cooling means is set for the driving section of the manual driving, and when the estimation unit estimates that the manual driving will be switched to the automatic driving, the creation unit may create the cooling schedule in which a cooling means is set for the driving section of the automatic driving.

The cooling execution device may further include a detection unit that detects a temperature change in a control device mounted on the vehicle that controls the automatic driving of the vehicle, and a prediction unit that predicts the temperature change in the control device, and the creation unit may compare the actual temperature change detected by the detection unit with the predicted temperature change predicted by the prediction unit, and create the cooling schedule in which the specified cooling means is set if the predicted temperature change exceeds the actual temperature change.

In the cooling device, the cooling means may include one or more types of air cooling means, one or more types of water cooling means, and a liquid nitrogen cooling means.

The cooling execution device may further include a prediction unit that predicts a temperature change in a control device mounted on the vehicle that controls the automatic driving of the vehicle, and the cooling execution unit may execute cooling of the control device using a cooling means selected from a plurality of cooling means that cool each of a plurality of parts of the control device based on the cooling schedule created by the creation unit.

According to one embodiment of the present invention, a cooling execution method executed by a computer may include an estimation step of estimating a switch between automatic driving and manual driving based on a preset driving route, a creation step of creating a cooling schedule in which cooling conditions based on a predetermined cooling means are set based on the estimation result of the estimation step, and a cooling execution step of executing cooling of a control device mounted on a vehicle that controls the automatic driving of the vehicle based on the cooling schedule created in the creation step.

According to one embodiment of the present invention, a cooling device is provided that includes a prediction unit that predicts a temperature change in a control device mounted on a vehicle that controls the automatic driving of the vehicle, and a cooling execution unit that performs cooling so that the temperature of the control device is maintained within a predetermined temperature range based on the temperature change predicted by the prediction unit.

Furthermore, in the cooling device, the cooling execution unit may determine the predetermined temperature range according to a threshold temperature that is predetermined for the control device.

Furthermore, the prediction unit may predict the temperature change of the control device using AI.

The cooling device may further include a model storage unit that stores a learning model that uses the information acquired by the control device as input and the temperature change of the control device as output, the learning model being generated by machine learning using the information acquired by the control device and the temperature change of the control device when the control device acquired the information as learning data, and an information acquisition unit that acquires the information acquired by the control device, and the prediction unit may predict the temperature change of the control device by inputting the information acquired by the information acquisition unit into the learning model. The information acquisition unit may acquire sensor information acquired by the control device from a sensor mounted on the vehicle, from the sensor or the control device.

Furthermore, the information acquisition unit may acquire from the control device the analysis results of the control device's analysis of an image captured by a camera mounted on the vehicle.

The information acquisition unit may acquire external information that the control device receives from an external device from the external device or the control device. The information acquisition unit may acquire traffic information of a road on which the vehicle is located, which the control device receives from the external device, from the external device or the control device.

Furthermore, the cooling execution unit may start cooling the control device using one or more cooling means selected from multiple types of cooling means, depending on the temperature of the control device predicted by the prediction unit.

Furthermore, the multiple types of cooling means in the cooling execution unit may include multiple of one or multiple types of air cooling means, one or multiple types of water cooling means, and liquid nitrogen cooling means.

Furthermore, the prediction unit may predict temperature changes in each of the multiple parts of the control device, and the cooling execution unit may start cooling the control device using a cooling means selected from multiple cooling means that cool each of the multiple parts of the control device based on the prediction result by the prediction unit.

Furthermore, the control device may have a plurality of processing chips, each disposed at a different position on the control device, and each of the plurality of cooling means may be disposed at a position corresponding to each of the plurality of processing chips.

According to one embodiment of the present invention, there is provided a cooling method executed by a cooling device, the cooling method including a prediction step of predicting a temperature change in a control device mounted on the vehicle that controls the automatic driving of the vehicle, and a cooling execution step of performing cooling so that the temperature of the control device is maintained within a predetermined temperature range based on the temperature change predicted by the prediction step.

According to one embodiment of the present invention, a cooling program is provided that causes a computer to execute a prediction procedure for predicting a temperature change in a control device mounted on a vehicle that controls the automatic driving of the vehicle, and a cooling execution procedure for performing cooling so that the temperature of the control device is maintained within a predetermined temperature range based on the temperature change predicted in the prediction procedure.

According to an embodiment, a cooling execution device is provided. The cooling execution device may have a detection unit that detects a temperature change in a control device mounted on a vehicle that controls the automatic driving of the vehicle, a selection unit that selects a predetermined operating condition for lowering the temperature of the control device when the temperature change exceeds a predetermined threshold, and an output unit that outputs the predetermined operating condition based on the selection result of the selection unit.

In the cooling execution device, when the temperature change exceeds a predetermined threshold, the selection unit may select, as the predetermined operating condition, an operating condition that reduces the amount of calculation related to the predetermined information processing of the control device.

The cooling execution device may further include an information acquisition unit that acquires the results of the information processing related to the automatic driving from an external information processing device that performs information processing related to the automatic driving as a predetermined information processing of the control device.

In the cooling execution device, when the temperature change exceeds a predetermined threshold, the selection unit may select, as the predetermined operating condition, an operating condition that suppresses the operating speed of the automatic operation to a predetermined speed or less.

In the cooling execution device, the selection unit may select, as the predetermined operating condition, an operating condition that changes the automatic operation to a manual operation when the temperature change exceeds a predetermined threshold.

In the cooling execution device, the selection unit may select, as the predetermined driving condition, a driving condition in which the vehicle stops at a predetermined position on a road included in the driving route of the autonomous driving, when the temperature change exceeds a predetermined threshold.

In the cooling execution device, when the temperature change exceeds a predetermined threshold, the selection unit may select, as the predetermined operating condition, an operating condition that suppresses the acquisition of predetermined information used for information processing of the automatic driving.

According to one embodiment of the present invention, a cooling execution method executed by a computer may include a detection step of detecting a temperature change in a control device mounted on a vehicle that controls automatic driving of the vehicle, a selection step of selecting a predetermined operating condition for lowering the temperature of the control device when the temperature change exceeds a predetermined threshold, and an output step of outputting the predetermined operating condition based on the selection result of the selection step.

According to one embodiment of the present invention, a cooling device is provided that includes a prediction unit that predicts a temperature change in a control device mounted on a vehicle that controls the automatic driving of the vehicle, a communication unit that communicates with other vehicles that are present within a predetermined range based on the temperature change predicted by the prediction unit, and an instruction unit that instructs the control device to execute a calculation related to the control of the automatic driving of the other vehicle with which communication is being performed by the communication unit.

The communication unit may also determine that other vehicles that are within a range in which communication with other vehicles can be maintained for a predetermined period of time are vehicles that are within the predetermined range and communicate with them.

The system may further include a cooling execution unit that starts cooling the control device based on the temperature change predicted by the prediction unit.

The cooling execution unit may also start cooling the control device in response to the prediction unit predicting that the temperature of the control device will be higher than a predetermined threshold.

Furthermore, the prediction unit may predict the temperature change of the control unit using AI.

The autonomous driving control device may further include a model storage unit that stores a learning model that uses the information acquired by the control device and the temperature change of the control device at the time the control device acquired the information as learning data, the learning model being generated by machine learning that uses the information acquired by the control device as input and the temperature change of the control device as output, and an information acquisition unit that acquires the information acquired by the control device, and the prediction unit may predict the temperature change of the control device by inputting the information acquired by the information acquisition unit into the learning model.

Furthermore, the information acquisition unit may acquire sensor information that the control device acquires from a sensor mounted on the vehicle from the sensor or the control device.

The information acquisition unit may also acquire from the control device the analysis results of an image captured by a camera mounted on the vehicle, which is analyzed by the control device.

Furthermore, the information acquisition unit may acquire external information that the control device receives from an external device from the external device or the control device. The information acquisition unit may acquire traffic information of the road on which the vehicle is located, which the control device receives from the external device, from the external device or the control device.

The cooling execution unit may also start cooling the control device using one or more cooling means selected from a plurality of types of cooling means, depending on the temperature of the control device predicted by the prediction unit.

According to one embodiment of the present invention, there is provided a cooling method executed by a cooling device, the cooling method including a prediction step of predicting a temperature change in a control device mounted on the vehicle that controls the automatic driving of the vehicle, a communication step of communicating with other vehicles present within a predetermined range based on the temperature change predicted by the prediction step, and an instruction step of instructing the control device to execute a calculation related to the control of the automatic driving of the other vehicle with which communication is being performed by the communication step.

According to one embodiment of the present invention, a cooling program is provided for causing a computer to execute a prediction procedure for predicting a temperature change in a control device mounted on a vehicle that controls the automatic driving of the vehicle, a communication procedure for communicating with other vehicles present within a predetermined range based on the temperature change predicted by the prediction procedure, and an instruction procedure for instructing the control device to execute a calculation related to the control of the automatic driving of the other vehicles with which communication is being performed by the communication procedure.

According to one embodiment of the present invention, a cooling execution device is provided. The cooling execution device may include a prediction unit that predicts a change in computing power of a control device mounted on the vehicle that controls the automatic driving of the vehicle. The cooling execution device may include a cooling execution unit that starts cooling the control device based on the change predicted by the prediction unit.

In the cooling execution device, the prediction unit may predict a change in the computing power of the control device using AI. The prediction unit may predict the moment when the computing power of the control device will be at its maximum, and the cooling execution unit may start cooling the control device based on the moment predicted by the prediction unit. The cooling execution unit may start cooling the control device at the moment when the computing power of the control device will be at its maximum. The prediction unit may predict the time until the temperature of the control device becomes higher than a predetermined temperature from the prediction result of the moment when the computing power of the control device will be at its maximum, and the cooling execution unit may start cooling the control device based on the time predicted by the prediction unit.

Any of the cooling execution devices may further include a model storage unit that stores a learning model that uses the information acquired by the control device as input and the computing power of the control device as output, the learning model being generated by machine learning using the information acquired by the control device and the computing power of the control device at the time the control device acquired the information as learning data, and an information acquisition unit that acquires the information acquired by the control device, and the prediction unit may predict a change in the computing power of the control device by inputting the information acquired by the information acquisition unit into the learning model. The information acquisition unit may acquire at least any of sensor information acquired by the control device from a sensor mounted on the vehicle, an analysis result of an analysis by the control device of an image captured by a camera mounted on the vehicle, external information received by the control device from an external device, and traffic information of a road on which the vehicle is located that is received by the control device from the external device.

Any of the cooling execution devices may further include a model storage unit that stores a learning model that takes the information acquired by the control device as input and outputs the time until the control device cools down when cooling of the control device is started, the learning model being generated by machine learning using the information acquired by the control device and the time until the control device cools down when cooling of the control device is started as learning data when the control device acquires the information, and an information acquisition unit that acquires the information acquired by the control device, and the cooling execution unit may determine the timing to start cooling of the control device based on the change predicted by the prediction unit and the time until the control device cools down when cooling of the control device is started, acquired by inputting the information acquired by the information acquisition unit into the learning model.

In any of the cooling execution devices, the cooling execution unit may adjust the degree of cooling of the control device according to a risk rate indicating the probability of a risk that the control device will not function properly due to a high temperature of the control device, thereby affecting normal automatic driving of the vehicle. The cooling execution unit may cool the control device with a first cooling intensity when the risk rate is lower than a first threshold, cool the control device with a second cooling intensity stronger than the first cooling intensity when the risk rate is higher than the first threshold and lower than a second threshold higher than the first threshold, and cool the control device with a third cooling intensity stronger than the second cooling intensity when the risk rate is higher than the second threshold.

According to one embodiment of the present invention, there is provided a cooling execution method executed by a computer. The cooling execution method may include a prediction step of predicting a change in computing power of a control device mounted on the vehicle that controls the automatic driving of the vehicle. The cooling execution method may include a cooling execution step of starting cooling of the control device based on the change predicted in the prediction step.

Note that the above summary of the invention does not list all of the necessary features of the present invention. Subcombinations of these features may also be inventions.

1 illustrates a schematic diagram of an example of a system 10. FIG. 2 is an explanatory diagram for explaining a learning phase in the system 10. FIG. 2 is an explanatory diagram for explaining a cooling execution phase in the system 10. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. 1 illustrates a schematic diagram of an example of a system 10. FIG. 2 is an explanatory diagram for explaining a learning phase in the system 10. FIG. 2 is an explanatory diagram for explaining a cooling execution phase in the system 10. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. 1 illustrates a schematic diagram of an example of a system 10. FIG. 2 is an explanatory diagram for explaining a learning phase in the system 10. FIG. 2 is an explanatory diagram for explaining a cooling execution phase in the system 10. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. 1 illustrates a schematic diagram of an example of a system 10. FIG. 2 is an explanatory diagram for explaining a learning phase in the system 10. FIG. 2 is an explanatory diagram for explaining a cooling execution phase in the system 10. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. 1 illustrates a schematic diagram of an example of a system 10. FIG. 2 is an explanatory diagram for explaining a learning phase in the system 10. FIG. 2 is an explanatory diagram for explaining a cooling execution phase in the system 10. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. 1 illustrates a schematic diagram of an example of a system 10. FIG. 2 is an explanatory diagram for explaining a learning phase in the system 10. FIG. 2 is an explanatory diagram for explaining a cooling execution phase in the system 10. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. FIG. 1 is a schematic diagram illustrating an example of a system 10. FIG. 2 is an explanatory diagram for explaining a learning phase in the system 10. FIG. 2 is an explanatory diagram for explaining a cooling execution phase in the system 10. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. 1 illustrates a schematic diagram of an example of a system 10. FIG. 2 is an explanatory diagram for explaining a learning phase in the system 10. FIG. 2 is an explanatory diagram for explaining a cooling execution phase in the system 10. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. FIG. 1 is a schematic diagram illustrating an example of a system 10. FIG. 2 is an explanatory diagram of a state in which communication between vehicles is being performed in this embodiment. FIG. 2 is an explanatory diagram for explaining a learning phase in the system 10. FIG. 2 is an explanatory diagram for explaining a cooling execution phase in the system 10. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. 1 illustrates a schematic diagram of an example of a system 10. FIG. 2 is an explanatory diagram for explaining a learning phase in the system 10. FIG. 2 is an explanatory diagram for explaining a cooling execution phase in the system 10. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. An example of a SoCBox 400 and a cooling unit 600 are shown in schematic form. 1 is a diagram illustrating an example of a hardware configuration of a computer 1200 that functions as a management server 100, a SoCBox 400, a cooling execution device 500, or a cooling device 700.

The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the invention as defined by the claims. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

First Embodiment
When an autonomous driving SoC (System Chip) performs advanced arithmetic processing, heat generation becomes an issue. Therefore, in this embodiment, Synchronized Burst Chilling, which is a technology that utilizes AI (Artificial Intelligence) to optimize rapid cooling of the SoC Box, is provided.

The SoCBox heats up quickly, making it difficult to perform advanced calculations in the vehicle (a challenge to fully autonomous driving). AI predicts heat dissipation from the SoCBox and cools it at the same time as it dissipates heat, preventing the SoCBox from getting too hot and enabling advanced calculations in the vehicle. It is expected that this technology can also be used to cool the battery, not just the SoCBox, and could be a solution to the problem of high temperatures caused by rapid charging.

FIG. 1 shows an example of a system 10. The system 10 includes a management server 100. The system 10 includes a SoCBox 400. The system 10 includes a cooling execution device 500. The system 10 includes a cooling unit 600.

The SoCBox 400, cooling execution device 500, and cooling unit 600 are mounted on a vehicle. The SoCBox 400 controls the automatic driving of the vehicle using the sensor values of multiple sensors mounted on the vehicle. Because automatic driving control of the vehicle places a very high processing load on the vehicle, the SoCBox 400 may become very hot. If the SoCBox 400 becomes too hot, it may not operate normally or may have a negative effect on the vehicle.

The cooling execution device 500 according to this embodiment predicts temperature changes in the SoCBox 400 and starts cooling the SoCBox 400 based on the temperature change. For example, the cooling execution device 500 immediately starts cooling the SoCBox 400 in response to predicting that the SoCBox 400 will start generating heat. By starting cooling before the SoCBox 400 starts generating heat or at the same time, it is possible to reliably prevent the SoCBox 400 from becoming too hot. Furthermore, it is possible to reduce the energy required for cooling compared to constantly cooling the SoCBox 400.

The cooling execution device 500 may use AI to predict temperature changes in the SoCBox 400. Learning of temperature changes in the SoCBox 400 may be performed by using data collected by the vehicle 200. For example, the management server 100 collects data from the vehicle 200 and performs the learning. The entity that performs the learning is not limited to the management server 100, and may be another device.

Vehicle 200 is equipped with SoCBox 400 and temperature sensor 40 that measures the temperature of SoCBox 400. SoCBox 400 controls the autonomous driving of vehicle 200 using sensor values from multiple sensors equipped in vehicle 200 and external information received from multiple types of servers 30. Server 30 may be an example of an external device. Examples of multiple types of servers 30 include a server that provides traffic information and a server that provides weather information. SoCBox 400 transmits to management server 100 the sensor values and external information used to control the autonomous driving, as well as the temperature change of SoCBox 400 when controlled.

The management server 100 performs learning using information received from one or more SoCBox 400. The management server 100 performs machine learning using information such as sensor values and external information acquired by the SoCBox 400, and the temperature change of the SoCBox 400 when the SoCBox 400 acquired this information, as learning data, to generate a learning model in which the information acquired by the SoCBox 400 is used as input and the temperature change of the SoCBox 400 is used as output.

Vehicle 300 is a vehicle having a cooling function according to this embodiment. Vehicle 300 is equipped with SoCBox 400, cooling execution device 500, and cooling section 600. Cooling execution device 500 may receive from management server 100 and store the learning model generated by management server 100.

The cooling execution device 500 obtains sensor values from multiple sensors mounted on the vehicle 300 and external information received from multiple types of servers 30, which are acquired by the SoCBox 400, from multiple sensors and multiple types of servers 30, or from the SoCBox 400, and predicts temperature changes in the SoCBox 400 by inputting the obtained information into a learning model.

The cooling execution device 500 starts cooling the SoCBox 400 using the cooling unit 600 when it predicts that the SoCBox 400 will start to generate heat or when it predicts that the temperature of the SoCBox 400 will rise above a predetermined threshold.

The SoCBox 400, the cooling execution device 500, the management server 100, and the server 30 may communicate via the network 20. The network 20 may include a vehicle network. The network 20 may include the Internet. The network 20 may include a LAN (Local Area Network). The network 20 may include a mobile communication network. The mobile communication network may conform to any of the following communication methods: 5G (5th Generation) communication method, LTE (Long Term Evolution) communication method, 3G (3rd Generation) communication method, and 6G (6th Generation) communication method or later.

FIG. 2 is an explanatory diagram for explaining the learning phase in the system 10. Here, examples of sensors 210 mounted on the vehicle 200 include a camera 211, a LiDAR (Light Detection and Ranging) 212, a millimeter wave sensor 213, an ultrasonic sensor 214, an IMU sensor 215, and a GNSS (Global Navigation Satellite System) sensor 216. The vehicle 200 does not have to be equipped with all of these, and may be equipped with some or other sensors.

SoCBox400 acquires sensor information from each sensor included in sensor 210. SoCBox400 may also perform communication via network 20, and receives external information from each of multiple servers 30 via network 20. SoCBox400 then uses the acquired information to execute autonomous driving control of vehicle 200.

The temperature sensor 40 measures the temperature change of the SoCBox 400. The SoCBox 400 transmits to the management server 100 the sensor information received from the sensor 210, the external information received from the server 30, and the temperature change measured by the temperature sensor 40 when the SoCBox 40 acquires this information and executes the automatic driving control.

The management server 100 includes an information acquisition unit 102, a model generation unit 104, and a model provision unit 106. The information acquisition unit 102 acquires various information. The management server 100 may receive information transmitted by the SoCBox 400.

The model generation unit 104 executes machine learning using the information acquired by the information acquisition unit 102 to generate a learning model. The model generation unit 104 executes machine learning using the information acquired by the SoCBox 400 and the temperature change of the SoCBox 400 when the SoCBox 400 acquired the information as learning data, thereby generating a learning model in which the information acquired by the SoCBox 400 is used as input and the temperature change of the SoCBox 400 is used as output.

The model providing unit 106 provides the learning model generated by the model generating unit 104. The model providing unit 106 may transmit the learning model to the cooling execution device 500 mounted on the vehicle 300.

The system 10 may be configured to predict the temperature change of each of the multiple parts of the SoCBox 400. In this case, the vehicle 200 may be equipped with multiple temperature sensors 40 that each measure the temperature change of each of the multiple parts of the SoCBox 400. The SoCBox 400 may transmit to the management server 100 the sensor information received from the sensor 210, the external information received from the server 30, and the temperature changes measured by the multiple temperature sensors 40 when the SoCBox 400 acquires the information and executes the autonomous driving control. The model generation unit 104 executes machine learning using the information acquired by the SoCBox 400 and the temperature changes of each of the multiple parts of the SoCBox 400 when the SoCBox 400 acquires the information as learning data, thereby generating a learning model that uses the information acquired by the SoCBox 400 as input and the temperature changes of each of the multiple parts of the SoCBox 400 as output.

FIG. 3 is an explanatory diagram for explaining the cooling execution phase in the system 10. Here, the sensors 310 mounted on the vehicle 300 are exemplified by a camera 311, a LiDAR 312, a millimeter wave sensor 313, an ultrasonic sensor 314, an IMU sensor 315, and a GNSS sensor 316. The vehicle 300 does not have to be equipped with all of these, and may be equipped with some or other sensors.

The cooling execution device 500 includes a model storage unit 502, an information acquisition unit 504, a prediction unit 506, and a cooling execution unit 508. The model storage unit 502 stores the learning model received from the management server 100. The information acquisition unit 504 acquires information acquired by the SoCBox 400.

The information acquisition unit 504 acquires the sensor information that the SoCBox 400 acquires from the sensor 310 from the sensor 310 or from the SoCBox 400. For example, the information acquisition unit 504 may receive from the SoCBox 400 the sensor information that the SoCBox 400 acquires from the sensor 310. The information acquisition unit 504 may receive from the sensor 310 the same sensor information that the SoCBox 400 acquires from the sensor 310. In this case, each sensor of the sensors 310 may transmit the sensor information to the SoCBox 400 and the cooling execution device 500, respectively.

The information acquisition unit 504 acquires the external information that the SoCBox 400 acquires from the server 30 from the server 30 or from the SoCBox 400. The information acquisition unit 504 may receive from the SoCBox 400 the external information that the SoCBox 400 received from the server 30. The information acquisition unit 504 may receive from the server 30 the same external information that the SoCBox 400 receives from the server 30. In this case, the server 30 may transmit the external information to both the SoCBox 400 and the cooling execution device 500.

The prediction unit 506 predicts the temperature change of the SoCBox 400. The prediction unit 506 may predict the temperature change of the SoCBox 400 using AI. For example, the prediction unit 506 predicts the temperature change of the SoCBox 400 by inputting the information acquired by the information acquisition unit 504 into a learning model stored in the model storage unit 502.

The cooling execution unit 508 starts cooling the SoCBox 400 based on the temperature change of the SoCBox 400 predicted by the prediction unit 506. For example, the cooling execution unit 508 starts cooling the SoCBox 400 in response to the prediction unit 506 predicting that the SoCBox 400 will start to generate heat. For example, the cooling execution unit 508 starts cooling the SoCBox 400 in response to the prediction unit 506 predicting that the temperature of the SoCBox 400 will become higher than a predetermined threshold.

The cooling execution unit 508 may use the cooling unit 600 to perform cooling of the SoCBox 400. The cooling unit 600 may cool the SoCBox 400 by air cooling means. The cooling unit 600 may cool the SoCBox 400 by water cooling means. The cooling unit 600 may cool the SoCBox 400 by liquid nitrogen cooling means.

The cooling unit 600 may include multiple types of cooling means. For example, the cooling unit 600 includes multiple types of air cooling means. For example, the cooling unit 600 includes multiple types of water cooling means. For example, the cooling unit 600 includes multiple types of liquid nitrogen cooling means. The cooling unit 600 may include multiple of one or multiple types of air cooling means, one or multiple types of water cooling means, and one or multiple liquid nitrogen cooling means.

The multiple cooling means may be arranged so that each cooling means cools a different part of the SoCBox 400. The prediction unit 506 may predict temperature changes in each of the multiple parts of the SoCBox 400 using information acquired by the information acquisition unit 504. The cooling execution unit 508 may start cooling the SoCBox 400 using a cooling means selected from the multiple cooling means that cool each of the multiple parts of the SoCBox 400 based on the prediction result by the prediction unit 506.

The cooling execution unit 508 may cool the SoCBox 400 using a cooling means according to the temperature of the SoCBox 400 predicted by the prediction unit 506. For example, the higher the temperature of the SoCBox 400, the more cooling means the cooling execution unit 508 uses to cool the SoCBox 400. As a specific example, when it is predicted that the temperature of the SoCBox 400 will exceed a first threshold, the cooling execution unit 508 starts cooling using one of the multiple cooling means, but when it is still predicted that the temperature of the SoCBox 400 will rise and exceed a second threshold, the cooling execution unit 508 increases the number of cooling means to be used.

The cooling execution unit 508 may use a more powerful cooling means to cool the SoCBox 400 as the temperature of the SoCBox 400 increases. For example, the cooling execution unit 508 may start cooling using air cooling means when it is predicted that the temperature of the SoCBox 400 will exceed a first threshold, start cooling using water cooling means when it is still predicted that the temperature of the SoCBox 400 will rise and exceed a second threshold, and start cooling using liquid nitrogen cooling means when it is still predicted that the temperature of the SoCBox 400 will rise and exceed a third threshold.

SoCBox400 may have multiple processing chips, each of which may be located at a different position on SoCBox400. Each of the multiple cooling means may be located at a position corresponding to each of the multiple processing chips.

For example, when the number of processing chips used changes depending on the control status of dynamic operation, cooling is performed by the cooling means corresponding to the processing chip being used, thereby achieving efficient cooling.

FIG. 4 shows an example of the SoCBox 400 and the cooling unit 600. FIG. 4 shows an example in which the cooling unit 600 is configured with a single cooling means. When the cooling execution device 500 predicts that the SoCBox 400 will start to generate heat or predicts that the temperature of the SoCBox 400 will exceed a predetermined threshold, the cooling unit 600 starts cooling, thereby cooling the entire SoCBox 400.

FIG. 5 shows an example of a schematic diagram of the SoCBox 400 and the cooling unit 600. FIG. 5 shows an example where the cooling unit 600 is configured with multiple cooling means for cooling each of the multiple parts of the SoCBox 400. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling.

FIG. 6 shows an example of the SoCBox 400 and the cooling unit 600. FIG. 6 shows an example in which the cooling unit 600 is configured with two types of cooling means. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling. In addition, the cooling execution device 500 increases the number of cooling means used as the temperature of the SoCBox 400 increases; in other words, in this example, first, cooling using one of the two types of cooling means is started, and when the temperature of the SoCBox 400 further increases, cooling using the other cooling means is started, thereby making it possible to efficiently use energy for cooling.

Second Embodiment
When an autonomous driving SoC (System on Chip) performs advanced arithmetic processing, heat generation becomes an issue. Therefore, in this embodiment, Synchronized Burst Chilling, which is a technology that utilizes AI (Artificial Intelligence) to optimize rapid cooling of the SoC Box, is provided.

FIG. 7 shows an example of a system 10. The system 10 includes a management server 100. The system 10 includes a SoCBox 400. The system 10 includes a cooling execution device 500. The system 10 includes a cooling unit 600.

The SoCBox 400, cooling execution device 500, and cooling unit 600 are mounted on a vehicle. The SoCBox 400 is a control device that controls the automatic driving of the vehicle using the sensor values of multiple sensors mounted on the vehicle. Because automatic driving control of the vehicle places a very high processing load on the vehicle, the SoCBox 400 can become very hot. If the SoCBox 400 becomes too hot, it may not operate normally or may have a negative effect on the vehicle.

The system 10 according to this embodiment predicts temperature changes in the SoCBox 400 based on location information of the vehicle having the cooling execution device 500 and temperature information of the SoCBox 400 held by the vehicle, and starts cooling the SoCBox 400 based on the temperature change. For example, the system 10 predicts heat generation in advance and immediately starts cooling the SoCBox 400 in places where the amount of processing is increased and heat generation is likely to occur, such as urban areas with many vehicles and pedestrians. By starting cooling before or at the same time as heat generation begins, it is possible to reliably prevent the SoCBox 400 from becoming too hot. Furthermore, the energy required for cooling can be reduced compared to when the SoCBox 400 is constantly cooled.

The system 10 may use AI to predict temperature changes in the SoCBox 400. Learning of temperature changes in the SoCBox 400 may be performed by using data collected by the vehicle 200. For example, the management server 100 collects data from the vehicle 200 and performs the learning. The entity that performs the learning is not limited to the management server 100, and may be another device.

Vehicle 300 is a vehicle having a cooling function according to this embodiment. Vehicle 300 is equipped with SoCBox 400, cooling execution device 500, and cooling unit 600. Cooling execution device 500 may receive from management server 100 and store the learning model generated by management server 100. Cooling execution device 500 may also receive from server 30 and store information related to the type of vehicle 300. The information related to the type of vehicle 300 may include information such as the model of vehicle 300, information related to the model and heat generation of SoCBox 400, and parameters for each model. Here, the parameters for each model include information such as information on models that are prone to heat generation in SoCBox 400, information on models that are unlikely to heat up in SoCBox 400, and information on cooling means that can be installed in each model.

The cooling execution device 500 obtains sensor values from multiple sensors mounted on the vehicle 300 and external information received from multiple types of servers 30, which are obtained by the SoCBox 400, from multiple sensors and multiple types of servers 30, or from the SoCBox 400, and inputs the obtained information into a learning model to predict temperature changes in the SoCBox 400. The cooling execution device 500 can also perform processing similar to the prediction processing performed by the management server 100, which will be described later.

The SoCBox 400, the cooling execution device 500, the management server 100, and the server 30 may communicate via a network 20. The network 20 may include a vehicle network. The network 20 may include the Internet. The network 20 may include a LAN (Local Area Network). The network 20 may include a mobile communication network. The mobile communication network may conform to any of the following communication methods: 5G (5th Generation) communication method, LTE (Long Term Evolution) communication method, 3G (3rd Generation) communication method, and 6G (6th Generation) communication method or later.

FIG. 8 is an explanatory diagram for explaining the learning phase in the system 10. Here, the following are exemplified as sensors 210 mounted on the vehicle 200: a camera 211, a LiDAR (Light Detection and Ranging) 212, a millimeter wave sensor 213, an ultrasonic sensor 214, an IMU sensor 215, a GNSS (Global Navigation Satellite System) sensor 216, and a GPS (Global Positioning System) sensor 217. The vehicle 200 does not have to be equipped with all of these, and may be equipped with some or other sensors.

The management server 100 includes an information acquisition unit 102, a model generation unit 104, a model provision unit 106, a creation unit 108, and a prediction unit 110.

The information acquisition unit 102 acquires various information. For example, the information acquisition unit 102 acquires location information of the vehicle 300 having the cooling execution device 500 and temperature information of the SoCBox 400 of the vehicle 300 from the cooling execution device 500. The information acquisition unit 102 also acquires location information of the vehicle 300 having the cooling execution device 500, temperature information of the SoCBox 400 of the vehicle 300, and information on the type of the vehicle 300 from the cooling execution device 500. The location information may be acquired from a GNSS sensor or a GPS sensor. The location information may include information on the driving route and destination of the vehicle 300. The information acquisition unit 102 may acquire various information based on a predetermined timing or period. The management server 100 may receive information transmitted by the SoCBox 400.

The creation unit 108 creates a map showing the relationship between the position of the vehicle 300 and the temperature of the SoCBox 400 from the position information of the vehicle 300 having the cooling execution device 500 acquired by the information acquisition unit 102 and the temperature information of the SoCBox 400 of the vehicle 300. The creation unit 108 also creates a map showing the relationship between the position of the vehicle 300 and the temperature of the SoCBox 400 for each type of vehicle 300 from the position information of the vehicle 300 having the cooling execution device 500 acquired by the information acquisition unit 102, the temperature information of the SoCBox 400 of the vehicle 300, and information related to the type of vehicle 300.

The prediction unit 110 predicts the temperature change of the SoCBox 400 based on the location information of the vehicle 300 having the cooling execution device 500 acquired by the information acquisition unit 102 and the temperature information of the SoCBox 400 of the vehicle 300. At this time, the prediction unit 110 may make the prediction using the location information of the vehicle 300 having the cooling execution device 500 and the temperature information of the SoCBox 400 of the vehicle 300 acquired by the information acquisition unit 102 in the past.

For example, the prediction unit 110 uses the accumulated location information of the vehicle 300 having the cooling execution device 500 and the temperature information of the SoCBox 400 possessed by the vehicle 300 to predict a temperature change in the SoCBox 400 based on the location information of the vehicle having the cooling execution device 500 acquired by the information acquisition unit 102 and the temperature information of the SoCBox 400 possessed by the vehicle 300. For example, based on data from previously acquired information showing that the amount of heat generated increases by about 20% in urban areas compared to normal times, the prediction unit 110 predicts a temperature change based on the fact that the amount of heat generated will increase by about 20% when the location information of the vehicle 300 is in an urban area.

The prediction unit 110 also predicts a temperature change in the SoCBox 400 based on the location information of the vehicle 300 having the cooling execution device 500 acquired by the information acquisition unit 102, the temperature information of the SoCBox 400 possessed by the vehicle 300, and a map created by the creation unit 108 that shows the relationship between the location of the vehicle 300 and the temperature of the SoCBox 400. The prediction unit 110 also predicts a temperature change in the SoCBox 400 based on the location information of the vehicle 300 having the cooling execution device 500 acquired by the information acquisition unit 102, the temperature information of the SoCBox 400 possessed by the vehicle 300, and a map created by the creation unit 108 that shows the relationship between the location of the vehicle 300 for the type of vehicle 300 and the temperature of the SoCBox 400.

The temperature change of the SoCBox 400 predicted by the prediction unit 110 includes the temperature change over time in the SoCBox 400 possessed by the vehicle 300. For example, the prediction unit 110 may predict the temperature change over time in the SoCBox 400 possessed by the vehicle 300 on the travel route from the current position of the vehicle 300 to the destination.

The system 10 may be configured to predict the temperature change of each of the multiple parts of the SoCBox 400. In this case, the vehicle 200 may be provided with multiple temperature sensors 40 that each measure the temperature change of each of the multiple parts of the SoCBox 400. The SoCBox 400 may transmit to the management server 100 the sensor information received from the sensor 210, the external information received from the server 30, and the temperature changes measured by the multiple temperature sensors 40 when the SoCBox 400 acquires the information and executes the autonomous driving control. The model generation unit 104 executes machine learning using the information acquired by the SoCBox 400 and the temperature changes of each of the multiple parts of the SoCBox 400 when the SoCBox 400 acquires the information as learning data, thereby generating a learning model that uses the information acquired by the SoCBox 400 as input and the temperature changes of each of the multiple parts of the SoCBox 400 as output.

FIG. 9 is an explanatory diagram for explaining the cooling execution phase in the system 10. Here, examples of sensors 310 mounted on the vehicle 300 include a camera 311, a LiDAR 312, a millimeter wave sensor 313, an ultrasonic sensor 314, an IMU sensor 315, a GNSS sensor 316, and a GPS sensor 317. The vehicle 300 does not have to be equipped with all of these, and may be equipped with some or other sensors other than these.

The information acquisition unit 504 acquires the prediction results of the temperature change of the SoCBox 400 predicted by the prediction unit 110 of the management server 100 from the management server 100.

The prediction unit 506 predicts temperature changes in the SoCBox 400. The prediction unit 506 may predict temperature changes in the SoCBox 400 using AI. For example, the prediction unit 506 predicts temperature changes in the SoCBox 400 by inputting the information acquired by the information acquisition unit 504 into a learning model stored in the model storage unit 502. The prediction unit 506 can also perform the same prediction processing as that performed by the prediction unit 110 of the management server 100.

The cooling execution unit 508 starts cooling the SoCBox 400 based on the predicted temperature change of the SoCBox 400 acquired by the information acquisition unit 504. For example, the cooling execution unit 508 starts cooling the SoCBox 400 a predetermined time before the SoCBox 400 starts to generate heat, using the predicted temperature change of the SoCBox 400 acquired by the information acquisition unit 504. Also, for example, the cooling execution unit 508 starts cooling the SoCBox 400 a predetermined time before the timing when the SoCBox 400 is predicted to reach or exceed a predetermined temperature, using the predicted temperature change of the SoCBox 400 acquired by the information acquisition unit 504. Also, for example, the cooling execution unit 508 uses the predicted temperature change of the SoCBox 400 acquired by the information acquisition unit 504 to start cooling the SoCBox 400 when the point where the SoCBox 400 is predicted to start generating heat is within a predetermined distance from the current location of the vehicle 300.

The cooling execution unit 508 uses the predicted temperature change of the SoCBox 400 acquired by the information acquisition unit 504 to start cooling the SoCBox 400 using one or more cooling means selected from a plurality of types of cooling means according to the temperature change of the SoCBox 400. The cooling execution unit 508 may use the cooling unit 600 to perform cooling of the SoCBox 400. The cooling unit 600 may cool the SoCBox 400 by air cooling means. The cooling unit 600 may cool the SoCBox 400 by water cooling means. The cooling unit 600 may cool the SoCBox 400 by liquid nitrogen cooling means.

FIG. 10 shows an example of the SoCBox 400 and the cooling unit 600. FIG. 10 shows an example in which the cooling unit 600 is configured with a single cooling means. When the cooling execution device 500 predicts that the SoCBox 400 will start to generate heat or predicts that the temperature of the SoCBox 400 will exceed a predetermined threshold, the cooling unit 600 starts cooling, thereby cooling the entire SoCBox 400.

FIG. 11 shows an example of a schematic diagram of a SoCBox 400 and a cooling unit 600. FIG. 11 shows an example where the cooling unit 600 is configured with multiple cooling means for cooling each of the multiple parts of the SoCBox 400. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling.

The cooling execution device 500 of the system 10 can also realize efficient cooling according to the location of the vehicle 300 by starting cooling of the SoCBox 400 based on the temperature change of the SoCBox 400 predicted based on the location information of the vehicle 300 and the temperature information of the SoCBox 400.

The cooling execution device 500 of the system 10 can also realize efficient cooling according to the position of the vehicle 300 by starting cooling of the SoCBox 400 based on a change in temperature of the SoCBox 400 predicted based on the position information of the vehicle 300, the temperature information of the SoCBox 400, and a map showing the relationship between the position of the vehicle 300 and the temperature of the SoCBox 400.

In addition, the cooling execution device 500 of the system 10 can realize efficient cooling according to the location and model of the vehicle 300 by starting cooling of the SoCBox 400 based on a change in temperature of the SoCBox 400 predicted based on location information of the vehicle 300, information on the type of the vehicle 300, temperature information of the SoCBox 400, and a map showing the relationship between the location of the vehicle 300 and the temperature of the SoCBox 400.

In addition, the cooling execution device 500 of the system 10 can reduce the possibility of overheating and perform efficient cooling by starting to cool the SoCBox 400 a predetermined time before the SoCBox 400 starts to generate heat based on the predicted temperature change of the SoCBox 400.

The cooling execution device 500 of the system 10 also uses the predicted temperature change of the SoCBox 400 to perform cooling using multiple cooling means in response to the temperature change of the SoCBox 400, thereby achieving efficient cooling in response to the temperature change.

In addition, the cooling execution device 500 of the system 10 uses the predicted temperature change of the SoCBox 400 to perform cooling using water cooling means and liquid nitrogen cooling means in response to the temperature change of the SoCBox 400, thereby achieving efficient cooling using cooling means that respond to temperature changes.

FIG. 12 shows an example of the SoCBox 400 and the cooling unit 600. FIG. 12 shows an example in which the cooling unit 600 is configured with two types of cooling means. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling. In addition, the cooling execution device 500 increases the number of cooling means used as the temperature of the SoCBox 400 increases; in other words, in this example, first, cooling using one of the two types of cooling means is started, and when the temperature of the SoCBox 400 further increases, cooling using the other cooling means is started, thereby making it possible to efficiently use energy for cooling.

Third Embodiment
When an autonomous driving SoC (System on Chip) performs advanced arithmetic processing, heat generation becomes an issue. Therefore, in this embodiment, Synchronized Burst Chilling, which is a technology that utilizes AI (Artificial Intelligence) to optimize rapid cooling of the SoC Box, is provided.

The SoCBox heats up quickly, making it difficult to perform advanced calculations in the vehicle (a challenge to fully autonomous driving). For example, even if the vehicle is in the same location, changes in the environment such as temperature, weather, and traffic conditions can cause the amount of heat generated by the SoCBox to change, leading to overheating. This is because changes in traffic and weather conditions increase the amount of detection by various sensors and make autonomous driving control more complicated. In such cases, AI can predict heat dissipation from the SoCBox and cool it at the same time as it dissipates heat, preventing the SoCBox from getting too hot and enabling advanced calculations in the vehicle. It is expected that this technology can be used to cool not only the SoCBox, but also the battery, making it a potential solution to the problem of high temperatures caused by rapid charging.

FIG. 13 shows an example of a system 10. The system 10 includes a management server 100. The system 10 includes a SoCBox 400. The system 10 includes a cooling execution device 500. The system 10 includes a cooling unit 600.

The system 10 according to this embodiment predicts temperature changes in the SoCBox 400 based on location information of the vehicle 300 having the cooling execution device 500, temperature information of the SoCBox 400 in the vehicle 300, information on traffic conditions, and weather information, and starts cooling the SoCBox 400 based on the temperature change. For example, the system 10 predicts heat generation in advance in situations where the amount of processing increases and heat generation is likely to occur in the SoCBox 400, such as during traffic jams or rainy weather, and starts cooling the SoCBox 400 immediately. By starting cooling before the heat generation starts or at the same time as the heat generation starts, it is possible to reliably prevent the SoCBox 400 from becoming too hot. Furthermore, the energy required for cooling can be reduced compared to when the SoCBox 400 is constantly cooled.

Vehicle 300 is a vehicle having a cooling function according to this embodiment. Vehicle 300 is equipped with SoCBox 400, cooling execution device 500, and cooling section 600. Cooling execution device 500 may receive from management server 100 and store the learning model generated by management server 100. Cooling execution device 500 may also receive and store information relating to traffic conditions (traffic information) from a server that provides traffic information. The information relating to traffic conditions includes information such as the traffic congestion status of vehicles, the number of pedestrians, whether there are any accidents, whether there are any construction works, and whether there are any events.

The cooling execution device 500 may also receive and store weather information from a server that provides weather information. The weather information includes information such as weather, temperature, humidity, and wind speed. The cooling execution device 500 may also receive and store information related to the type of vehicle 300 from the server 30. The information related to the type of vehicle 300 may include information such as the model of the vehicle 300, information related to the model and heat generation of the SoCBox 400, and parameters for each model.

FIG. 14 is an explanatory diagram for explaining the learning phase in the system 10. Here, the sensors 210 mounted on the vehicle 200 are exemplified by a camera 211, a LiDAR (Light Detection and Ranging) 212, a millimeter wave sensor 213, an ultrasonic sensor 214, an IMU sensor 215, a GNSS (Global Navigation Satellite System) sensor 216, and a GPS (Global Positioning System) sensor 217. The vehicle 200 does not have to be equipped with all of these, and may be equipped with some or other sensors.

The information acquisition unit 102 acquires various types of information. For example, the information acquisition unit 102 acquires location information of the vehicle 300 having the cooling execution device 500, temperature information of the SoCBox 400 possessed by the vehicle 300, information regarding traffic conditions, and weather information. Here, the location information may be acquired from a GNSS sensor or a GPS sensor. The location information may also include information regarding the driving route and destination of the vehicle 300.

For example, the information acquisition unit 102 acquires location information of the vehicle 300 having the cooling execution device 500, temperature information of the SoCBox 400 of the vehicle 300, information on traffic conditions, and weather information from the cooling execution device 500. Also, for example, the information acquisition unit 102 acquires weather information from a server that provides weather information. Also, for example, the information acquisition unit 102 acquires information on traffic conditions from a server that provides traffic information.

The information acquisition unit 102 also acquires information relating to the type of vehicle 300 from the cooling execution device 500. The information relating to the type of vehicle may include information such as the model of the vehicle 300, information relating to the model and heat generation of the SoCBox 400, and parameters for each model. The information acquisition unit 102 may acquire various information based on a specified timing or period. The management server 100 may receive information transmitted by the SoCBox 400.

The creation unit 108 creates a map showing the relationship between the location of the vehicle 300, the information on traffic conditions, the weather information, and the temperature of the SoCBox 400 from the location information of the vehicle 300 having the cooling execution device 500 acquired by the information acquisition unit 102, the temperature information of the SoCBox 400 possessed by the vehicle 300, the information on traffic conditions, and the weather information. For example, the creation unit 108 creates a map showing the relationship between the location of the vehicle 300 and the temperature of the SoCBox 400 for each piece of information on traffic conditions and weather information from the location information of the vehicle 300 having the cooling execution device 500 acquired by the information acquisition unit 102, the temperature information of the SoCBox 400 possessed by the vehicle 300, the information on traffic conditions, and the weather information.

The creation unit 108 also creates a map showing the relationship between the location of the vehicle 300 and the temperature of the SoCBox 400 for each type of vehicle 300, based on the location information of the vehicle 300 having the cooling execution device 500 acquired by the information acquisition unit 102, the temperature information of the SoCBox 400 possessed by the vehicle 300, and information regarding the type of vehicle 300.

The prediction unit 110 predicts the temperature change of the SoCBox 400 based on the location information of the vehicle 300 having the cooling execution device 500 acquired by the information acquisition unit 102, the temperature information of the SoCBox 400 possessed by the vehicle 300, the information on the traffic conditions, and the weather information. At this time, the prediction unit 110 may make the prediction using the location information of the vehicle 300 having the cooling execution device 500, the temperature information of the SoCBox 400 possessed by the vehicle 300, the information on the traffic conditions, and the weather information acquired by the information acquisition unit 102 in the past.

For example, the prediction unit 110 uses the accumulated location information of the vehicle 300 having the cooling execution device 500, temperature information of the SoCBox 400 possessed by the vehicle 300, information on traffic conditions, and weather information to predict the temperature change of the SoCBox 400 based on the location information of the vehicle 300 having the cooling execution device 500 acquired by the information acquisition unit 102, temperature information of the SoCBox 400 possessed by the vehicle 300, information on traffic conditions, and weather information.

For example, based on data from previously acquired information indicating that the amount of heat generated increases by approximately 20% when it is raining compared to when it is sunny, the prediction unit 110 predicts a temperature change when the weather information indicates rain, taking into account that the amount of heat generated will increase by approximately 20%. Also, based on data from previously acquired information indicating that the amount of heat generated will increase by approximately 30% when there is congestion compared to normal conditions, the prediction unit 110 predicts a temperature change when the traffic conditions are congested, taking into account that the amount of heat generated will increase by approximately 30%.

The prediction unit 110 also predicts the temperature change of the SoCBox 400 based on the location information of the vehicle 300 having the cooling execution device 500 acquired by the information acquisition unit 102, the temperature information of the SoCBox 400 possessed by the vehicle 300, information on traffic conditions, weather information, and a map created by the creation unit 108 showing the relationship between the location of the vehicle 300, information on traffic conditions, weather information, and the temperature of the SoCBox 400.

The prediction unit 110 also predicts the temperature change of the SoCBox 400 based on the location information of the vehicle 300 having the cooling execution device 500 acquired by the information acquisition unit 102, the temperature information of the SoCBox 400 of the vehicle 300, the information on traffic conditions, the weather information, and a map created by the creation unit 108 that shows the relationship between the location of the vehicle 300 and the temperature of the SoCBox 400 for each of the information on traffic conditions and the weather information.

The prediction unit 110 also predicts the temperature change of the SoCBox 400 based on the position information of the vehicle 300 having the cooling execution device 500 acquired by the information acquisition unit 102, the temperature information of the SoCBox 400 possessed by the vehicle 300, and the map created by the creation unit 108 that shows the relationship between the position of the vehicle 300 and the temperature of the SoCBox 400 for each type of vehicle 300.

FIG. 15 is an explanatory diagram for explaining the cooling execution phase in the system 10. Here, examples of sensors 310 mounted on the vehicle 300 include a camera 311, a LiDAR 312, a millimeter wave sensor 313, an ultrasonic sensor 314, an IMU sensor 315, a GNSS sensor 316, and a GPS sensor 317. The vehicle 300 does not have to be equipped with all of these, and may not have some of them, or may have sensors other than these.

FIG. 16 shows an example of the SoCBox 400 and the cooling unit 600. FIG. 16 shows an example in which the cooling unit 600 is configured with one cooling means. When the cooling execution device 500 predicts that the SoCBox 400 will start to generate heat or predicts that the temperature of the SoCBox 400 will exceed a predetermined threshold, the cooling unit 600 starts cooling, thereby cooling the entire SoCBox 400.

FIG. 17 shows an example of a schematic diagram of a SoCBox 400 and a cooling unit 600. FIG. 17 shows an example where the cooling unit 600 is configured with multiple cooling means for cooling each of the multiple parts of the SoCBox 400. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling.

In addition, the cooling execution device 500 of the system 10 starts cooling the SoCBox 400 based on temperature changes in the SoCBox 400 predicted based on the vehicle 300's location information, SoCBox 400 temperature information, traffic condition information, and weather information, thereby enabling efficient cooling in response to changes in the SoCBox 400 temperature when the amount of detection by various sensors increases due to changes in the environment or when autonomous driving control becomes more complex.

The cooling execution device 500 of the system 10 can also realize efficient cooling according to the vehicle 300's location and dynamic environment by initiating cooling of the SoCBox 400 based on a predicted change in temperature of the SoCBox 400 based on the vehicle 300's location information, SoCBox 400 temperature information, traffic condition information, weather information, and a map showing the relationship between the vehicle 300's location information, traffic condition information, weather information, and the SoCBox 400 temperature.

The cooling execution device 500 of the system 10 also creates a map showing the relationship between the location information of the vehicle 300 and the temperature of the SoCBox 400 for each piece of information related to traffic conditions and weather information, predicts temperature changes in the SoCBox 400, and starts cooling the SoCBox 400, thereby achieving efficient cooling according to the location of the vehicle 300 for each dynamic environment.

In addition, the cooling execution device 500 of the system 10 starts cooling the SoCBox 400 based on a change in temperature of the SoCBox 400 predicted based on the location information of the vehicle 300, the temperature information of the SoCBox 400, information on traffic conditions, weather information, the vehicle type of the vehicle 300, the location information of the vehicle 300, information on traffic conditions, weather information, and a map showing the relationship with the temperature of the SoCBox 400, thereby realizing efficient cooling according to the vehicle type and location of the vehicle 300 and the dynamic environment.

FIG. 18 shows an example of the SoCBox 400 and the cooling unit 600. FIG. 18 shows an example in which the cooling unit 600 is configured with two types of cooling means. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling. Furthermore, the cooling execution device 500 increases the number of cooling means used as the temperature of the SoCBox 400 increases; in other words, in this example, first, cooling using one of the two types of cooling means is started, and when the temperature of the SoCBox 400 further increases, cooling using the other cooling means is started, thereby making it possible to efficiently use energy for cooling.

Fourth Embodiment
When an autonomous driving SoC (System on Chip) performs advanced arithmetic processing, heat generation becomes an issue. Therefore, in this embodiment, Synchronized Burst Chilling is provided, which is a technology that utilizes AI (Artificial Intelligence) to optimize rapid cooling of a SoCBox having multiple SoCs.

The SoCBox heats up quickly, making it difficult to perform advanced calculations in the vehicle (a challenge to fully autonomous driving). For example, changes in driving conditions can increase the amount of detection by various sensors and complicate autonomous driving control, which can cause the SoCBox to overheat. A SoCBox that has multiple SoCs (integrated circuits) does not heat up uniformly; for example, when a certain autonomous driving control is performed, only the SoC that controls that autonomous driving control will heat up. In such cases, AI can predict the heat dissipation and its location in the SoCBox, and simultaneously cool the location where heat dissipation occurs, preventing the SoCBox from becoming too hot and enabling advanced calculations in the vehicle. It is expected that this technology can be used not only for SoCBoxes, but also for cooling batteries, which could be a solution to the problem of high temperatures caused by rapid charging.

FIG. 19 shows an example of a system 10. The system 10 includes a management server 100. The system 10 includes a SoCBox 400. The system 10 includes a cooling execution device 500. The system 10 includes a cooling unit 600.

The SoCBox 400, cooling execution device 500, and cooling unit 600 are mounted on a vehicle. The SoCBox 400 is a control device that has multiple SoCs and controls the automatic driving of the vehicle using the sensor values of multiple sensors mounted on the vehicle. Because automatic driving control of the vehicle places a very high processing load on the vehicle, the SoCBox 400 can become very hot. If the SoCBox 400 becomes too hot, it may not operate normally or may have a negative effect on the vehicle.

System 10 according to this embodiment predicts temperature changes at each location of SoCBox 400 based on position information of the SoC in SoCBox 400, information related to the processing of the SoC, and information related to the driving status of the vehicle, and starts cooling SoCBox 400 based on the temperature changes at each location. For example, system 10 predicts the heat generation and its location that will occur for each of various control processes such as driving straight, turning right or left, stopping, and situation judgment using various sensors, and immediately starts cooling SoCBox 400. By starting cooling before or at the same time as heat generation begins, it is possible to reliably prevent SoCBox 400 from becoming too hot. In addition, the energy required for cooling can be reduced compared to when SoCBox 400 is constantly cooled.

The system 10 may use AI to predict temperature changes at each location of the SoCBox 400. Learning of temperature changes at each location of the SoCBox 400 may be performed by using data collected by the vehicle 200. For example, the management server 100 collects data from the vehicle 200 and performs the learning. The entity that performs the learning is not limited to the management server 100, and may be another device.

Vehicle 200 is equipped with SoCBox400 and temperature sensor 40 that measures the temperature at each position of SoCBox400. SoCBox400 controls the autonomous driving of vehicle 200 using sensor values from multiple sensors equipped in vehicle 200 and external information received from multiple types of servers 30. SoCBox400 also stores location information of the SoCs contained in SoCBox400, information related to the processing of each SoC, and information related to the driving status of vehicle 300. Here, information related to the processing of each SoC refers to information on the processing and control performed by each SoC, and includes information on the processing controlled by each SoC, such as acceleration, deceleration, turning right or left, stopping, vehicle detection, pedestrian detection, obstacle detection, detection by various sensors, and various calculations. Furthermore, information on the driving status of the vehicle 300 refers to information on the driving status and operation status of the vehicle 300, and includes information on processing such as acceleration, deceleration, right and left turns, stopping, vehicle detection, pedestrian detection, obstacle detection, detection by various sensors, and various calculations. Note that the above-mentioned processing contents and driving status are only examples, and processing and driving status other than those described are also included. The server 30 may be an example of an external device. Examples of multiple types of servers 30 include a server that provides traffic information and a server that provides weather information. The SoCBox 400 transmits to the management server 100 sensor values and external information used to control the autonomous driving, as well as temperature changes at each position of the SoCBox 400 when controlled.

The management server 100 performs learning using information received from one or more SoCBox 400. The management server 100 performs machine learning using information such as sensor values and external information acquired by the SoCBox 400, and the temperature change at each position on the SoCBox 400 when the SoCBox 400 acquired this information, as learning data, to generate a learning model in which the information acquired by the SoCBox 400 is used as input and the temperature change at each position on the SoCBox 400 is used as output.

The cooling execution device 500 may also store location information of each SoC in the SoCBox 400, information regarding the processing of each SoC, and information regarding the driving status of the vehicle 300, which are acquired from the SoCBox 400.

The cooling execution device 500 obtains sensor values from multiple sensors mounted on the vehicle 300 and external information received from multiple types of servers 30, which are obtained by the SoCBox 400, from multiple sensors and multiple types of servers 30, or from the SoCBox 400, and inputs the obtained information into a learning model to predict temperature changes at each position of the SoCBox 400. The cooling execution device 500 can also perform processing similar to the prediction processing performed by the management server 100, which will be described later.

The cooling execution device 500 starts cooling the SoCBox 400 using the cooling unit 600 when it predicts that the SoCBox 400 will start to generate heat, or when it predicts that the temperature at each position on the SoCBox 400 will exceed a predetermined threshold value.

FIG. 20 is an explanatory diagram for explaining the learning phase in the system 10. Here, the sensors 210 mounted on the vehicle 200 are exemplified by a camera 211, a LiDAR (Light Detection and Ranging) 212, a millimeter wave sensor 213, an ultrasonic sensor 214, an IMU sensor 215, a GNSS (Global Navigation Satellite System) sensor 216, and a GPS (Global Positioning System) sensor 217. The vehicle 200 does not have to be equipped with all of these, and may be equipped with some or other sensors.

SoCBox400 acquires sensor information from each sensor included in sensor 210. SoCBox400 may also perform communication via network 20, and receives external information from each of multiple servers 30 via network 20. SoCBox400 then uses the acquired information to execute automatic driving control of vehicle 200. SoCBox400 also stores location information for each SoC it possesses.

Temperature sensor 40 measures temperature changes at each location on SoCBox 400. SoCBox 400 transmits to management server 100 the sensor information received from sensor 210, the external information received from server 30, and the temperature changes at each location measured by temperature sensor 40 when it acquires this information and executes automatic driving control.

The management server 100 includes an information acquisition unit 102, a model generation unit 104, a model provision unit 106, and a prediction unit 110.

The information acquisition unit 102 acquires various information. For example, the information acquisition unit 102 acquires position information of each SoC in the SoCBox 400, information on the processing of each SoC, and information on the driving status of the vehicle 300. For example, the information acquisition unit 102 acquires position information of each SoC in the SoCBox 400, information on the processing of each SoC, and information on the driving status of the vehicle 300 from the cooling execution device 500. For example, the information acquisition unit 102 may acquire the position information of each SoC by identifying the position of each SoC using information such as the manufacturer and model number of the SoCBox 400. The information acquisition unit 102 may acquire various information based on a predetermined timing or period. The management server 100 may receive information transmitted by the SoCBox 400.

The model generation unit 104 executes machine learning using the information acquired by the information acquisition unit 102 to generate a learning model. The model generation unit 104 executes machine learning using the information acquired by SoCBox 400 and the temperature change at each position on SoCBox 400 when SoCBox 400 acquired the information as learning data, thereby generating a learning model in which the information acquired by SoCBox 400 is used as input and the temperature change at each position on SoCBox 400 is used as output.

The prediction unit 110 predicts the temperature change at each position of the SoCBox 400 based on the position information of each SoC in the SoCBox 400, information on the processing of each SoC, and information on the driving status of the vehicle 300 acquired by the information acquisition unit 102. For example, the prediction unit 110 predicts the temperature change at each position of the SoCBox 400 using information on the driving status acquired by the information acquisition unit 102, such as information on the SoC that is driving while detecting obstacles and pedestrians, and information on the processing of each SoC, such as information on the SoC that controls obstacle detection, pedestrian detection, and driving, and position information of the SoC in the SoCBox 400.

The prediction unit 110 also predicts temperature changes over time at each location in the SoCBox 400 using the location information of each SoC in the SoCBox 400, information related to the processing of each SoC, and information related to the driving conditions of the vehicle 300 acquired by the information acquisition unit 102.

For example, the prediction unit 110 uses information on the driving situation acquired by the information acquisition unit 102, such as information that the vehicle is driving while detecting obstacles and pedestrians, and information on the processing of each SoC, such as information on the SoCs that control obstacle detection, pedestrian detection, and driving, and position information of the SoCs in the SoCBox 400, to predict temperature changes at each position of the SoCBox 400 if the driving situation continues.

FIG. 21 is an explanatory diagram for explaining the cooling execution phase in the system 10. Here, examples of sensors 310 mounted on the vehicle 300 include a camera 311, a LiDAR 312, a millimeter wave sensor 313, an ultrasonic sensor 314, an IMU sensor 315, a GNSS sensor 316, and a GPS sensor 317. The vehicle 300 does not have to be equipped with all of these, and may not have some of them, or may have sensors other than these.

The information acquisition unit 504 acquires the sensor information that the SoCBox 400 acquires from the sensor 310 from the sensor 310 or from the SoCBox 400. For example, the information acquisition unit 504 may receive from the SoCBox 400 the sensor information that the SoCBox 400 acquires from the sensor 310. The information acquisition unit 504 may receive from the sensor 310 the same sensor information that the SoCBox 400 acquires from the sensor 310. In this case, each sensor of the sensor 310 may transmit the sensor information to the SoCBox 400 and the cooling execution device 500, respectively. Also, for example, the information acquisition unit 504 acquires information on the position of each SoC in the SoCBox 400 from the SoCBox 400.

The information acquisition unit 504 acquires from the management server 100 the predicted results of the temperature change at each position of the SoCBox 400 predicted by the prediction unit 110 of the management server 100.

The cooling execution unit 508 starts cooling the SoCBox 400 based on the predicted results of temperature change at each position of the SoCBox 400 acquired by the information acquisition unit 504. For example, the cooling execution unit 508 starts cooling the positions of the SoCBox 400 where heat is generated, using the predicted results of temperature change at each position of the SoCBox 400 acquired by the information acquisition unit 504.

Also, for example, the cooling execution unit 508 uses the predicted temperature change results for each position of the SoCBox 400 acquired by the information acquisition unit 504 to start cooling the positions where the SoCBox 400 generates heat a predetermined time before the SoCBox 400 starts to generate heat.

Also, for example, the cooling execution unit 508 uses the predicted temperature change at each position of the SoCBox 400 acquired by the information acquisition unit 504 to start cooling the positions where heat is generated in the SoCBox 400 a predetermined time before the timing when each position of the SoCBox 400 is predicted to reach or exceed a predetermined temperature.

The cooling execution unit 508 uses the predicted results of the temperature change at each position of the SoCBox 400 acquired by the information acquisition unit 504 to start cooling the positions where heat is generated in the SoCBox 400 using one or more cooling means selected from a plurality of types of cooling means according to the temperature change at each position of the SoCBox 400. The cooling execution unit 508 may use the cooling unit 600 to perform cooling of the SoCBox 400. The cooling unit 600 may cool the SoCBox 400 by air cooling means. The cooling unit 600 may cool the SoCBox 400 by water cooling means. The cooling unit 600 may cool the positions where heat is generated in the SoCBox 400 by liquid nitrogen cooling means.

The multiple cooling means may be arranged so that each cooling means cools a different part of SoCBox400. The prediction unit 506 may predict temperature changes in each of the multiple parts of SoCBox400 using information acquired by the information acquisition unit 504. The cooling execution unit 508 may start cooling the location where heat is generated in SoCBox400 using a cooling means selected from the multiple cooling means that cool each of the multiple parts of SoCBox400 based on the prediction result by the prediction unit 506.

The cooling execution unit 508 may cool the SoCBox 400 using a cooling means according to the temperature of the SoCBox 400 predicted by the prediction unit 506. For example, the higher the temperature of the SoCBox 400, the more cooling means the cooling execution unit 508 uses to cool the location where heat is generated in the SoCBox 400. As a specific example, when it is predicted that the temperature of the SoCBox 400 will exceed a first threshold, the cooling execution unit 508 starts cooling using one of the multiple cooling means, but when it is still predicted that the temperature of the SoCBox 400 will rise and exceed a second threshold, the cooling execution unit 508 increases the number of cooling means to be used.

FIG. 22 shows an example of the SoCBox 400 and the cooling unit 600. FIG. 22 shows an example in which the cooling unit 600 is configured with one cooling means. When the cooling execution device 500 predicts that the SoCBox 400 will start to generate heat or predicts that the temperature of the SoCBox 400 will exceed a predetermined threshold, the cooling unit 600 starts cooling, thereby cooling the entire SoCBox 400.

FIG. 23 shows an example of a schematic diagram of a SoCBox 400 and a cooling unit 600. FIG. 23 shows an example where the cooling unit 600 is configured with multiple cooling means for cooling each of the multiple parts of the SoCBox 400. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling.

The cooling execution device 500 of the system 10 starts cooling the locations where heat is generated in the SoCBox 400 based on the location information of the SoC in the SoCBox 400, information related to the control of the SoC, and the predicted temperature change at each location of the SoCBox 400, which is predicted from the driving conditions of the vehicle 300. This allows the cooling of only the locations that require cooling, thereby achieving efficient cooling.

In addition, the cooling execution device 500 of the system 10 uses the location information of the SoC in the SoCBox 400, information related to the control of the SoC, and the driving conditions of the vehicle 300 to predict temperature changes over time at each location of the SoCBox 400, and starts cooling at locations where heat is generated in the SoCBox 400, thereby cooling only the locations that require cooling at an effective timing, thereby achieving efficient cooling.

In addition, the cooling execution device 500 of the system 10 uses the predicted temperature change at each location of the SoCBox 400, which is predicted from the location information of the SoC in the SoCBox 400, information related to the control of the SoC, and the driving conditions of the vehicle 300, to start cooling the locations where heat will occur in the SoCBox 400 before heat generation actually occurs, thereby preventing overheating and cooling only the areas that need cooling, thereby achieving efficient cooling.

In addition, the cooling execution device 500 of the system 10 uses the predicted temperature change at each position of the SoCBox 400 to perform cooling using multiple cooling means according to the temperature change at each position of the SoCBox 400, thereby achieving efficient cooling in response to temperature changes.

In addition, the cooling execution device 500 of the system 10 uses the predicted temperature change at each position of the SoCBox 400 to perform cooling using water cooling means and liquid nitrogen cooling means according to the temperature change at each position of the SoCBox 400, thereby achieving efficient cooling using cooling means that correspond to the temperature change.

FIG. 24 shows an example of the SoCBox 400 and the cooling unit 600. FIG. 24 shows an example in which the cooling unit 600 is configured with two types of cooling means. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling. Furthermore, the cooling execution device 500 increases the number of cooling means used as the temperature of the SoCBox 400 increases; in other words, in this example, first cooling using one of the two types of cooling means is started, and when the temperature of the SoCBox 400 further increases, cooling using the other cooling means is started, thereby making it possible to efficiently use energy for cooling.

Fifth embodiment
When an autonomous driving SoC (System on Chip) performs advanced arithmetic processing, heat generation becomes an issue. Therefore, in this embodiment, Synchronized Burst Chilling, which is a technology that utilizes AI (Artificial Intelligence) to optimize rapid cooling of the SoC Box, is provided.

FIG. 25 shows an example of a system 10. The system 10 includes a management server 100. The system 10 includes a SoCBox 400. The system 10 includes a cooling execution device 500. The system 10 includes a cooling unit 600.

The vehicle 200 is equipped with a SoCBox 400 and a temperature sensor 40 that measures the temperature of the SoCBox 400. The SoCBox 400 controls the autonomous driving of the vehicle 200 using sensor values from multiple sensors equipped in the vehicle 200 and external information received from multiple types of servers 30. The server 30 may be an example of an external device. Examples of multiple types of servers 30 include a server that provides traffic information and a server that provides weather information. The SoCBox 400 transmits to the management server 100 the sensor values and external information used to control the autonomous driving, as well as the temperature change of the SoCBox 400 when controlled.

FIG. 26 is an explanatory diagram for explaining the learning phase in the system 10. Here, examples of sensors 210 mounted on the vehicle 200 include a camera 211, a LiDAR (Light Detection and Ranging) 212, a millimeter wave sensor 213, an ultrasonic sensor 214, an IMU sensor 215, and a GNSS (Global Navigation Satellite System) sensor 216. The vehicle 200 does not have to be equipped with all of these, and may be equipped with some or other sensors.

FIG. 27 is an explanatory diagram for explaining the cooling execution phase in the system 10. Here, the sensors 310 mounted on the vehicle 300 are exemplified by a camera 311, a LiDAR 312, a millimeter wave sensor 313, an ultrasonic sensor 314, an IMU sensor 315, and a GNSS sensor 316. The vehicle 300 does not have to be equipped with all of these, and may be equipped with some or other sensors.

The cooling execution device 500 includes a detection unit 501, a model storage unit 502, an information acquisition unit 504, a prediction unit 506, and a cooling execution unit 508. The model storage unit 502 stores the learning model received from the management server 100. The information acquisition unit 504 acquires information acquired by the SoCBox 400.

The detection unit 501 detects the temperature of a control device (SoCBox400) mounted on a vehicle that controls the automatic driving of the vehicle. The detection unit 501 may also detect the temperature of each of multiple parts of the SoCBox400. For example, the detection unit 501 can detect the temperature of one or multiple SoCBox400s, detect the occurrence of an increase or decrease in temperature, and detect changing temperature values.

The prediction unit 506 predicts temperature changes in the control device (SoCBox 400) mounted on the vehicle that controls the vehicle's autonomous driving. The prediction unit 506 may predict temperature changes in the SoCBox 400 using AI. For example, the prediction unit 506 predicts temperature changes in the SoCBox 400 by inputting information acquired by the information acquisition unit 504 into a learning model stored in the model storage unit 502. Furthermore, the prediction unit 506 may predict temperature changes in each of multiple parts of the control device (SoCBox 400). For example, the prediction unit 506 can predict the occurrence of a temperature rise or fall in one or multiple SoCBoxes 400, or predict the numerical value of the changing temperature.

The cooling execution unit 508 executes cooling of the control device (SoCBox 400) using a predetermined cooling means based on the time that the temperature detected by the detection unit 501 continues to be equal to or higher than the predetermined temperature. Specifically, when the time that the temperature continues to be equal to or higher than the predetermined temperature exceeds a predetermined threshold, the cooling execution unit 508 can execute cooling using a cooling means including one or more types of air cooling means, one or more types of water cooling means, and a liquid nitrogen cooling means. For example, when the temperature detected by the detection unit 501 continues to be equal to or higher than the predetermined temperature for a time that exceeds a predetermined threshold (for example, the time that the temperature continues to be equal to or higher than the predetermined temperature for 10 minutes or more), the cooling execution unit 508 may execute cooling of the control device using a predetermined cooling means (for example, air cooling means, water cooling means, liquid nitrogen cooling means, etc.). Note that the predetermined threshold (time) for the time that the temperature continues to be equal to or higher than the predetermined temperature described above is a condition that can be set arbitrarily and is not limited.

The cooling execution unit 508 may also perform rapid cooling when the temperature exceeds a predetermined threshold. For example, the cooling execution unit 508 may perform rapid cooling when the temperature exceeds a predetermined threshold at which overheating occurs. Note that any threshold condition may be set as the predetermined threshold here.

The cooling execution unit 508 performs cooling using the cooling means described above, based on the time that the temperature change predicted by the prediction unit 506 will continue to be above a predetermined temperature. For example, the cooling execution unit 508 can perform cooling using the cooling means described above when traveling through a traveling location where the temperature change is predicted to continue to be above a predetermined temperature for more than a predetermined time.

FIG. 28 shows an example of a schematic diagram of the SoCBox 400 and the cooling unit 600. FIG. 28 shows an example where the cooling unit 600 is configured with a single cooling means. When the cooling execution device 500 predicts that the SoCBox 400 will start to generate heat or predicts that the temperature of the SoCBox 400 will exceed a predetermined threshold, the cooling unit 600 starts cooling, thereby cooling the entire SoCBox 400.

FIG. 29 shows an example of a schematic diagram of a SoCBox 400 and a cooling unit 600. FIG. 29 shows an example where the cooling unit 600 is configured with multiple cooling means for cooling each of the multiple parts of the SoCBox 400. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling.

FIG. 30 shows an example of the SoCBox 400 and the cooling unit 600. FIG. 30 shows an example in which the cooling unit 600 is composed of two types of cooling means. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling. In addition, the cooling execution device 500 increases the number of cooling means used as the temperature of the SoCBox 400 increases; in other words, in this example, first cooling using one of the two types of cooling means is started, and when the temperature of the SoCBox 400 further increases, cooling using the other cooling means is started, thereby making it possible to efficiently use energy for cooling.

Sixth embodiment
When an autonomous driving SoC (System on Chip) performs advanced arithmetic processing, heat generation becomes an issue. Therefore, in this embodiment, Synchronized Burst Chilling, which is a technology that utilizes AI (Artificial Intelligence) to optimize rapid cooling of the SoC Box, is provided.

FIG. 31 shows an example of a system 10. The system 10 includes a management server 100. The system 10 includes a SoCBox 400. The system 10 includes a cooling execution device 500. The system 10 includes a cooling unit 600.

FIG. 32 is an explanatory diagram for explaining the learning phase in the system 10. Here, examples of sensors 210 mounted on the vehicle 200 include a camera 211, a LiDAR (Light Detection and Ranging) 212, a millimeter wave sensor 213, an ultrasonic sensor 214, an IMU sensor 215, and a GNSS (Global Navigation Satellite System) sensor 216. The vehicle 200 does not have to be equipped with all of these, and may be equipped with some or other sensors.

FIG. 33 is an explanatory diagram for explaining the cooling execution phase in the system 10. Here, a camera 311, a LiDAR 312, a millimeter wave sensor 313, an ultrasonic sensor 314, an IMU sensor 315, and a GNSS sensor 316 are shown as examples of sensors 310 mounted on the vehicle 300. The vehicle 300 does not have to be equipped with all of these, and may be equipped with some or other sensors other than these.

The cooling execution device 500 includes a detection unit 501, a model storage unit 502, an information acquisition unit 504, an estimation unit 505, a prediction unit 506, a creation unit 507, and a cooling execution unit 508. The model storage unit 502 stores the learning model received from the management server 100. The information acquisition unit 504 acquires information acquired by the SoCBox 400.

The detection unit 501 detects temperature changes in a control device (SoCBox400) mounted on a vehicle that controls the vehicle's automatic driving. The detection unit 501 may also detect temperature changes in each of multiple parts of the SoCBox400. For example, the detection unit 501 can detect the occurrence of a rise or fall in temperature in one or multiple SoCBox400s, or detect changing temperature values.

The estimation unit 505 estimates whether switching from autonomous driving to manual driving will occur based on a preset driving route. Furthermore, the estimation unit 505 may estimate whether switching from autonomous driving to manual driving will occur based on road conditions on the driving route. For example, the estimation unit 505 can estimate whether switching from autonomous driving to manual driving will occur for a preset driving route based on road conditions such as heavy pedestrian traffic, occurrence of traffic jams, occurrence of accidents, occurrence of construction work, occurrence of road closures, etc.

The prediction unit 506 predicts temperature changes in the control device (SoCBox 400) mounted on the vehicle that controls the autonomous driving of the vehicle. The prediction unit 506 may predict temperature changes in SoCBox 400 using AI. For example, the prediction unit 506 predicts temperature changes in SoCBox 400 by inputting the information acquired by the information acquisition unit 504 into a learning model stored in the model storage unit 502.

The creation unit 507 creates a cooling schedule in which a specified cooling means is set based on the estimation result of the estimation unit 505. Specifically, when the estimation unit 505 estimates that automatic driving will be switched to manual driving, the creation unit 507 may create a cooling schedule in which a cooling means is set for a driving section of manual driving that is assumed to generate more heat than manual driving. On the other hand, when the estimation unit 505 estimates that manual driving will be switched to automatic driving, the creation unit 507 may create a cooling schedule in which a cooling means is set for a driving section of automatic driving that is assumed to generate less heat than automatic driving.

For example, when the estimation unit 505 estimates that a switch from automatic driving to manual driving will occur due to a change in road conditions on a driving route previously set by the estimation unit 505 (such as the occurrence of a situation where automatic driving is difficult), the creation unit 507 may create a cooling schedule in which a cooling means corresponding to manual driving is set. On the other hand, when the estimation unit 505 estimates that a switch from manual driving to automatic driving will occur due to a change in road conditions on a driving route previously set by the estimation unit 505 (such as a situation where automatic driving is possible), the creation unit 507 may create a cooling schedule in which a cooling means corresponding to automatic driving is set.

The creation unit 507 may compare the actual temperature change of the control device (SoCBox 400) detected by the detection unit 501 with the predicted temperature change predicted by the prediction unit 506, and if the predicted temperature change exceeds the actual temperature change, create a cooling schedule in which a specified cooling means is set. For example, the creation unit 507 may perform cooling using a specified cooling means based on the prediction by the prediction unit 506 that the temperature change of the control device (SoCBox 400) will be a 5°C temperature rise and the detection result by the detection unit 501 that the actual temperature change is a 10°C temperature rise.

The cooling execution unit 508 executes cooling of the control device (SoCBox 400) mounted on the vehicle that controls the automatic driving of the vehicle, based on the cooling schedule created by the creation unit 507. For example, when a cooling schedule for a driving section for manual driving or a cooling schedule for a driving section for automatic driving is created by the creation unit 507, the cooling execution unit 508 may execute cooling of the control device (SoCBox 400) using the cooling means, cooling time, cooling timing, etc. set in the cooling schedule.

In addition, when the creation unit 507 creates a cooling schedule based on a comparison between a predicted temperature change and an actual temperature change, the cooling execution unit 508 may execute cooling of the control device (SoCBox 400) using the cooling means, cooling time, cooling timing, etc. set in the cooling schedule.

The cooling execution unit 508 may execute cooling of the control device (SoCBox400) using a cooling means selected from a plurality of cooling means for cooling each of a plurality of parts of the control device (SoCBox400) based on the cooling schedule created by the creation unit 507. For example, when air cooling means, water cooling means, and liquid nitrogen cooling means are set in the cooling schedule created by the creation unit 507, and further conditions for executing cooling of a plurality of parts of the control device are set, the cooling execution unit 508 may select one or more of the plurality of cooling means described above to execute cooling.

FIG. 34 shows an example of a schematic diagram of the SoCBox 400 and the cooling unit 600. FIG. 34 shows an example where the cooling unit 600 is configured with a single cooling means. When the cooling execution device 500 predicts that the SoCBox 400 will start to generate heat or predicts that the temperature of the SoCBox 400 will exceed a predetermined threshold, the cooling unit 600 starts cooling, thereby cooling the entire SoCBox 400.

FIG. 35 shows an example of a schematic diagram of a SoCBox 400 and a cooling unit 600. FIG. 35 shows an example where the cooling unit 600 is configured with multiple cooling means for cooling each of the multiple parts of the SoCBox 400. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling.

FIG. 36 shows an example of the SoCBox 400 and the cooling unit 600. FIG. 36 shows an example in which the cooling unit 600 is configured with two types of cooling means. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling. Furthermore, the cooling execution device 500 increases the number of cooling means used as the temperature of the SoCBox 400 increases; in other words, in this example, first cooling using one of the two types of cooling means is started, and when the temperature of the SoCBox 400 further increases, cooling using the other cooling means is started, thereby making it possible to efficiently use energy for cooling.

Seventh embodiment
When an autonomous driving SoC (System on Chip) (processing chip) performs advanced arithmetic processing, heat generation becomes an issue. Therefore, in this embodiment, Synchronized Burst Chilling, a technology that utilizes AI (Artificial Intelligence) to optimize rapid cooling of the SoC Box, is provided.

The SoCBox heats up quickly, making it difficult to perform advanced calculations in the vehicle (a challenge to fully autonomous driving). For example, the SoCBox contains multiple SoCs, and as autonomous driving control becomes more complex, the amount of processing performed by the SoCs increases, which can cause the SoCBox to heat up and overheat. For this reason, AI can predict heat dissipation from the SoCBox and cool it so that its temperature remains within a specified range, preventing the SoCBox from getting too hot and enabling advanced calculations in the vehicle. It is expected that this technology can be used to cool not only the SoCBox, but also the battery, which could be a solution to the problem of high temperatures caused by rapid charging.

FIG. 37 shows an example of a system 10. The system 10 includes a management server 100. The system 10 includes a SoCBox 400. The system 10 includes a cooling device 700. The system 10 includes a cooling unit 600.

The SoCBox 400, cooling device 700, and cooling section 600 are mounted on a vehicle. The SoCBox 400 is a control device having multiple SoCs, and controls the autonomous driving of the vehicle using the sensor values of multiple sensors mounted on the vehicle. Because controlling the autonomous driving of the vehicle places a very high processing load on the vehicle, the SoCBox 400 can become very hot. If the SoCBox 400 becomes too hot, it may not operate normally or may have a negative effect on the vehicle.

The cooling device 700 according to this embodiment predicts temperature changes in the SoCBox 400 and, based on the temperature changes, cools the SoCBox 400 so that the temperature of the SoCBox 400 is maintained within a predetermined temperature range. For example, the cooling device 700 predicts that the SoCBox 400 will start to generate heat, and if the predicted temperature after heat generation exceeds the predetermined temperature range, it cools the SoCBox 400 to maintain it within the predetermined temperature range.

As a result, the cooling device 700 can maintain the temperature of the SoCBox 400 within a specified temperature range, reducing the need to rapidly cool the temperature of the SoCBox 400, and ultimately reducing the total energy consumed for cooling.

The cooling device 700 may determine the predetermined temperature range according to a threshold temperature that is predetermined for the SoCBox 400. For example, the cooling device 700 determines the predetermined temperature range to be a temperature range around an arbitrary temperature that is about 5° C. lower than the threshold temperature that is preset, taking into consideration the normal processing of the various SoCs contained in the SoCBox 400.

As a result, the cooling device 700 can constantly cool the SoCBox 400 to maintain the temperature within an arbitrary temperature range that is approximately 5°C lower than the threshold temperature, rather than repeatedly starting to cool the SoCBox 400 rapidly once the predicted temperature after heat generation approaches the threshold temperature, thereby reducing the total energy used for cooling.

Here, the specified temperature range is a temperature range centered on an arbitrary temperature lower than a threshold temperature set as the upper limit temperature at which the multiple SoCs contained in the SoCBox can perform normal processing, and is not limited to the temperature difference between the threshold temperature and the center temperature of the temperature range, or the width of the temperature range.

The cooling device 700 may use AI to predict temperature changes in the SoCBox 400. The learning of temperature changes in the SoCBox 400 may be performed by using data collected by the vehicle 200. For example, the management server 100 collects data from the vehicle 200 and performs the learning. The entity that performs the learning is not limited to the management server 100, and may be another device.

The vehicle 200 is equipped with a SoCBox 400 and a temperature sensor 40 that measures the temperature of the SoCBox 400. The SoCBox 400 controls the autonomous driving of the vehicle 200 using the sensor values of multiple sensors equipped in the vehicle 200 and external information received from multiple types of servers 30.

Server 30 may be an example of an external device. Examples of multiple types of servers 30 include a server that provides traffic information, a server that provides weather information, etc. SoCBox 400 transmits to management server 100 sensor values and external information used to control autonomous driving, as well as the temperature change of SoCBox 400 when controlled.

Vehicle 300 is a vehicle having a cooling function according to this embodiment. Vehicle 300 is equipped with SoCBox 400, cooling device 700, and cooling section 600. Cooling device 700 may receive from management server 100 and store the learning model generated by management server 100.

The cooling device 700 obtains sensor values from multiple sensors mounted on the vehicle 300 and external information received from multiple types of servers 30, which are acquired by the SoCBox 400, from multiple sensors and multiple types of servers 30, or from the SoCBox 400, and inputs the obtained information into a learning model to predict temperature changes in the SoCBox 400.

The cooling device 700 predicts when the SoCBox 400 will start to generate heat, and if the predicted temperature after heat generation exceeds a predetermined temperature range, it starts cooling the SoCBox 400 using the cooling unit 600, and maintains the temperature of the SoCBox 400 within the predetermined temperature range.

The SoCBox 400, the cooling device 700, the management server 100, and the server 30 may communicate via the network 20. The network 20 may include a vehicle network. The network 20 may include the Internet. The network 20 may include a LAN (Local Area Network).

The network 20 may include a mobile communication network. The mobile communication network may conform to any of the following communication methods: 5G (5th Generation) communication method, LTE (Long Term Evolution) communication method, 3G (3rd Generation) communication method, and 6G (6th Generation) communication method or later.

FIG. 38 is an explanatory diagram for explaining the learning phase in the system 10. Here, examples of sensors 210 mounted on the vehicle 200 include a camera 211, a LiDAR (Light Detection and Ranging) 212, a millimeter wave sensor 213, an ultrasonic sensor 214, an IMU sensor 215, and a GNSS (Global Navigation Satellite System) sensor 216. The vehicle 200 does not have to be equipped with all of these, and may be equipped with some or other sensors.

The model providing unit 106 provides the learning model generated by the model generating unit 104. The model providing unit 106 may transmit the learning model to the cooling device 700 mounted on the vehicle 300.

The system 10 may be configured to predict temperature changes in each of the multiple parts of the SoCBox 400. In this case, the vehicle 200 may be equipped with multiple temperature sensors 40 that each measure the temperature change in each of the multiple parts of the SoCBox 400. The SoCBox 400 may transmit to the management server 100 the sensor information received from the sensor 210, the external information received from the server 30, and the temperature changes measured by the multiple temperature sensors 40 when the SoCBox 400 acquires this information and executes autonomous driving control.

The model generation unit 104 performs machine learning using the information acquired by SoCBox 400 and the temperature changes in each of the multiple parts of SoCBox 400 when SoCBox 400 acquired the information as learning data, thereby generating a learning model in which the information acquired by SoCBox 400 is used as input and the temperature changes in each of the multiple parts of SoCBox 400 are used as output.

FIG. 39 is an explanatory diagram for explaining the cooling execution phase in the system 10. Here, a camera 311, a LiDAR 312, a millimeter wave sensor 313, an ultrasonic sensor 314, an IMU sensor 315, and a GNSS sensor 316 are shown as examples of sensors 310 mounted on the vehicle 300. The vehicle 300 does not have to be equipped with all of these, and may not have some of them, or may have sensors other than these.

The cooling device 700 includes a model storage unit 502, an information acquisition unit 504, a prediction unit 506, and a cooling execution unit 508. The model storage unit 502 stores the learning model received from the management server 100. The information acquisition unit 504 acquires information acquired by the SoCBox 400.

The information acquisition unit 504 acquires the sensor information that the SoCBox 400 acquires from the sensor 310 from the sensor 310 or from the SoCBox 400. For example, the information acquisition unit 504 may receive the sensor information that the SoCBox 400 acquires from the sensor 310 from the SoCBox 400.

The information acquisition unit 504 may receive the same sensor information from the sensor 310 as the sensor information that the SoCBox 400 acquires from the sensor 310. In this case, each sensor of the sensor 310 may transmit the sensor information to the SoCBox 400 and the cooling device 700, respectively.

The information acquisition unit 504 acquires the external information that the SoCBox 400 acquires from the server 30 from the server 30 or from the SoCBox 400. The information acquisition unit 504 may receive from the SoCBox 400 the external information that the SoCBox 400 received from the server 30. The information acquisition unit 504 may receive from the server 30 the same external information that the SoCBox 400 receives from the server 30. In this case, the server 30 may transmit the external information to both the SoCBox 400 and the cooling device 700.

The cooling execution unit 508 performs cooling so as to maintain the temperature of the SoCBox 400 within a predetermined temperature range based on the temperature change of the SoCBox 400 predicted by the prediction unit 506. For example, in response to the prediction unit 506 predicting that the temperature of the SoCBox 400 will be higher than the upper limit temperature within the predetermined temperature range, the cooling execution unit 508 starts cooling the SoCBox 400 and maintains the temperature of the SoCBox 400 within the predetermined temperature range.

The cooling execution unit 508 may cool the SoCBox 400 using a cooling means that corresponds to the temperature of the SoCBox 400 predicted by the prediction unit 506. For example, the higher the temperature of the SoCBox 400, the more cooling means the cooling execution unit 508 uses to cool the SoCBox 400.

As a specific example, when it is predicted that the temperature of SoCBox 400 will exceed the upper limit of a predetermined temperature range, the cooling execution unit 508 starts cooling using one of the multiple cooling means, and when it is still predicted that the temperature of SoCBox 400 will rise and exceed the aforementioned upper limit, the cooling execution unit 508 increases the number of cooling means used.

The higher the temperature of SoCBox400, the more powerful the cooling means that the cooling execution unit 508 uses to cool SoCBox400. For example, if it is predicted that the temperature of SoCBox400 will exceed the upper limit temperature, the cooling execution unit 508 starts cooling using air cooling means, if it is still predicted that the temperature of SoCBox400 will rise and exceed the upper limit temperature, the cooling execution unit 508 starts cooling using water cooling means, and if it is still predicted that the temperature of SoCBox400 will rise and exceed the upper limit temperature, the cooling execution unit 508 starts cooling using liquid nitrogen cooling means.

Figure 40 shows an example of the SoCBox 400 and cooling unit 600. Figure 40 shows an example where the cooling unit 600 is configured with a single cooling means. When the cooling device 700 predicts that the SoCBox 400 will start to generate heat or predicts that the temperature of the SoCBox 400 will exceed a predetermined temperature range, it can start cooling using the cooling unit 600, thereby cooling the entire SoCBox 400.

FIG. 41 shows an example of a schematic diagram of a SoCBox 400 and a cooling unit 600. FIG. 41 shows an example where the cooling unit 600 is composed of multiple cooling means that respectively cool multiple parts of the SoCBox 400.

The cooling device 700 predicts the temperature changes in each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to heat up or that the temperature of any part will exceed a predetermined temperature range, it performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling.

FIG. 42 shows an example of a SoCBox 400 and a cooling unit 600. FIG. 42 shows an example in which the cooling unit 600 is configured with two types of cooling means. The cooling device 700 predicts temperature changes in each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined temperature range, it performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling.

In addition, the cooling device 700 increases the number of cooling means used as the temperature of the SoCBox 400 increases. That is, in this example, first cooling is started using one of the two types of cooling means, and when the temperature of the SoCBox 400 further increases, cooling is started using the other cooling means, thereby making it possible to make the energy used for cooling more efficient.

Eighth embodiment
When an autonomous driving SoC (System on Chip) performs advanced arithmetic processing, heat generation becomes an issue. Therefore, in this embodiment, Synchronized Burst Chilling, which is a technology that utilizes AI (Artificial Intelligence) to optimize rapid cooling of the SoC Box, is provided.

FIG. 43 shows an example of a system 10. The system 10 includes a management server 100. The system 10 includes a SoCBox 400. The system 10 includes a cooling execution device 500. The system 10 includes a cooling unit 600.

FIG. 44 is an explanatory diagram for explaining the learning phase in the system 10. Here, examples of sensors 210 mounted on the vehicle 200 include a camera 211, a LiDAR (Light Detection and Ranging) 212, a millimeter wave sensor 213, an ultrasonic sensor 214, an IMU sensor 215, and a GNSS (Global Navigation Satellite System) sensor 216. The vehicle 200 does not have to be equipped with all of these, and may be equipped with some or other sensors.

FIG. 45 is an explanatory diagram for explaining the cooling execution phase in the system 10. Here, a camera 311, a LiDAR 312, a millimeter wave sensor 313, an ultrasonic sensor 314, an IMU sensor 315, and a GNSS sensor 316 are shown as examples of sensors 310 mounted on the vehicle 300. The vehicle 300 does not have to be equipped with all of these, and may not have some of them, or may have sensors other than these.

The cooling execution device 500 includes a detection unit 501, a model storage unit 502, an information acquisition unit 504, a prediction unit 506, a selection unit 510, a cooling execution unit 508, and an output unit 509. The model storage unit 502 stores the learning model received from the management server 100. The information acquisition unit 504 acquires information acquired by the SoCBox 400.

Detection unit 501 detects temperature changes in a control device mounted on a vehicle that controls the vehicle's automatic driving. Detection unit 501 may also detect temperature changes in each of multiple parts of SoCBox 400. For example, detection unit 501 can detect the occurrence of a temperature rise or fall in one or multiple SoCBox 400s, or detect changing temperature values.

The information acquisition unit 504 acquires the external information that SoCBox 400 acquires from server 30 from server 30 or from SoCBox 400. The information acquisition unit 504 may receive from SoCBox 400 the external information that SoCBox 400 received from server 30. The information acquisition unit 504 may receive from server 30 the same external information that SoCBox 400 receives from server 30. In this case, the server 30 may transmit the external information to each of SoCBox 400 and the cooling execution device 500. The information acquisition unit 504 may also acquire the results of information processing related to autonomous driving from an external information processing device that performs information processing related to autonomous driving as a specified information processing of the control device (SoCBox 400). For example, when an external information processing device performs information processing related to the control of autonomous driving that is normally performed by the vehicle control device (SoCBox 400), the information acquisition unit 504 can acquire the results of the information processing related to the autonomous driving from the external information processing device.

The selection unit 510 selects a specific operating condition that lowers the temperature of the control device when the temperature change exceeds a specific threshold. From here, we will explain specific examples of operating conditions selected by the selection unit 510.

For example, when the temperature change exceeds a predetermined threshold, the selection unit 510 may select, as the predetermined operating condition, an operating condition that suppresses the amount of calculation related to the predetermined information processing of the control device (SoCBox 400). As a result, the cooling execution device suppresses the amount of heat generated by the calculation related to the information processing, and provides a cooling effect for the control device.

When the temperature change exceeds a predetermined threshold, the selection unit 510 may select, as the predetermined operating condition, an operating condition that suppresses the operating speed of the automatic operation to a predetermined speed or less. As a result, the cooling execution device suppresses the amount of calculation related to the information processing of the automatic operation, thereby suppressing the amount of heat generated by the calculation and achieving a cooling effect for the control device.

In addition, the selection unit 510 may select an operating condition that changes automatic operation to manual operation as the predetermined operating condition when the temperature change exceeds a predetermined threshold. This allows the cooling execution device to switch to manual operation, which involves less calculation than automatic operation, thereby suppressing the amount of heat generated by the calculations and achieving a cooling effect for the control device.

When the temperature change exceeds a predetermined threshold, the selection unit 510 may select, as the predetermined driving condition, a driving condition in which the vehicle stops at a predetermined position (e.g., a shoulder) on a road included in the driving route of the autonomous driving. As a result, the cooling execution device stops the autonomous driving to reduce the amount of calculations related to the autonomous driving, thereby reducing the amount of heat generated by the calculations and achieving a cooling effect for the control device.

When the temperature change exceeds a predetermined threshold, the selection unit 510 may select, as the predetermined operating condition, an operating condition that suppresses the acquisition of predetermined information used in the information processing for autonomous driving. As a result, the cooling execution device suppresses the acquisition of information used in the information processing for autonomous driving, and suppresses the amount of calculations related to autonomous driving, thereby suppressing the amount of heat generated by the calculations and achieving a cooling effect for the control device.

The output unit 509 outputs a predetermined driving condition based on the selection result of the selection unit 510. Specifically, the output unit 509 may output information about the driving conditions for the control device (SoCBox 400) to control the automatic driving of the vehicle based on the driving conditions selected by the selection unit 510. Note that the information about the driving conditions output by the output unit 509 is not particularly limited as long as it is in a format that can be used by the control device of the vehicle.

FIG. 46 shows an example of a schematic diagram of the SoCBox 400 and the cooling unit 600. FIG. 46 shows an example where the cooling unit 600 is configured with a single cooling means. When the cooling execution device 500 predicts that the SoCBox 400 will start to generate heat or predicts that the temperature of the SoCBox 400 will exceed a predetermined threshold, the cooling unit 600 starts cooling, thereby cooling the entire SoCBox 400.

FIG. 47 shows an example of a schematic diagram of a SoCBox 400 and a cooling unit 600. FIG. 47 shows an example where the cooling unit 600 is configured with multiple cooling means for cooling each of the multiple parts of the SoCBox 400. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling.

FIG. 48 shows an example of the SoCBox 400 and the cooling unit 600. FIG. 48 shows an example in which the cooling unit 600 is configured with two types of cooling means. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby realizing efficient cooling. In addition, the cooling execution device 500 increases the number of cooling means to be used as the temperature of the SoCBox 400 increases, that is, in this example, first starts cooling using one of the two types of cooling means, and when the temperature of the SoCBox 400 further increases, starts cooling using the other cooling means, thereby making it possible to efficiently use energy for cooling.
Ninth embodiment

When an autonomous driving SoC (System on Chip) (processing chip) performs advanced arithmetic processing, heat generation becomes an issue. Therefore, in this embodiment, we provide a technology that utilizes AI (Artificial Intelligence) to cool the SoCBox, which is a control device.

The SoCBox quickly becomes hot, making it difficult to perform advanced calculations in the vehicle (a challenge to fully autonomous driving). For example, the SoCBox contains multiple SoCs, and as autonomous driving control becomes more complex, the amount of processing performed by the SoCs increases, which can cause the SoCBox to become hot and overheat. For this reason, AI can predict heat dissipation from the SoCBox and communicate with other vehicles traveling nearby before the SoCBox overheats, allowing them to shoulder part of the calculation load of the SoCs, preventing the SoCBox from becoming too hot and enabling advanced calculations in the vehicle.

FIG. 49 shows an example of a system 10. The system 10 includes a management server 100. The system 10 includes a SoCBox 400. The system 10 includes a cooling device 700. The system 10 includes a cooling unit 600.

The cooling device 700 according to this embodiment predicts temperature changes in the SoCBox 400, communicates with other vehicles within a specified range based on the temperature changes, and instructs the control device to execute calculations related to the control of the autonomous driving of the other vehicles with which communication is taking place. For example, the cooling device 700 predicts that the SoCBox 400 will start to generate heat, and if the predicted temperature after heat generation exceeds a preset threshold temperature, communicates with other vehicles traveling parallel to the vehicle. The cooling device 700 then groups the multiple vehicles with which it is communicating, and instructs the SoCBox 400 to perform calculations to shoulder part of the computational load of the SoC of the communicating vehicle. The cooling device 700 may also perform calculations related to autonomous driving between the vehicles with which communication is taking place, for example, to complement each other.

As a result, when the cooling device 700 predicts that the temperature of the SoCBox 400 will exceed a set threshold, it can communicate with nearby vehicles to have them shoulder part of the computational load or to compensate for each other's computational load, thereby reducing the computational load and lowering the temperature of the SoCBox 400.

The aforementioned preset threshold temperature is a temperature set as the upper limit temperature at which the multiple SoCs in the SoCBox400 can perform normal processing.

The cooling device 700 may also determine that other vehicles that are within a range where communication with other vehicles can be maintained for a predetermined period of time are vehicles that are within the predetermined range and communicate with them. For example, the cooling device 700 may determine that a vehicle that is within a range where the communication unit can communicate and communication between the vehicles can be maintained for a certain period of time is a vehicle that is within the predetermined range, and communicate with that vehicle. As a method of determining that a vehicle is within a predetermined range, for example, a vehicle that responded to a predetermined broadcast communication or a vehicle that has been confirmed to be in the vicinity based on location information may be determined to be a vehicle that is within the predetermined range.

The cooling device 700 may also start cooling the SoCBox 400 based on the temperature change predicted by the prediction unit. For example, when it is predicted that the temperature of the SoCBox 400 will exceed the aforementioned threshold temperature, the cooling device 700 starts cooling the SoCBox 400 using air-cooling means or the like.

As a result, the cooling device 700 communicates with the other vehicles mentioned above, reducing the computational load, and by cooling the SoCBox 400 from outside, it is possible to rapidly cool the temperature of the SoCBox 400.

The vehicle 200 is equipped with a SoCBox 400, a temperature sensor 40 that measures the temperature of the SoCBox 400, and a cooling device 700. The SoCBox 400 controls the autonomous driving of the vehicle 200 using the sensor values of multiple sensors installed in the vehicle 200 and external information received from multiple types of servers 30.

The cooling device 700 obtains sensor values from multiple sensors mounted on the vehicle 200 and external information received from multiple types of servers 30, which are acquired by the SoCBox 400, from multiple sensors and multiple types of servers 30, or from the SoCBox 400, and predicts temperature changes in the SoCBox 400 by inputting the obtained information into a learning model.

For example, the cooling device 700 predicts when the SoCBox 400 will start to generate heat, and if the predicted temperature after heat generation exceeds a preset threshold temperature, the cooling device 700 communicates with other vehicles traveling nearby and reduces the calculation load on the SoCBox 400, thereby lowering the temperature of the SoCBox 400.

Vehicle 300 is a vehicle having a cooling unit according to this embodiment. Vehicle 300 is equipped with SoCBox 400, cooling device 700, and cooling unit 600. Cooling device 700 may receive from management server 100 and store the learning model generated by management server 100.

FIG. 50 is an explanatory diagram of the state in which communication between vehicles is taking place in this embodiment. As described above, when the cooling device 700 predicts that the temperature of the SoCBox 400 will exceed a preset threshold temperature, it communicates with other vehicles traveling nearby, and the communicating vehicle instructs the SoCBox 400 to perform calculations to shoulder part of the computational load of the communicating vehicle's SoC.

In the example of FIG. 50, vehicles 200-2, 200-3, and 200-4 are traveling near vehicle 200-1 at a similar speed. Then, because it is predicted that the temperature of SoCBox 400 of vehicle 200-1 will exceed the threshold temperature, vehicles 200-1 to 200-4 are grouped by the communication unit of 200-1 to form network 20.

After the network 20 is configured, the cooling device 700 of the destination vehicle issues an instruction to perform calculations to shoulder part of the computational load of the SoCBox 400 of the source vehicle. As a result, part of the computational load of the SoC of the source vehicle 200-1 is shouldered by the SoCs of the other destination vehicles 200-2 to 200-4, reducing the computational load of the SoC of the source vehicle 200-1 and lowering the temperature of the SoCBox 400 of vehicle 200-1.

FIG. 51 is an explanatory diagram for explaining the learning phase in the system 10. Here, examples of the sensors 210 mounted on the vehicle 200 include a camera 211, a LiDAR (Light Detection and Ranging) 212, a millimeter wave sensor 213, an ultrasonic sensor 214, an IMU sensor 215, and a GNSS (Global Navigation Satellite System) sensor 216. The vehicle 200 does not have to be equipped with all of these, and may be equipped with some or other sensors.

SoCBox400 acquires sensor information from each sensor included in sensor 210. SoCBox400 may also perform communication via network 20, and receives external information from each of multiple servers 30 via network 20. Then, SoCBox400 uses the acquired information to execute autonomous driving control of vehicle 200 and vehicle 300.

The model providing unit 106 provides the learning model generated by the model generating unit 104. The model providing unit 106 may transmit the learning model to the cooling device 700 mounted on the vehicle 200 and the vehicle 300.

FIG. 52 is an explanatory diagram for explaining the cooling execution phase in the system 10. Here, a camera 311, a LiDAR 312, a millimeter wave sensor 313, an ultrasonic sensor 314, an IMU sensor 315, and a GNSS sensor 316 are shown as examples of sensors 310 mounted on the vehicle 300. The vehicle 300 does not have to be equipped with all of these, and may not have some of them, or may have sensors other than these.

The cooling device 700 includes a prediction unit 506, a communication unit 520, an instruction unit 530, a cooling execution unit 540, a model storage unit 550, and an information acquisition unit 560. The prediction unit 506 predicts temperature changes in the SoCBox 400. The prediction unit 506 may predict temperature changes in the SoCBox 400 using AI. For example, the prediction unit 506 predicts temperature changes in the SoCBox 400 by inputting information acquired by the information acquisition unit 560 (described below) into a learning model stored in the model storage unit 550 (described below).

The communication unit 520 communicates with other vehicles that are within a predetermined range based on the temperature change predicted by the prediction unit 506. For example, when the prediction unit 506 predicts that the temperature of the SoCBox 400 will exceed a preset threshold temperature, the communication unit 520 communicates with other vehicles that are determined to be within the aforementioned predetermined range, thereby forming the network 20.

The instruction unit 530 instructs the control device to execute calculations related to the control of autonomous driving of another vehicle with which communication is being performed via the communication unit 520. For example, when the instruction unit 530's own vehicle is connected to another vehicle for communication, the instruction unit 530 refers to the availability of resources of the SoC of the own vehicle and determines whether or not it is possible to execute a part of the calculation load of the SoC of the other vehicle that is the source of communication. Then, when the instruction unit 530 determines that it is possible to execute a part of the calculation load of the SoC of the other vehicle that is the source of communication, the instruction unit 530 instructs the SoCBox 400 of the own vehicle to execute a part of the calculation load of the SoC of the other vehicle that is the source of communication.

The cooling execution unit 540 starts cooling the SoCBox 400 based on the temperature change of the SoCBox 400 predicted by the prediction unit 506. For example, the cooling execution unit 540 starts cooling the SoCBox 400 in response to the prediction unit 506 predicting that the temperature of the SoCBox 400 will become higher than a predetermined threshold.

The cooling execution unit 540 may use the cooling unit 600 described below to perform cooling of the SoCBox 400. The cooling unit 600 may cool the SoCBox 400 by air cooling means. The cooling unit 600 may cool the SoCBox 400 by water cooling means. The cooling unit 600 may cool the SoCBox 400 by liquid nitrogen cooling means.

The model storage unit 550 stores the learning model received from the management server 100. The information acquisition unit 504 acquires information acquired by the SoCBox 400.

The information acquisition unit 560 acquires the sensor information that the SoCBox 400 acquires from the sensor 310 from the sensor 310 or from the SoCBox 400. For example, the information acquisition unit 560 may receive the sensor information that the SoCBox 400 acquires from the sensor 310 from the SoCBox 400.

The information acquisition unit 560 may receive the same sensor information from the sensor 310 as the sensor information that the SoCBox 400 acquires from the sensor 310. In this case, each sensor of the sensor 310 may transmit the sensor information to the SoCBox 400 and the cooling device 700, respectively.

The information acquisition unit 560 acquires the external information that the SoCBox 400 acquires from the server 30 from the server 30 or from the SoCBox 400. The information acquisition unit 560 may receive from the SoCBox 400 the external information that the SoCBox 400 received from the server 30. The information acquisition unit 560 may receive from the server 30 the same external information that the SoCBox 400 receives from the server 30. In this case, the server 30 may transmit the external information to both the SoCBox 400 and the cooling device 700.

The cooling execution unit 540 may cool the SoCBox 400 using a cooling means that corresponds to the temperature of the SoCBox 400 predicted by the prediction unit 506. For example, the higher the temperature of the SoCBox 400, the more cooling means the cooling execution unit 508 uses to cool the SoCBox 400.

As a specific example, when it is predicted that the temperature of SoCBox 400 will exceed a first threshold, the cooling execution unit 540 starts cooling using one of the multiple cooling means, and when it is still predicted that the temperature of SoCBox 400 will rise and exceed a second threshold, the number of cooling means used is increased.

The cooling execution unit 508 may use a more powerful cooling means to cool the SoCBox 400 as the temperature of the SoCBox 400 increases. For example, the cooling execution unit 508 may start cooling using air cooling means when it is predicted that the temperature of the SoCBox 400 will exceed a first threshold, start cooling using water cooling means when it is predicted that the temperature of the SoCBox 400 will still rise and exceed a second threshold, and start cooling using liquid nitrogen cooling means when it is predicted that the temperature of the SoCBox 400 will still rise and exceed a third threshold.

FIG. 53 shows an example of a SoCBox 400 and a cooling unit 600. FIG. 53 shows an example in which the cooling unit 600 is configured with a single cooling means. When the cooling device 700 predicts that the SoCBox 400 will start to generate heat or predicts that the temperature of the SoCBox 400 will exceed a predetermined threshold, the cooling unit 600 starts cooling, thereby cooling the entire SoCBox 400.

FIG. 54 shows an example of a schematic diagram of a SoCBox 400 and a cooling unit 600. FIG. 54 shows an example where the cooling unit 600 is composed of multiple cooling means that respectively cool multiple parts of the SoCBox 400.

The cooling device 700 predicts the temperature changes in each of the multiple parts of the SoCBox 400, and when it predicts that one of the parts will start to generate heat or that the temperature of one of the parts will exceed a predetermined threshold, it performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling.

FIG. 55 shows an example of a SoCBox 400 and a cooling unit 600. FIG. 55 shows an example in which the cooling unit 600 is configured with two types of cooling means. The cooling device 700 predicts temperature changes in each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, it performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling.

Tenth embodiment
When an autonomous driving SoC (System Chip) performs advanced arithmetic processing, heat generation becomes an issue. Therefore, in this embodiment, Synchronized Burst Chilling, which is a technology that utilizes AI (Artificial Intelligence) to optimize rapid cooling of the SoC Box, is provided.

Because the SoCBox quickly becomes hot, it is difficult to perform advanced calculations in the vehicle (a challenge to fully autonomous driving). Therefore, it is conceivable that AI could be used to predict heat dissipation from the SoCBox and cool it down at the same time. For example, by using AI to predict heat dissipation from the SoCBox and cooling it at the same time as heat dissipation, it would be possible to prevent the SoCBox from becoming too hot and enable advanced calculations in the vehicle.

In such a case, it is desirable to optimize the timing of cooling. For example, the moment when the computing power of the SoCBox will be at its maximum is predicted, and the cooling device is controlled at the optimal timing. Also, for example, the time from when the cooling is triggered to when cooling actually occurs is calculated backwards and taken into consideration. Also, for example, the degree of cooling is adjusted according to the risk rate. As a specific example, cooling is performed if the risk rate exceeds 30%, cooling is weakened if it is 20% or less, and cooling is strengthened if it is over 50%, etc.

AI can predict heat dissipation from the SoCBox and cool it at the same time as it dissipates heat, preventing the SoCBox from getting too hot and enabling advanced calculations in the vehicle. It can also efficiently cool the SoCBox while taking into account necessity, time, and risk.

FIG. 56 shows an example of a system 10. The system 10 includes a management server 100. The system 10 includes a SoCBox 400. The system 10 includes a cooling execution device 500. The system 10 includes a cooling unit 600.

The cooling execution device 500 according to this embodiment predicts, for example, a change in temperature of the SoCBox 400, and starts cooling the SoCBox 400 based on the temperature change. For example, the cooling execution device 500 immediately starts cooling the SoCBox 400 in response to predicting that the SoCBox 400 will start generating heat. By starting cooling before the SoCBox 400 starts generating heat, or at the same time, it is possible to reliably prevent the SoCBox 400 from becoming too hot. Furthermore, it is possible to reduce the energy required for cooling compared to constantly cooling the SoCBox 400.

The cooling execution device 500 may obtain sensor values from multiple sensors mounted on the vehicle 300 and external information received from multiple types of servers 30, which are obtained by the SoCBox 400, from the multiple sensors and multiple types of servers 30, or from the SoCBox 400, and input the obtained information into a learning model to predict temperature changes in the SoCBox 400.

The cooling execution device 500 may start cooling the SoCBox 400 using the cooling unit 600 when it predicts that the SoCBox 400 will start to generate heat or when it predicts that the temperature of the SoCBox 400 will rise above a predetermined threshold.

When predicting the temperature change of SoCBox 400, the cooling execution device 500 may predict the computing power of SoCBox 400 during the calculation process. For example, the cooling execution device 500 predicts the change in computing power of SoCBox 400 using AI, and predicts the temperature change of SoCBox 400 based on the prediction result. As a specific example, the cooling execution device 500 predicts the moment when the computing power of SoCBox 400 will be at its maximum using AI, and predicts the temperature change of SoCBox 400 by taking into account the temperature change of SoCBox 400 caused by the computing power of SoCBox 400 reaching its maximum.

The management server 100 may perform machine learning using information such as sensor values and external information acquired by the SoCBox 400 and the measured computing power of the SoCBox 400 as learning data, to generate a learning model in which the information acquired by the SoCBox 400 is used as input and the computing power of the SoCBox 400 is used as output. The cooling execution device 500 may use the learning model to predict changes in the computing power of the SoCBox 400.

Also, the cooling execution device 500 according to this embodiment may predict a change in the computing power of the SoCBox 400 and start cooling the SoCBox 400 based on the change in computing power. For example, the cooling execution device 500 predicts the moment when the computing power of the SoCBox 400 will be at its maximum, and starts cooling the SoCBox 400 based on the prediction result. As a specific example, the cooling execution device 500 predicts the moment when the computing power of the SoCBox 400 will be at its maximum, and starts cooling the SoCBox 400 at the timing of the predicted moment. Also, for example, the cooling execution device 500 predicts the moment when the computing power of the SoCBox 400 will be at its maximum, and starts cooling the SoCBox 400 at a timing that is a predetermined time back from the predicted moment.

The cooling execution device 500 according to this embodiment may perform cooling of the SoCBox 400 taking into consideration the time from the cooling trigger to the actual cooling. For example, the cooling execution device 500 uses AI to predict the time until cooling of the SoCBox 400 actually occurs when cooling of the SoCBox 400 is started in the situation in which the SoCBox 400 is placed, and controls the timing of starting cooling of the SoCBox 400 according to the prediction result. As a specific example, the cooling execution device 500 starts cooling of the SoCBox 400 at a timing that goes back the predicted time from the timing at which it is actually desired to start cooling of the SoCBox 400. Even if cooling of SoCBox400 is started using the desired timing as a trigger, if there is a time lag before SoCBox400 actually starts cooling, the start of cooling will be delayed. However, by using such a prediction, it is possible to ensure that cooling of SoCBox400 actually starts at the desired timing.

The management server 100 may perform machine learning using, as learning data, information such as sensor values and external information acquired by the SoCBox 400 and the time it takes for the SoCBox 400 to cool down if cooling of the SoCBox 400 is initiated when the SoCBox 400 acquires the information, to generate a learning model in which the information acquired by the SoCBox 400 is used as input and the time it takes for the SoCBox 400 to actually cool down if cooling of the SoCBox 400 is initiated is output. The cooling execution device 500 may use the learning model to control the trigger for cooling the SoCBox 400.

The cooling execution device 500 according to this embodiment may, for example, adjust the degree of cooling of the SoCBox 400 according to the risk rate. The risk rate may, for example, be the probability that the SoCBox 400 will become too hot and stop functioning properly. The risk rate may, for example, be the probability that the SoCBox 400 will become too hot and stop functioning properly, affecting the normal automatic operation of the vehicle controlled by the SoCBox 400.

The risk rate may be, for example, the probability that SoCBox400 will become too hot and stop functioning properly, affecting the normal automatic driving of the vehicle controlled by SoCBox400 and causing an accident. For example, the risk rate will be different between a case where SoCBox400 becomes too hot and stops functioning properly when the vehicle is driving in a deserted area in good weather and a case where SoCBox400 becomes too hot and stops functioning properly when the vehicle is driving in a crowded area such as a city in bad weather.

The cooling execution device 500 stores in advance, for example, a first threshold value for the risk rate and a second threshold value higher than the first threshold value. Then, when the risk rate is lower than the first threshold value, the cooling execution device 500 cools the SoCBox 400 at a first cooling intensity, when the risk rate is higher than the first threshold value and lower than the second threshold value, the cooling execution device 500 cools the SoCBox 400 at a second cooling intensity stronger than the first cooling intensity, and when the risk rate is higher than the second threshold value, the cooling execution device 500 cools the SoCBox 400 at a third cooling intensity stronger than the second cooling intensity. This makes it possible to cool the SoCBox 400 according to the risk rate and to optimize the energy required for cooling. Note that the number of cooling intensity stages is not limited to three.

FIG. 57 is an explanatory diagram for explaining the learning phase in the system 10. Here, examples of the sensors 210 mounted on the vehicle 200 include a camera 211, a LiDAR (Light Detection and Ranging) 212, a millimeter wave sensor 213, an ultrasonic sensor 214, an IMU sensor 215, and a GNSS (Global Navigation Satellite System) sensor 216. The vehicle 200 does not have to be equipped with all of these, and may be equipped with some or other sensors.

SoCBox400 records its computing power. SoCBox400 may record its computing power periodically or irregularly. SoCBox400 may record the sensor information received from sensor 210, the external information received from server 30, and its computing power when acquiring this information and executing autonomous driving control, and transmit this to management server 100.

The model generation unit 104 performs machine learning using the information acquired by the information acquisition unit 102 to generate a learning model.

The model generation unit 104 may generate a learning model in which the information acquired by SoCBox 400 is used as input and the temperature change of SoCBox 400 is used as output by executing machine learning using the information acquired by SoCBox 400 and the temperature change of SoCBox 400 when SoCBox 400 acquired the information as learning data.

The model generation unit 104 may perform machine learning using the information acquired by SoCBox 400 and the computing power of SoCBox 400 at the time SoCBox 400 acquired the information as learning data, thereby generating a learning model in which the information acquired by SoCBox 400 is used as input and the computing power of SoCBox 400 is used as output.

The model generation unit 104 may perform machine learning using, as learning data, the information acquired by the SoCBox 400 and the time it takes for the SoCBox 400 to cool down if cooling of the SoCBox 400 is started when the SoCBox 400 acquires the information, to generate a learning model in which the information acquired by the SoCBox 400 is used as input and the time it takes for the SoCBox 400 to cool down if cooling of the SoCBox 400 is started is used as output.

A cooling unit 600 may be installed in the vehicle 200 to collect data related to the cooling of the SoCBox 400. For example, when the cooling unit 600 is caused to cool the SoCBox 400, the temperature sensor 40 is used to measure the time from when the cooling unit 600 is triggered to when the SoCBox 400 is actually cooled. The SoCBox 400 transmits to the management server 100 the sensor information received from the sensor 210, the external information received from the server 30, and the time from when the cooling unit 600 is triggered to when the SoCBox 400 is actually cooled, in the case where the cooling unit 600 cools the SoCBox 400 when this information is obtained. The model generation unit 104 of the management server 100 may perform machine learning using, as learning data, information such as sensor values and external information acquired by the SoCBox 400 and the time it takes for the SoCBox 400 to actually cool down if cooling of the SoCBox 400 is started when the SoCBox 400 acquires the information, to generate a learning model in which the information acquired by the SoCBox 400 is used as input and the time it takes for the SoCBox 400 to actually cool down if cooling of the SoCBox 400 is started is used as output. The model provision unit 106 may transmit the learning model to the cooling execution device 500 mounted on the vehicle 300.

FIG. 58 is an explanatory diagram for explaining the cooling execution phase in the system 10. Here, a camera 311, a LiDAR 312, a millimeter wave sensor 313, an ultrasonic sensor 314, an IMU sensor 315, and a GNSS sensor 316 are shown as examples of sensors 310 mounted on the vehicle 300. The vehicle 300 does not have to be equipped with all of these, and may not have some of them, or may have sensors other than these.

The cooling execution device 500 includes a model storage unit 502, an information acquisition unit 504, a prediction unit 506, a cooling execution unit 508, and a risk rate acquisition unit 511. The model storage unit 502 stores the learning model received from the management server 100. The information acquisition unit 504 acquires information acquired by the SoCBox 400.

The prediction unit 506 may predict the temperature change of the SoCBox 400. The prediction unit 506 may predict the temperature change of the SoCBox 400 using AI. For example, the prediction unit 506 predicts the temperature change of the SoCBox 400 by inputting the information acquired by the information acquisition unit 504 into a learning model stored in the model storage unit 502.

When predicting the temperature change of SoCBox 400, prediction unit 506 may predict the computing power of SoCBox 400 during the calculation process. For example, prediction unit 506 predicts the computing power of SoCBox 400 by inputting the information acquired by information acquisition unit 504 into the learning model stored in model storage unit 502, and predicts the temperature change of SoCBox 400 based on the prediction result. As a specific example, prediction unit 506 predicts the moment when the computing power of SoCBox 400 will be at its maximum, and predicts the temperature change of SoCBox 400 by taking into account the temperature change of SoCBox 400 caused by the computing power of SoCBox 400 reaching its maximum.

The cooling execution unit 508 may start cooling the SoCBox 400 based on the temperature change of the SoCBox 400 predicted by the prediction unit 506. For example, the cooling execution unit 508 starts cooling the SoCBox 400 in response to the prediction unit 506 predicting that the SoCBox 400 will start generating heat. For example, the cooling execution unit 508 starts cooling the SoCBox 400 in response to the prediction unit 506 predicting that the temperature of the SoCBox 400 will become higher than a predetermined threshold.

The prediction unit 506 may predict changes in the computing power of the SoCBox 400. The prediction unit 506 may predict changes in the computing power of the SoCBox 400 using AI. For example, the prediction unit 506 predicts the computing power of the SoCBox 400 by inputting the information acquired by the information acquisition unit 504 into a learning model stored in the model storage unit 502. As a specific example, the prediction unit 506 may predict the moment when the computing power of the SoCBox 400 will be at its maximum.

The cooling execution unit 508 may start cooling the SoCBox 400 based on the change in the computing power of the SoCBox 400 predicted by the prediction unit 506. For example, the cooling execution unit 508 starts cooling the SoCBox 400 based on the moment when the computing power of the SoCBox 400 will be at its maximum, as predicted by the prediction unit 506. As a specific example, the cooling execution unit 508 starts cooling the SoCBox 400 at the moment when the computing power of the SoCBox 400 is at its maximum. This makes it possible to start cooling the SoCBox 400 when the computing power of the SoCBox 400 reaches its maximum and the amount of heat generated by the SoCBox 400 is at its maximum, and therefore cooling can be performed efficiently.

As a specific example, the cooling execution unit 508 starts cooling the SoCBox 400 in response to the state in which the computing power of the SoCBox 400 remains higher than a predetermined threshold for a predetermined period of time. Even if the computing power of the SoCBox 400 becomes high, if the computing power returns to a low state immediately thereafter, the temperature of the SoCBox 400 can be prevented from becoming excessively high. However, if the computing power of the SoCBox 400 remains high for a certain period of time, the temperature of the SoCBox 400 may continue to rise. The cooling execution unit 508 can prevent such a temperature rise.

The prediction unit 506 may predict the time until the temperature of SoCBox 400 becomes higher than a predetermined temperature, based on the prediction result of the moment when the computing power of SoCBox 400 becomes maximum. The cooling execution unit 508 may start cooling SoCBox 400 based on the time predicted by the prediction unit 506. For example, the cooling execution unit 508 calculates backwards from the time when the temperature of SoCBox 400 becomes higher than the predetermined temperature, determines the timing to start cooling SoCBox 400 so that the temperature of SoCBox 400 does not become higher than the predetermined temperature, and starts cooling SoCBox 400 at the determined timing.

The cooling execution unit 508 may execute cooling of the SoCBox 400 taking into consideration the time from the cooling trigger to the actual cooling. For example, the cooling execution unit 508 uses AI to predict the time until the SoCBox 400 is actually cooled when cooling of the SoCBox 400 is started in the situation in which the SoCBox 400 is placed, and controls the timing of starting cooling of the SoCBox 400 according to the prediction result. The cooling execution unit 508 may predict the time by inputting the information acquired by the information acquisition unit 504 into a learning model that uses the information acquired by the SoCBox 400 stored in the model storage unit 502 as input, and outputs the time until the SoCBox 400 is actually cooled when cooling of the SoCBox 400 is started. As a specific example, the cooling execution unit 508 instructs the cooling unit 600 to start cooling at a timing that is a predicted amount of time back from the timing at which cooling of the SoCBox 400 is actually desired to start.

The risk rate acquisition unit 511 acquires a risk rate. The risk rate acquisition unit 511 may calculate a risk rate using information acquired by the information acquisition unit 504. For example, the risk rate acquisition unit 511 calculates a risk rate by calculating the possibility of an accident occurring from the temperature of SoCBox 400 predicted by the prediction unit 506 using relationship data indicating the relationship between the temperature of SoCBox 400 and the occurrence status of an accident involving a vehicle equipped with SoCBox 400.

The risk rate acquisition unit 511 calculates a risk rate based on, for example, the position of the vehicle 300. The risk rate acquisition unit 511 calculates a risk rate that is higher the more objects there are around the vehicle 300. For example, the risk rate acquisition unit 511 calculates a risk rate that is higher the more other vehicles there are around the vehicle 300. For example, the risk rate acquisition unit 511 calculates a risk rate that is higher the more people there are around the vehicle 300. The risk rate acquisition unit 511 may determine the number, quantity, etc. of objects present around the vehicle 300 using information acquired from the camera 311, LiDAR 312, etc.

The risk rate acquisition unit 511 calculates the risk rate based on the weather in the area where the vehicle 300 is located, for example. The risk rate acquisition unit 511 calculates the risk rate so that it is higher in so-called bad weather than in so-called good weather. As a specific example, the risk rate acquisition unit 511 calculates the risk rate so that it is higher in rainy weather than in sunny weather. The risk rate acquisition unit 511 may determine the weather in the area where the vehicle 300 is located based on information received from a server that provides weather information. The risk rate acquisition unit 511 may determine the weather in the area where the vehicle 300 is located by using the camera 311 to detect clouds around the vehicle 300 or remotely from the vehicle 300.

The risk rate acquisition unit 511 may calculate the risk rate using a judgment method other than these. In addition, the risk rate acquisition unit 511 may calculate the risk rate by combining multiple judgment methods.

The cooling execution unit 508 may adjust the degree of cooling of the SoCBox 400 according to the risk rate acquired by the risk rate acquisition unit 511. The cooling execution unit 508 may, for example, store in advance a first threshold value for the risk rate and a second threshold value higher than the first threshold value. Then, the cooling execution unit 508 cools the SoCBox 400 at a first cooling intensity when the risk rate is lower than the first threshold value, cools the SoCBox 400 at a second cooling intensity stronger than the first cooling intensity when the risk rate is higher than the first threshold value and lower than the second threshold value, and cools the SoCBox 400 at a third cooling intensity stronger than the second cooling intensity when the risk rate is higher than the second threshold value. The number of cooling intensity stages is not limited to three.

Figure 59 shows an example of a schematic diagram of a SoCBox 400 and a cooling unit 600. Figure 59 shows an example where the cooling unit 600 is configured with a single cooling means. When the cooling execution device 500 predicts that the SoCBox 400 will start to generate heat or predicts that the temperature of the SoCBox 400 will exceed a predetermined threshold, the cooling unit 600 starts cooling, thereby cooling the entire SoCBox 400.

FIG. 60 shows an example of a schematic diagram of a SoCBox 400 and a cooling unit 600. FIG. 60 shows an example where the cooling unit 600 is configured with multiple cooling means for cooling each of the multiple parts of the SoCBox 400. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby achieving efficient cooling.

FIG. 61 shows an example of the SoCBox 400 and the cooling unit 600. FIG. 61 shows an example in which the cooling unit 600 is configured with two types of cooling means. The cooling execution device 500 predicts the temperature change of each of the multiple parts of the SoCBox 400, and when it predicts that any part will start to generate heat or that the temperature of any part will exceed a predetermined threshold, performs cooling using only the cooling means corresponding to that part, thereby realizing efficient cooling. Furthermore, the cooling execution device 500 increases the number of cooling means used as the temperature of the SoCBox 400 increases; in other words, in this example, first, cooling using one of the two types of cooling means is started, and when the temperature of the SoCBox 400 further increases, cooling using the other cooling means is started, thereby making it possible to efficiently use energy for cooling.

<Hardware configuration diagram>
62 shows an example of a hardware configuration of a computer 1200 functioning as the management server 100, the SoCBox 400, the cooling execution device 500, or the cooling device 700. A program installed in the computer 1200 can cause the computer 1200 to function as one or more "parts" of the device according to the present embodiment, or cause the computer 1200 to execute operations or one or more "parts" associated with the device according to the present embodiment, and/or cause the computer 1200 to execute a process or steps of the process according to the present embodiment. Such a program may be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks of the flowcharts and block diagrams described herein.

The computer 1200 according to this embodiment includes a CPU 1212, a RAM 1214, and a graphics controller 1216, which are connected to each other by a host controller 1210. The computer 1200 also includes input/output units such as a communication interface 1222, a storage device 1224, a DVD drive, and an IC card drive, which are connected to the host controller 1210 via an input/output controller 1220. The DVD drive may be a DVD-ROM drive, a DVD-RAM drive, etc. The storage device 1224 may be a hard disk drive, a solid state drive, etc. The computer 1200 also includes a ROM 1230 and a legacy input/output unit such as a keyboard, which are connected to the input/output controller 1220 via an input/output chip 1240.

The CPU 1212 operates according to the programs stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires image data generated by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into itself, and causes the image data to be displayed on the display device 1218.

The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive reads programs or data from a DVD-ROM or the like and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card and/or writes programs and data to an IC card.

ROM 1230 stores therein a boot program or the like executed by computer 1200 upon activation, and/or a program that depends on the hardware of computer 1200. I/O chip 1240 may also connect various I/O units to I/O controller 1220 via USB ports, parallel ports, serial ports, keyboard ports, mouse ports, etc.

The programs are provided by a computer-readable storage medium such as a DVD-ROM or an IC card. The programs are read from the computer-readable storage medium, installed in storage device 1224, RAM 1214, or ROM 1230, which are also examples of computer-readable storage media, and executed by CPU 1212. The information processing described in these programs is read by computer 1200, and brings about cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be constructed by realizing the operation or processing of information according to the use of computer 1200.

For example, when communication is performed between computer 1200 and an external device, CPU 1212 may execute a communication program loaded into RAM 1214 and instruct communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of CPU 1212, communication interface 1222 reads transmission data stored in a transmission buffer area provided in RAM 1214, storage device 1224, a DVD-ROM, or a recording medium such as an IC card, and transmits the read transmission data to the network, or writes received data received from the network to a reception buffer area or the like provided on the recording medium.

The CPU 1212 may also cause all or a necessary portion of a file or database stored in an external recording medium such as the storage device 1224, a DVD drive (DVD-ROM), an IC card, etc. to be read into the RAM 1214, and perform various types of processing on the data on the RAM 1214. The CPU 1212 may then write back the processed data to the external recording medium.

Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and may undergo information processing. CPU 1212 may perform various types of processing on data read from RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search/replacement, etc., as described throughout this disclosure and specified by the instruction sequence of the program, and write back the results to RAM 1214. CPU 1212 may also search for information in a file, database, etc. in the recording medium. For example, if multiple entries, each having an attribute value of a first attribute associated with an attribute value of a second attribute, are stored in the recording medium, CPU 1212 may search for an entry whose attribute value of the first attribute matches a specified condition from among the multiple entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

The above-described programs or software modules may be stored in a computer-readable storage medium on the computer 1200 or in the vicinity of the computer 1200. In addition, a recording medium such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the programs to the computer 1200 via the network.

The blocks in the flowcharts and block diagrams in this embodiment may represent stages of a process in which an operation is performed or "parts" of a device responsible for performing the operation. Particular stages and "parts" may be implemented by dedicated circuitry, programmable circuitry provided with computer-readable instructions stored on a computer-readable storage medium, and/or a processor provided with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuitry may include digital and/or analog hardware circuitry and may include integrated circuits (ICs) and/or discrete circuits. The programmable circuitry may include reconfigurable hardware circuitry including AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, and memory elements, such as, for example, field programmable gate arrays (FPGAs) and programmable logic arrays (PLAs).

A computer-readable storage medium may include any tangible device capable of storing instructions that are executed by a suitable device, such that a computer-readable storage medium having instructions stored thereon comprises an article of manufacture that includes instructions that can be executed to create means for performing the operations specified in the flowchart or block diagram. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), electrically erasable programmable read-only memories (EEPROMs), static random access memories (SRAMs), compact disk read-only memories (CD-ROMs), digital versatile disks (DVDs), Blu-ray disks, memory sticks, integrated circuit cards, and the like.

The computer readable instructions may include either assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk (registered trademark), JAVA (registered trademark), C++, etc., and conventional procedural programming languages such as the "C" programming language or similar programming languages.

The computer-readable instructions may be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, or to a programmable circuit, either locally or over a local area network (LAN), a wide area network (WAN) such as the Internet, so that the processor of the general-purpose computer, special-purpose computer, or other programmable data processing apparatus, or to a programmable circuit, executes the computer-readable instructions to generate means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

The present invention has been described above using an embodiment, but the technical scope of the present invention is not limited to the scope described in the above embodiment. It will be clear to those skilled in the art that various modifications and improvements can be made to the above embodiment. It is clear from the claims that forms incorporating such modifications or improvements can also be included in the technical scope of the present invention.

The order of execution of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before" or "prior to," and it should be noted that the processes may be performed in any order, unless the output of a previous process is used in a later process. Even if the operational flow in the claims, specifications, and drawings is explained using "first," "next," etc. for convenience, it does not mean that it is necessary to perform the processes in that order.

10 System 20 Network 30 Server 40 Temperature sensor 100 Management server 102 Information acquisition unit 104 Model generation unit 106 Model provision unit 108, 507

Creation unit

110, 506 Prediction unit 200, 200-1 to 200-4, 300

Vehicle

210, 310

Sensor

211, 311

Camera

212, 312 LiDAR
213, 313

mmWave sensor

214, 314

Ultrasonic sensor

215, 315

IMU sensor

216, 316

GNSS sensor

217, 317 GPS sensor 400 SoCBox
500 Cooling execution device 501 Detection unit 502, 550 Model storage unit 504, 560 Information acquisition unit 505 Estimation unit 508 Cooling execution unit 509 Output unit 510 Selection unit 511 Risk rate acquisition unit 520 Communication unit 530 Instruction unit 540 Cooling execution unit 600 Cooling unit 700 Cooling device 1200 Computer 1210 Host controller 1212 CPU
1214 RAM
1216 Graphic controller 1218 Display device 1220 Input/output controller 1222 Communication interface 1224 Storage device 1230 ROM
1240 Input/Output Chip

Claims

A prediction unit that predicts a temperature change of a control device mounted on the vehicle that controls automatic driving of the vehicle;
a cooling execution unit that starts cooling of the control device based on the temperature change predicted by the prediction unit.
The cooling execution device according to claim 1, wherein the cooling execution unit starts cooling the control device in response to the prediction unit predicting that the temperature of the control device will be higher than a predetermined threshold.
The cooling execution device according to claim 1, wherein the prediction unit predicts the temperature change of the control device using AI.
a model storage unit that stores a learning model that uses the information acquired by the control device as input and the temperature change of the control device as output, the learning model being generated by machine learning using the information acquired by the control device and the temperature change of the control device when the control device acquires the information as learning data;
and an information acquisition unit that acquires information acquired by the control device,
The cooling execution device according to claim 3 , wherein the prediction unit predicts the temperature change of the control device by inputting the information acquired by the information acquisition unit into the learning model.
The cooling execution device according to claim 4, wherein the information acquisition unit acquires sensor information acquired by the control device from a sensor mounted on the vehicle from the sensor or the control device.
The cooling execution device according to claim 4, wherein the information acquisition unit acquires from the control device an analysis result of an image captured by a camera mounted on the vehicle by the control device.
The cooling execution device according to claim 4, wherein the information acquisition unit acquires external information that the control device receives from an external device from the external device or the control device.
The cooling execution device according to claim 7, wherein the information acquisition unit acquires traffic information of the road on which the vehicle is located, which the control device receives from the external device, from the external device or the control device.
The cooling execution device according to claim 1, wherein the cooling execution unit starts cooling the control device using one or more cooling means selected from a plurality of types of cooling means depending on the temperature of the control device predicted by the prediction unit.
The cooling device according to claim 9, wherein the multiple types of cooling means include multiple of one or more types of air cooling means, one or more types of water cooling means, and liquid nitrogen cooling means.
The prediction unit predicts a temperature change of each of a plurality of parts of the control device,
The cooling execution device according to claim 10, wherein the cooling execution unit starts cooling the control device using a cooling means selected from a plurality of cooling means that cool each of a plurality of parts of the control device based on a prediction result by the prediction unit.
the controller having a plurality of processing chips, each processing chip being disposed at a different location on the controller;
The cooling implementation apparatus of claim 11 , wherein each of the plurality of cooling means is disposed at a position corresponding to each of the plurality of processing chips.
A program for causing a computer to function as a cooling execution device according to any one of claims 1 to 12.
1. A computer-implemented method for implementing cooling, comprising:
A prediction step of predicting a temperature change of a control device mounted on the vehicle that controls automatic driving of the vehicle;
and a cooling execution step of starting cooling of the control device based on the temperature change predicted in the prediction step.
A cooling system including a server and a cooling execution device,
The server,
an information acquisition unit that acquires location information of a vehicle having the cooling device and temperature information of a control device of the vehicle from the cooling device;
a prediction unit that predicts a temperature change of the control device based on location information of the vehicle having the cooling execution device acquired by the information acquisition unit and temperature information of the control device of the vehicle,
The cooling device includes:
an information acquisition unit that acquires, from the server, a prediction result of a temperature change of the control device predicted by the prediction unit of the server;
a cooling execution unit that starts cooling the control device based on a predicted result of a temperature change of the control device acquired by the information acquisition unit.
The server,
a creating unit that creates a map showing a relationship between a position of the vehicle having the cooling execution device and a temperature of a control device of the vehicle, based on position information of the vehicle having the cooling execution device acquired by the information acquiring unit and temperature information of the control device of the vehicle,
The cooling system according to claim 15, characterized in that the prediction unit predicts a temperature change of the control device based on location information of a vehicle having the cooling execution device acquired by the information acquisition unit, temperature information of a control device possessed by the vehicle, and a map created by the creation unit representing a relationship between the location of the vehicle and the temperature of the control device.
The information acquisition unit of the server acquires, from the cooling execution device, location information of a vehicle having the cooling execution device, temperature information of a control device of the vehicle, and information regarding the type of the vehicle;
the creation unit creates a map representing a relationship between a position of the vehicle and a temperature of the control device in the vehicle type based on the position information of the vehicle having the cooling execution device acquired by the information acquisition unit, the temperature information of a control device of the vehicle, and information on the type of the vehicle;
The cooling system according to claim 16, characterized in that the prediction unit of the server predicts a temperature change of the control device based on location information of a vehicle having the cooling execution device acquired by the information acquisition unit, temperature information of a control device possessed by the vehicle, and a map created by the creation unit representing a relationship between the location of the vehicle and the temperature of the control device for the type of vehicle.
The cooling system according to claim 15, characterized in that the cooling execution unit uses a prediction result of the temperature change of the control device acquired by the information acquisition unit to start cooling the control device a predetermined time before the control device begins to generate heat.
The cooling system according to claim 15, characterized in that the cooling execution unit uses a prediction result of the temperature change of the control device acquired by the information acquisition unit and starts cooling of the control device using one or more cooling means selected from multiple types of cooling means in accordance with the temperature change of the control device.
The multiple types of cooling means include one or multiple types of air cooling means, one or multiple types of water cooling means,
20. The cooling system of claim 19, comprising a plurality of: a liquid nitrogen cooling means;
A cooling execution method executed by a server and a cooling execution device, comprising:
an information acquisition step in which the server acquires, from the cooling execution device, location information of the vehicle having the cooling execution device and temperature information of a control device of the vehicle;
a prediction step in which the server predicts a temperature change of the control device based on location information of the vehicle having the cooling execution device acquired in the information acquisition step and temperature information of the control device of the vehicle; and an information acquisition step in which the cooling execution device acquires from the server a prediction result of the temperature change of the control device predicted in the prediction step of the server;
a cooling execution step of starting cooling of the control device based on the prediction of a temperature change of the control device acquired in the information acquisition step by the cooling execution device.
A cooling program including a program executed by a server and a program executed by a cooling execution device,
The server,
an information acquisition step of acquiring location information of a vehicle having the cooling execution device and temperature information of a control device of the vehicle from the cooling execution device;
a prediction step of predicting a temperature change of the control device based on location information of the vehicle having the cooling execution device acquired in the information acquisition step and temperature information of the control device of the vehicle;
The cooling device includes:
an information acquisition step of acquiring, from the server, a prediction result of a temperature change of the control device predicted by the prediction step of the server;
and a cooling execution step of starting cooling of the control device based on the predicted result of the temperature change of the control device acquired in the information acquisition step.
A cooling system including a server and a cooling execution device,
The server,
an information acquisition unit that acquires location information of a vehicle having the cooling device, temperature information of a control device of the vehicle, information regarding traffic conditions, and weather information from the cooling device;
a prediction unit that predicts a temperature change of the control device based on location information of the vehicle having the cooling execution device acquired by the information acquisition unit, temperature information of a control device of the vehicle, information about the traffic situation, and weather information,
The cooling device includes:
an information acquisition unit that acquires, from the server, a prediction result of a temperature change of the control device predicted by the prediction unit of the server;
a cooling execution unit that starts cooling the control device based on a predicted result of a temperature change of the control device acquired by the information acquisition unit.
The server,
a creation unit that creates a map showing a relationship between the position of the vehicle, the information about the traffic conditions, the weather information, and the temperature of the control device, based on the position information of the vehicle having the cooling execution device acquired by the information acquisition unit, the temperature information of a control device of the vehicle, the information about the traffic conditions, and the weather information,
The cooling system of claim 23, wherein the prediction unit predicts a temperature change of the control device based on location information of a vehicle having the cooling execution device acquired by the information acquisition unit, temperature information of a control device possessed by the vehicle, information regarding the traffic conditions, the weather information, and a map created by the creation unit representing a relationship between the location of the vehicle, information regarding the traffic conditions, the weather information, and the temperature of the control device.
The cooling system of claim 24, wherein the creation unit creates a map showing a relationship between the position of the vehicle and the temperature of the control device for each of the information on the traffic conditions and the weather information from the position information of the vehicle having the cooling execution device acquired by the information acquisition unit, temperature information of the control device possessed by the vehicle, information on the traffic conditions, and the weather information.
The information acquisition unit of the server further acquires information regarding the type of the vehicle from the cooling execution device,
The cooling system of claim 24, wherein the creation unit creates a map representing a relationship between the location of the vehicle, the information about the traffic conditions, the weather information, the type of the vehicle, and the temperature of the control device, based on location information of a vehicle having the cooling execution device, temperature information of a control device possessed by the vehicle, information about the traffic conditions, the weather information, and information about the type of the vehicle.
The cooling system according to claim 23, characterized in that the cooling execution unit uses a prediction result of the temperature change of the control device acquired by the information acquisition unit to start cooling the control device a predetermined time before the control device begins to generate heat.
The cooling system of claim 23, characterized in that the cooling execution unit uses a prediction result of the temperature change of the control device acquired by the information acquisition unit and starts cooling of the control device using one or more cooling means selected from multiple types of cooling means in accordance with the temperature change of the control device.
The multiple types of cooling means include one or multiple types of air cooling means, one or multiple types of water cooling means,
30. The cooling system of claim 28, comprising a plurality of: a liquid nitrogen cooling means; and a liquid nitrogen cooling means.
A cooling execution method executed by a server and a cooling execution device, comprising:
an information acquisition process in which the server acquires, from the cooling execution device, location information of the vehicle having the cooling execution device, temperature information of a control device of the vehicle, information regarding traffic conditions, and weather information;
a prediction step in which the server predicts a temperature change of the control device based on location information of the vehicle having the cooling execution device acquired in the information acquisition step, temperature information of a control device of the vehicle, information about the traffic situation, and weather information;
an information acquisition step in which the cooling execution device acquires, from the server, a prediction result of a temperature change of the control device predicted by the prediction step of the server;
a cooling execution step of starting cooling of the control device based on the prediction of a temperature change of the control device acquired in the information acquisition step by the cooling execution device.
A cooling program including a program executed by a server and a program executed by a cooling execution device,
The server,
an information acquisition step of acquiring location information of a vehicle having the cooling execution device and temperature information of a control device of the vehicle from the cooling execution device;
a prediction step of predicting a temperature change of the control device based on location information of the vehicle having the cooling execution device acquired in the information acquisition step, temperature information of a control device of the vehicle, information on traffic conditions, and weather information;
The cooling device includes:
an information acquisition step of acquiring, from the server, a prediction result of a temperature change of the control device predicted by the prediction step of the server;
and a cooling execution step of starting cooling of the control device based on the predicted result of the temperature change of the control device acquired in the information acquisition step.
A cooling system including a server and a cooling execution device,
The server,
an information acquisition unit that acquires, from the cooling execution device, position information of each integrated circuit in the control device, information related to processing of the each integrated circuit, and information related to a driving state of the vehicle;
a prediction unit that predicts a temperature change at each position of the control device based on position information of each integrated circuit in the control device, information related to processing of each integrated circuit, and information related to a driving state of the vehicle, all of which are acquired by the information acquisition unit;
The cooling device includes:
an information acquisition unit that acquires, from the server, a prediction result of a temperature change at each position of the control device predicted by the prediction unit of the server;
and a cooling execution unit that starts cooling the control device based on the predicted results of temperature changes at each position of the control device acquired by the information acquisition unit.
The cooling system of claim 32, characterized in that the prediction unit predicts temperature changes over time at each position of the control device using position information of each integrated circuit in the control device acquired by the information acquisition unit, information regarding the processing of each integrated circuit, and information regarding the driving status of the vehicle.
The cooling system according to claim 32, characterized in that the cooling execution unit starts cooling at a position where heat is generated in the control device using a prediction result of temperature change at each position of the control device acquired by the information acquisition unit.
The cooling system of claim 34, characterized in that the cooling execution unit uses the predicted results of temperature change at each position of the control device acquired by the information acquisition unit to start cooling the position where heat generation occurs in the control device a predetermined time before the control device starts to generate heat.
The cooling system of claim 32, characterized in that the cooling execution unit uses the predicted results of temperature changes at each position of the control device acquired by the information acquisition unit, and starts cooling the positions where heat is generated in the control device using one or more cooling means selected from multiple types of cooling means in accordance with the temperature changes at each position of the control device.
The multiple types of cooling means include one or multiple types of air cooling means, one or multiple types of water cooling means,
37. The cooling system of claim 36, comprising more than one of: and liquid nitrogen cooling means.
A cooling method executed by a server and a cooling execution device, comprising:
an information acquisition step in which the server acquires, from the cooling execution device, location information of each integrated circuit in the control device, information related to processing of each integrated circuit, and information related to a driving state of the vehicle;
a prediction step in which the server predicts a temperature change at each position of the control device based on position information of each integrated circuit in the control device, information related to processing of each integrated circuit, and information related to a driving state of the vehicle, all of which are acquired by the information acquisition step;
an information acquisition step in which the cooling execution device acquires from the server a prediction result of a temperature change at each position of the control device predicted by the prediction step of the server;
and a cooling execution step of starting cooling of the control device based on the predicted results of temperature changes at each position of the control device acquired by the information acquisition step.
A cooling program including a program executed by a server and a program executed by a cooling execution device,
The server,
an information acquisition step of acquiring, from the cooling execution device, position information of each integrated circuit in the control device, information related to processing of the each integrated circuit, and information related to a driving state of the vehicle;
a prediction step of predicting a temperature change at each position of the control device based on position information of each integrated circuit in the control device, information related to the processing of each integrated circuit, and information related to a driving state of the vehicle, which are acquired in the information acquisition step;
The cooling device includes:
an information acquisition step of acquiring, from the server, a prediction result of a temperature change at each position of the control device predicted by the prediction step of the server;
and a cooling execution step of starting cooling of the control device based on the predicted results of temperature changes at each position of the control device acquired by the information acquisition step.
A detection unit that detects a temperature of a control device mounted on the vehicle that controls automatic driving of the vehicle;
a cooling execution unit that executes cooling of the control device using a predetermined cooling means based on a time during which the temperature detected by the detection unit continues to be equal to or higher than a predetermined temperature;
A cooling execution device comprising:
When the time during which the temperature is equal to or higher than the predetermined temperature exceeds a predetermined threshold, the cooling execution unit executes cooling using the cooling means, which includes one or more types of air cooling means, one or more types of water cooling means, and a liquid nitrogen cooling means.
41. The cooling implementation of claim 40.
The cooling execution unit executes rapid cooling when the temperature exceeds a predetermined threshold.
42. The cooling implementation of claim 41.
A prediction unit that predicts a temperature change of a control device mounted on the vehicle that controls automatic driving of the vehicle,
the cooling execution unit executes cooling using the cooling means based on a time during which the temperature change predicted by the prediction unit will continue to be equal to or higher than the predetermined temperature.
41. The cooling implementation of claim 40.
A prediction unit predicts a temperature change of each of the plurality of parts of the control device,
the cooling execution unit starts cooling the control device using a cooling means selected from a plurality of cooling means that cool each of a plurality of parts of the control device based on a prediction result by the prediction unit.
42. The cooling implementation of claim 41.
the controller having a plurality of processing chips, each processing chip being disposed at a different location on the controller;
each of the plurality of cooling means is disposed at a position corresponding to each of the plurality of processing chips;
45. The cooling implementation of claim 44.
A cooling execution program for causing a computer to function as the cooling execution device according to any one of claims 40 to 45.
1. A computer-implemented method for implementing cooling, comprising:
A detection step of detecting a temperature of a control device mounted on the vehicle that controls automatic driving of the vehicle;
a cooling execution step of executing cooling of the control device using a predetermined cooling means based on a time during which the temperature detected in the detection step continues to be equal to or higher than a predetermined temperature;
A method for performing cooling comprising:
An estimation unit that estimates switching between automatic driving and manual driving based on a preset driving route;
a creation unit that creates a cooling schedule in which a predetermined cooling means is set based on an estimation result of the estimation unit;
a cooling execution unit that executes cooling of a control device mounted on a vehicle that controls automatic driving of the vehicle based on the cooling schedule created by the creation unit;
A cooling device comprising:
The estimation unit estimates whether or not switching from the autonomous driving to the manual driving will occur based on road conditions of the travel route.
49. The cooling implementation of claim 48.
the creation unit creates the cooling schedule in which a cooling means for a driving section of the manual driving is set when the estimation unit estimates that the automatic driving will be switched to the manual driving,
When the estimation unit estimates that the manual driving will be switched to the automatic driving, the cooling schedule is created in which a cooling means for a driving section of the automatic driving is set.
49. The cooling implementation of claim 48.
A detection unit that detects a temperature change of a control device mounted on the vehicle that controls automatic driving of the vehicle;
A prediction unit that predicts a temperature change of the control device,
the creation unit compares the actual temperature change detected by the detection unit with the predicted temperature change predicted by the prediction unit, and creates the cooling schedule in which the predetermined cooling means is set when the predicted temperature change exceeds the actual temperature change.
49. The cooling implementation of claim 48.
The cooling means includes a plurality of one or more types of air cooling means, one or more types of water cooling means, and liquid nitrogen cooling means.
49. The cooling implementation of claim 48.
A prediction unit that predicts a temperature change of a control device mounted on the vehicle that controls automatic driving of the vehicle,
the cooling execution unit executes cooling of the control device using a cooling means selected from a plurality of cooling means that cool each of a plurality of parts of the control device based on the cooling schedule created by the creation unit.
53. The cooling implementation of claim 52.
the controller having a plurality of processing chips, each processing chip being disposed at a different location on the controller;
each of the plurality of cooling means is disposed at a position corresponding to each of the plurality of processing chips;
54. The cooling implementation of claim 53.
A program for causing a computer to function as a cooling execution device according to any one of claims 48 to 54.
1. A computer-implemented method for implementing cooling, comprising:
An estimation step of estimating switching between autonomous driving and manual driving based on a preset driving route;
a creating step of creating a cooling schedule in which cooling conditions based on a predetermined cooling means are set based on the estimation result of the estimation step;
a cooling execution step of executing cooling of a control device mounted on a vehicle that controls automatic driving of the vehicle based on the cooling schedule created in the creation step;
A method for performing cooling comprising:
A prediction unit that predicts a temperature change of a control device mounted on the vehicle that controls automatic driving of the vehicle;
a cooling execution unit that performs cooling so that the temperature of the control device is maintained within a predetermined temperature range based on the temperature change predicted by the prediction unit.
58. The cooling device of claim 57, wherein the cooling execution unit determines the predetermined temperature range in response to a threshold temperature that is predetermined for the control device.
The cooling device according to claim 57, wherein the prediction unit predicts the temperature change of the control device using AI.
a model storage unit that stores a learning model that uses the information acquired by the control device as input and the temperature change of the control device as output, the learning model being generated by machine learning using the information acquired by the control device and the temperature change of the control device when the control device acquires the information as learning data;
and an information acquisition unit that acquires information acquired by the control device,
60. The cooling device according to claim 59, wherein the prediction unit predicts the temperature change of the control device by inputting the information acquired by the information acquisition unit into the learning model.
61. The cooling device according to claim 60, wherein the information acquisition unit acquires sensor information, which the control device acquires from a sensor mounted on the vehicle, from the sensor or the control device.
The cooling device according to claim 60, characterized in that the information acquisition unit acquires, from the control device, an analysis result obtained by the control device analyzing an image captured by a camera mounted on the vehicle.
61. The cooling device according to claim 60, wherein the information acquisition unit acquires external information, which the control device receives from an external device, from the external device or the control device.
64. The cooling device according to claim 63, wherein the information acquisition unit acquires traffic information of a road on which the vehicle is located, which the control device receives from the external device, from the external device or the control device.
The cooling device according to claim 57, characterized in that the cooling execution unit starts cooling the control device using one or more cooling means selected from a plurality of types of cooling means depending on the temperature of the control device predicted by the prediction unit.
66. The cooling device of claim 65, wherein the plurality of types of cooling means include a plurality of one or more types of air cooling means, one or more types of water cooling means, and liquid nitrogen cooling means.
The prediction unit predicts a temperature change of each of a plurality of parts of the control device,
The cooling device according to claim 66, characterized in that the cooling execution unit starts cooling the control device using a cooling means selected from a plurality of cooling means that cool each of a plurality of parts of the control device based on the prediction result by the prediction unit.
the controller having a plurality of processing chips, each processing chip being disposed at a different location on the controller;
68. The cooling device according to claim 67, wherein each of the plurality of cooling means is disposed at a position corresponding to each of the plurality of processing chips.
1. A cooling method carried out in a cooling device, comprising:
A prediction step of predicting a temperature change of a control device mounted on the vehicle that controls automatic driving of the vehicle;
a cooling execution step of performing cooling so that the temperature of the control device is maintained within a predetermined temperature range based on the temperature change predicted by the prediction step.
A prediction step of predicting a temperature change of a control device mounted on the vehicle that controls automatic driving of the vehicle;
a cooling execution step of performing cooling so that the temperature of the control device is maintained within a predetermined temperature range based on the temperature change predicted in the prediction step.
A detection unit that detects a temperature change of a control device mounted on the vehicle that controls automatic driving of the vehicle;
A selection unit that selects a predetermined operating condition for lowering the temperature of the control device when the temperature change exceeds a predetermined threshold value;
an output unit that outputs the predetermined operating condition based on a selection result of the selection unit;
A cooling device comprising:
the selection unit selects, as the predetermined operating condition, an operating condition that reduces a calculation amount related to a predetermined information processing of the control device when the temperature change exceeds a predetermined threshold.
72. The cooling implementation of claim 71.
Further comprising an information acquisition unit that acquires a result of the information processing related to the autonomous driving from an external information processing device that performs information processing related to the autonomous driving as a predetermined information processing of the control device,
72. The cooling implementation of claim 71.
The selection unit selects, as the predetermined operating condition, an operating condition that suppresses an operating speed of the autonomous driving to a predetermined speed or less when the temperature change exceeds a predetermined threshold.
72. The cooling implementation of claim 71.
The selection unit selects, as the predetermined operating condition, an operating condition for changing the automatic operation to a manual operation when the temperature change exceeds a predetermined threshold.
72. The cooling implementation of claim 71.
the selection unit selects, as the predetermined driving condition, a driving condition in which the vehicle is stopped at a predetermined position on a road included in a driving route of the autonomous driving, when the temperature change exceeds a predetermined threshold.
72. The cooling implementation of claim 71.
The selection unit selects, as the predetermined operating condition, an operating condition that suppresses acquisition of predetermined information used for information processing of the autonomous driving when the temperature change exceeds a predetermined threshold.
72. The cooling implementation of claim 71.
A program for causing a computer to function as a cooling execution device according to any one of claims 71 to 77.
1. A computer-implemented method for implementing cooling, comprising:
A detection step of detecting a temperature change of a control device mounted on the vehicle that controls automatic driving of the vehicle;
a selection step of selecting a predetermined operating condition for reducing the temperature of the control device when the temperature change exceeds a predetermined threshold;
an output step of outputting the predetermined operating condition based on a selection result of the selection step;
A method for performing cooling comprising:
A prediction unit that predicts a temperature change of a control device mounted on the vehicle that controls automatic driving of the vehicle;
a communication unit that communicates with other vehicles that are present within a predetermined range based on the temperature change predicted by the prediction unit;
and an instruction unit that instructs the control device to execute a calculation related to control of automatic driving of another vehicle with which communication is being performed by the communication unit.
The cooling device according to claim 80, characterized in that the communication unit determines that another vehicle present within a range in which communication with another vehicle can be maintained for a predetermined time is a vehicle present within the predetermined range and communicates with the other vehicle.
The cooling device according to claim 80, further comprising a cooling execution unit that starts cooling of the control device based on the temperature change predicted by the prediction unit.
The cooling device according to claim 82, wherein the cooling execution unit starts cooling the control device in response to the prediction unit predicting that the temperature of the control device will be higher than a predetermined threshold value.
The cooling device according to claim 80, wherein the prediction unit predicts the temperature change of the control device using AI.
a model storage unit that stores a learning model that uses the information acquired by the control device as input and the temperature change of the control device as output, the learning model being generated by machine learning using the information acquired by the control device and the temperature change of the control device when the control device acquires the information as learning data;
and an information acquisition unit that acquires information acquired by the control device,
The cooling device according to claim 84, wherein the prediction unit predicts the temperature change of the control device by inputting the information acquired by the information acquisition unit into the learning model.
86. The cooling device according to claim 85, wherein the information acquisition unit acquires sensor information, which the control device acquires from a sensor mounted on the vehicle, from the sensor or the control device.
86. The cooling device according to claim 85, wherein the information acquisition unit acquires, from the control device, an analysis result obtained by the control device analyzing an image captured by a camera mounted on the vehicle.
86. The cooling device according to claim 85, wherein the information acquisition unit acquires external information, which the control device receives from an external device, from the external device or the control device.
89. The cooling device according to claim 88, wherein the information acquisition unit acquires traffic information of a road on which the vehicle is located, which the control device receives from the external device, from the external device or the control device.
The cooling device according to claim 82, characterized in that the cooling execution unit starts cooling the control device using one or more cooling means selected from a plurality of types of cooling means depending on the temperature of the control device predicted by the prediction unit.
91. The cooling device of claim 90, wherein the plurality of types of cooling means include a plurality of one or more types of air cooling means, one or more types of water cooling means, and liquid nitrogen cooling means.
The prediction unit predicts a temperature change of each of a plurality of parts of the control device,
The cooling device according to claim 91, characterized in that the cooling execution unit starts cooling the control device using a cooling means selected from a plurality of cooling means that cool each of a plurality of parts of the control device based on the prediction result by the prediction unit.
the controller having a plurality of processing chips, each processing chip being disposed at a different location on the controller;
93. The cooling device according to claim 92, wherein each of the plurality of cooling means is disposed at a position corresponding to each of the plurality of processing chips.
1. A cooling method carried out in a cooling device, comprising:
A prediction step of predicting a temperature change of a control device mounted on the vehicle that controls automatic driving of the vehicle;
a communication step of communicating with other vehicles present within a predetermined range based on the temperature change predicted by the prediction step;
and an instruction step of instructing the control device to execute a calculation related to control of automatic driving of another vehicle with which communication is being performed by the communication step.
A prediction step of predicting a temperature change of a control device mounted on the vehicle that controls automatic driving of the vehicle;
a communication step of communicating with other vehicles present within a predetermined range based on the temperature change predicted by the prediction step;
and an instruction procedure for instructing the control device to execute a calculation related to control of automatic driving of another vehicle with which communication is being performed through the communication procedure.
A prediction unit that predicts a change in computing power of a control device mounted on the vehicle that controls automatic driving of the vehicle;
a cooling execution unit that starts cooling of the control device based on the change predicted by the prediction unit.
The cooling execution device according to claim 96, wherein the prediction unit predicts changes in the computing power of the control device using AI.
The prediction unit predicts a moment when the computing power of the control device will be maximized;
98. The cooling implementation unit of claim 97, wherein the cooling implementation unit initiates cooling of the control device based on the moment predicted by the prediction unit.
The cooling execution device of claim 98, wherein the cooling execution unit starts cooling the control device at the moment when the computing power of the control device is maximized.
the prediction unit predicts a time until a temperature of the control device becomes higher than a predetermined temperature based on a prediction result of the moment when the computing power of the control device becomes maximum;
100. The cooling execution device of claim 99, wherein the cooling execution unit initiates cooling of the control device based on the time predicted by the prediction unit.
a model storage unit that stores a learning model that uses the information acquired by the control device and the computing power of the control device at the time when the control device acquired the information as learning data, the learning model being generated by machine learning, and that uses the information acquired by the control device as input and the computing power of the control device as output;
An information acquisition unit that acquires information acquired by the control device,
97. The cooling execution apparatus of claim 96, wherein the prediction unit predicts a change in the computing power of the control device by inputting information acquired by the information acquisition unit into the learning model.
The cooling execution device according to claim 101, wherein the information acquisition unit acquires at least one of sensor information acquired by the control device from a sensor mounted on the vehicle, an analysis result obtained by the control device analyzing an image captured by a camera mounted on the vehicle, external information received by the control device from an external device, and traffic information of a road on which the vehicle is located received by the control device from the external device.
a model storage unit that stores a learning model that uses information acquired by the control device as input and outputs the time until the control device is cooled down when cooling of the control device is started, the learning model being generated by machine learning using information acquired by the control device and a time until the control device is cooled down when cooling of the control device is started when the control device acquires the information as learning data;
An information acquisition unit that acquires information acquired by the control device;
Further comprising:
The cooling execution unit determines the timing to start cooling the control device based on the change predicted by the prediction unit and the time it takes for the control device to be cooled when cooling of the control device is started, obtained by inputting the change predicted by the prediction unit and the information acquired by the information acquisition unit into the learning model.
The cooling execution device according to claim 96, wherein the cooling execution unit adjusts the degree of cooling of the control device according to a risk rate indicating the probability of a risk that the control device will not function properly due to a high temperature of the control device, affecting normal automatic driving of the vehicle.
The cooling execution unit cools the control device with a first cooling intensity when the risk rate is lower than a first threshold, cools the control device with a second cooling intensity stronger than the first cooling intensity when the risk rate is higher than the first threshold and lower than a second threshold higher than the first threshold, and cools the control device with a third cooling intensity stronger than the second cooling intensity when the risk rate is higher than the second threshold. The cooling execution device of claim 104.
A program for causing a computer to function as a cooling execution device according to any one of claims 96 to 104.
1. A computer-implemented method for implementing cooling, comprising:
A prediction step of predicting a change in computing power of a control device mounted on the vehicle that controls automatic driving of the vehicle;
and a cooling execution step of starting cooling of the control device based on the change predicted in the prediction step.