JP7263580B1 - Server system and vehicle - Google Patents

Abstract

A server system is capable of appropriately allocating resources for calculations related to vehicle behavior. A server system (1) includes a receiving section (18) for receiving vehicle information, a first control section (4) for performing calculations regarding the behavior of each vehicle (100) using control software, and a vehicle A container for operating the control software is defined in units corresponding to at least one of the use case of each vehicle (100) corresponding to the information and the range in which each vehicle (100) is located. a second control unit (6) that allocates resources used for the operation of the server system (1) and increases or decreases the amount of resources allocated to at least one of the containers when a predetermined condition regarding the processing load in the server system (1) is satisfied; A transmitter (16) for transmitting a control signal instructing the behavior calculated by the first controller (4) to each vehicle. [Selection drawing] Fig. 1

Description

The present invention relates to server systems and vehicles.

As a countermeasure against functional failure in a server system that performs calculations related to vehicle behavior, for example, Patent Document 1 discloses a vehicle that compensates for information by vehicle-to-vehicle communication when communication with a communication center having information cannot be performed.

JP 2019-101641 A

In a server system such as that described above, if resources for calculations related to vehicle behavior are not properly allocated, it becomes a factor that causes a malfunction. Such a problem cannot be solved by the invention according to Patent Document 1.

An aspect of the present invention has been made in view of the above problems, and an object thereof is to enable a server system to appropriately allocate resources for calculations related to vehicle behavior.

A server system according to an aspect of the present invention includes a receiving unit that receives vehicle information indicating the state of each vehicle from one or more vehicles, and a first control unit that performs calculations related to the behavior of each vehicle using control software. and a container in which the control software is operated is defined by a unit corresponding to at least one of the use case of each vehicle corresponding to the vehicle information and the range in which each vehicle is located, and the control is performed for each container a second control unit that allocates resources used for software operation and increases or decreases the amount of resources allocated to at least one of the containers when a predetermined condition regarding the processing load in the server system is satisfied; a transmitting unit configured to transmit a control signal indicating the behavior calculated by the unit to each vehicle.

A vehicle according to another aspect of the present invention is a vehicle associated with a server system, wherein the server system instructs to perform calculations related to the behavior of one or more vehicles included in a specific range including the own vehicle. a receiving unit for receiving; a control unit for performing the calculation using control software when the receiving unit receives the instruction; and a transmitting unit for transmitting information indicating the state of the host vehicle to the server system. and a transmission unit configured to transmit a control signal indicating the behavior calculated by the control unit to other vehicles included in the specific range by inter-vehicle communication.

A server system or a vehicle control program for implementing the server system in a computer by operating a computer as each part (software element) provided in the server system or vehicle according to each aspect of the present invention, and a computer-readable recording thereof recording media are also included in the scope of the present invention.

Further, the control program may use various machine learning methods in the process of causing the computer to operate as each of the parts or in other processes. In this case, the program using the machine learning technique may operate on a server system or vehicle, or may operate on another device (for example, edge computer or cloud server).

According to one aspect of the present invention, the server system can appropriately allocate resources according to the state of the vehicle and the processing load in calculations related to the behavior of the vehicle.

1 is an example block diagram showing a functional configuration of a server system and a vehicle associated with the server system; FIG. FIG. 10 is an example of a conceptual diagram for explaining a container defined by a second control unit; FIG. 10 is an example of a flowchart showing the flow of processing according to processing example 1, which is mainly performed by a server system; FIG. 1 is an example of a conceptual diagram of road traffic realized by a server system and vehicles; FIG. FIG. 10 is an example of a flowchart showing a flow of processing according to processing example 2, which is mainly performed by a server system; FIG. It is an example of the conceptual diagram of the road traffic which illustrated the specific range which the 3rd control part set. FIG. 4 is a conceptual diagram showing the amounts of resources allocated to each container before and after offload processing;

An embodiment of the present invention will be described in detail below.

[1. Configuration example of server system 1 and vehicle 100]
FIG. 1 is an example of a block diagram showing a functional configuration of a server system 1 and a vehicle 100 associated with the server system 1. As shown in FIG.

The server system 1 is a device that functions as a server for one or more vehicles 100, receives vehicle information from each vehicle 100, and transmits information for defining the behavior of each vehicle 100. . Here, the information for defining the behavior of the vehicle 100 may include a control signal for controlling the behavior of the self-driving vehicle and information indicating the content of instructions to the driver. Vehicle information is information indicating the state of the vehicle 100, and is information including the position and speed of the vehicle 100, use cases, and the like. The vehicle information may include information, image data, and the like indicating the surroundings of the vehicle, sensed by a sensor separately provided in the vehicle. Further, the use case of the vehicle 100 means what kind of situation the vehicle 100 is in or what kind of operation it is going to perform. For example, merging vehicles 100, making a U-turn, moving to a parking space, and driving on a highway are examples of use cases.

The server system 1 includes a control section 2 , a storage section 12 and a communication section 14 . The control unit 2 is a control device that controls the entire server system 1 , and includes a first control unit 4 , a second control unit 6 , a third control unit 8 and a learning unit 10 .

The first control unit 4 performs calculations regarding the behavior of each vehicle 100 using control software. The control software is software that operates in a container, which is a virtually partitioned execution environment, under the control of the container engine. That is, the control software operating in the first container and the control software operating in the second container perform independent calculations. Recent technologies using containers include Docker (registered trademark) and Kubernetes (registered trademark).

The second control unit 6 defines one or more containers in which the control software is to be operated, and allocates resources used for the operation of the control software to each container. The resource here means the processing capacity of the server system 1 .

Further, the second control unit 6 increases or decreases the amount of resources allocated to at least one of the containers when a predetermined condition regarding the processing load in the server system 1 is satisfied. That is, the amount of resources allocated to each container may be variable and different from each other. From another aspect, the occupancy rate of the control unit 2 implemented as a CPU or the like and the storage unit 12 implemented as a memory or the like may differ from container to container. Further, the predetermined condition is, for example, a matter related to the processing load of the receiving unit, such as when network congestion occurs in communication between the server system 1 and the vehicle 100, or when the processing load of the first control unit 4 A related matter is a condition that is satisfied when a certain amount of excess or deficiency of resources occurs in the control software.

FIG. 2 is an example of a conceptual diagram for explaining the container defined by the second control unit 6. As shown in FIG. In the server system 1 of FIG. 2, description of members other than the container realized on the storage unit 12 and the communication unit 14 is omitted. In the example of FIG. 2, containers 23 and 33 are containers corresponding to area A in which a certain vehicle 100 is located, and containers 25 and 35 are containers corresponding to area B in which another vehicle 100 is located. A frame line 21 indicates that the contained container corresponds to use case A, and a frame line 31 indicates that the contained container corresponds to use case B. there is That is, for example, the container 23 is a container that is used for operation of control software for performing calculations related to the behavior of the vehicle 100 that corresponds to the use case A and is included in the range A.

The second control unit 6 defines a container in which the control software is to be operated in units corresponding to at least one of the use case of each vehicle 100 corresponding to the vehicle information and the range in which each vehicle 100 is located. The second control unit 6 may, for example, define a container for each use case of each vehicle 100, or define a container for each region where each vehicle 100 is located. Also, the size of each container in FIG. 2 indicates the amount of resources allocated to the container. A frame line 23' indicates an example in which the second control unit 6 increases the amount of resources allocated to the container 23, and a frame line 25' indicates a decrease in the amount of resources allocated to the container 25 by the second control unit 6. It shows an example of

The second control unit 6 may be configured to allocate an amount of resources according to the shape of the road included in the range to containers defined by units according to the range in which each vehicle 100 is located. Here, the resource amount may be, for example, the amount per vehicle 100 included in the range within a predetermined time. Further, the shape of a road means a shape classified as, for example, a straight road, a curved road, or a junction road. For example, the second control unit 6 is configured to allocate a larger amount of resources to a container corresponding to a range including road intersections than to a container corresponding to a range not including road intersections. may According to the above configuration, the second control unit 6 can determine the amount of resource to be allocated to the container according to the complexity of the shape of the road.

In addition, the second control unit 6 determines that the container specified by the unit according to the use case of each vehicle 100 is subject to acceleration of the vehicle 100, traveling at a predetermined speed or higher, or change of direction. It may be configured to allocate the amount of resources according to whether or not. According to the above configuration, the second control unit 6 can determine the amount of resources to be allocated to the container, for example, according to the risk level of the use case.

The third control unit 8 performs processing for setting a specific range on the road and at least a part of the calculation performed by the first control unit 4 for the vehicle 100 included in the specific range. off-road processing to be executed by a type 1 vehicle; Here, the first class vehicle is an example of the vehicle 100 . In the off-road processing, the transmission unit 16 transmits information necessary for calculation to the first class vehicle. Details of the processing of the third control unit 8 and the type 1 vehicle will be described later.

The learning unit 10 receives one or more pieces of vehicle information, and creates a learning model that outputs a prediction about the processing load on the server system 1 as a set of one or more pieces of vehicle information and information indicating the processing load on the server system 1 . is used as training data for learning. Also, for example, the second control unit 6 may determine the amount of resources to be allocated to the container after a certain period of time based on the prediction output by the learning model.

The machine learning method executed by the learning unit 10 is not limited to a specific method. For example, when vehicle information includes image data, CNN (Convolutional Neural Network) or RNN (Recurrent Neural Network) may be used. There may be.

Also, the learning unit 10 may be configured to use any one of the following machine learning techniques or a combination thereof, for example.

・Support Vector Machine (SVM)
・Clustering
・Inductive Logic Programming (ILP)
・Genetic Algorithms (GP)
・Bayesian Network (BN)
The storage unit 12 is a storage device that stores various types of information, such as information for identifying each vehicle 100, information indicating the state of each vehicle 100, information regarding roads and maps, and the like. The storage unit 12 also stores a parameter set that defines the learning model described above. The learning unit 10 updates the values of the parameter set stored in the storage unit 12 by learning the learning model. In one aspect, the learning unit 10 updates the values of the parameter set in a gradient direction that decreases the loss function defined by the vehicle information and the output values of the learning model.

The communication unit 14 is a member that transmits and receives various types of information under the control of the control unit 2 and includes a transmission unit 16 and a reception unit 18 . As illustrated in FIG. 2 , the communication unit 14 normally communicates with each vehicle 100 via one or more base stations 200 using LTE V2X indirect communication, 5G NR V2X indirect communication, or the like. The transmission unit 16 transmits, for example, a control signal that instructs the behavior calculated by the first control unit 4 to each vehicle 100 . The receiving unit 18 receives vehicle information indicating the state of each vehicle 100 from one or more vehicles 100, for example. The receiving unit 18 also has a function of setting a period for receiving vehicle information for each vehicle 100 .

The vehicle 100 is a connected car, a self-driving car, or a similar car, and includes a control unit 102 , a storage unit 112 , a communication unit 114 and an operation unit 120 .

Control unit 102 is a control device that controls the entire vehicle 100 . The storage unit 112 is a storage device that stores various types of information, and stores, for example, information for connecting to the server system 1, information about the host vehicle, information about roads and maps, and the like.

The communication unit 114 is a member that transmits and receives various types of information under the control of the control unit 102 , and includes a transmission unit 116 and a reception unit 118 . The transmission unit 116 transmits vehicle information to the server system 1, for example. The receiving unit 118 receives a control signal for controlling behavior of the own vehicle, which is transmitted from the server system 1, for example.

Information transmitted and received between the server system 1 and each vehicle 100 is not limited to the information described above. may be broken.

The operation unit 120 is a mechanism for operating each part of the own vehicle and each operating part itself. When the own vehicle is an automatic driving vehicle, the operating unit 120 automatically operates each unit of the own vehicle according to the control contents indicated by the control signal received by the receiving unit 118 . The operation unit 120 may also include members such as speakers that are not directly related to movement of the vehicle 100 .

In addition, in the present disclosure, among the vehicles 100, vehicles 100 that include a receiving unit 118, a control unit 102, and a transmitting unit 116 that further have the following functions in addition to the functions described above are defined as type 1 vehicles.
A receiving unit 118 that receives from the server system 1 an instruction to perform calculations related to the behavior of one or more vehicles 100 included in a specific range including the own vehicle.
• The control unit 102 that performs the above calculation using control software when the receiving unit 118 receives the above instruction.
- Transmit a control signal that instructs the behavior calculated by the control unit 102 to the other vehicle 100 included in the specific range by inter-vehicle communication using LTE V2X direct communication, 5G NR V2X indirect communication, or the like. transmitter 116;

From another point of view, the type 1 vehicle means the vehicle 100 for which the server system 1 can perform off-road processing. The type 1 vehicle contributes to the server system 1 reducing the processing load of calculations for the vehicles 100 included in the specific range. Further, the server system 1 can refer to the vehicle information received from the vehicle 100 to identify whether the vehicle 100 is a first class vehicle.

Note that the functions of a single member included in the server system 1 and the vehicle 100 may be realized by a plurality of different members, and the functions of the plurality of members included in the server system 1 and the vehicle 100 may be realized by another single member. It may be realized by a member. Further, the server system 1 may be implemented by, for example, a first server device having a database and a second server device that communicates with the vehicle 100 .

[2. Processing example 1 of server system 1]
Next, an example of the flow of processing executed by the server system 1 will be described. In this example, a configuration will be described in which the server system 1 eliminates network congestion in communication between the server system 1 and the vehicles 100 by extending the vehicle information reception cycle of some or all of the vehicles 100. do. FIG. 3 is an example of a flow chart showing the flow of processing according to this example, which is centered on the server system 1 .

In S<b>101 , the receiving unit 18 of the server system 1 receives vehicle information transmitted from each vehicle 100 . Initially, the receiving unit 18 receives the vehicle information in the first cycle defined as the default, but the cycle of receiving the vehicle information changes as the processing of S104 and the like, which will be described later, is executed. The transmission unit 16 transmits to each vehicle 100 a control signal that instructs the behavior calculated by the first control unit 4, but the transmission cycle may be the same as the vehicle information reception cycle. It doesn't have to be.

In S102, the control unit 2 determines whether or not the number of vehicles 100 for which the receiving unit 18 has received vehicle information per unit time is equal to or greater than a predetermined number. When the control unit 2 determines that the number of vehicles 100 is equal to or greater than the predetermined number (S102: YES), in S103, due to network congestion in communication between the server system 1 and the vehicle 100, the receiving unit 18 It is determined whether or not there is a vehicle 100 for which a delay of a predetermined time or longer has occurred in receiving vehicle information.

When the control unit 2 determines in S102 that the number of vehicles 100 is less than the predetermined number (S102: NO), the processing from S101 is repeated. Here, to supplement the determination of S102, the above-mentioned predetermined number is the number determined from the viewpoint that network congestion may occur due to the large number of vehicles 100 simultaneously connected to the server system 1 .

When the control unit 2 determines in S103 that there is at least one vehicle 100 causing the delay (S103: YES), the process of S104 is executed. Note that the control unit 2 may be configured to make a determination of "YES" when there are a predetermined number or more of the vehicles 100 in which the delay occurs.

In S<b>104 , the receiving unit 18 performs processing to lengthen the cycle of receiving vehicle information for all vehicles 100 associated with the server system 1 . A cycle longer than the above-described first cycle by the process of S104 is an example of a second cycle in the present disclosure. It is desirable that the length of the second cycle is about one minute or less at maximum.

If the controller 2 determines in S103 that the vehicle 100 causing the delay does not exist (S103: NO), in S105 the receiver 18 receives vehicle information from all the vehicles 100 in the first cycle. Determine whether or not it is received. When the control unit 2 determines that the receiving unit 18 has received vehicle information from all the vehicles 100 in the first period (S105: YES), the process from S101 is repeated using the first period. be

That is, as described above, the receiving unit 18 receives the vehicle information in the first cycle when the predetermined condition that network congestion occurs in communication between the server system 1 and the vehicle 100 is not satisfied. Vehicle information is received in a second period if a predetermined condition is satisfied.

In addition, when the receiving unit 18 determines in S105 that there is a vehicle 100 receiving vehicle information in the second cycle (S105: NO), the control unit 2 determines in S106 that the condition for canceling network congestion is Determine whether it is satisfied. Here, the condition for network congestion cancellation is a condition for returning the cycle for receiving vehicle information from all vehicles 100 to the first cycle, and is a condition that is satisfied in any of the following cases, for example. .
- When the number of vehicles 100 for which the receiving unit 18 has received vehicle information per unit time is equal to or less than a certain number.
- A certain period of time or more has passed since the process of S107 was most recently executed.
- When there is no delay in receiving vehicle information by the receiving unit 18 .

When the control unit 2 determines in S106 that the conditions related to the cancellation of network congestion are not satisfied (S106: NO), the process of S107 is executed. In S<b>107 , the receiving unit 18 performs a process of returning the cycle of receiving vehicle information from vehicles 100 located within a part of range and vehicles 100 corresponding to a part of use cases to the first cycle. FIG. 4 is an example of a conceptual diagram of road traffic realized by the server system 1 and the vehicle 100. As shown in FIG. In the example of FIG. 4 , it is desirable that the cycle of receiving vehicle information from vehicles 100 located on a junction in area 39 is shorter than that from vehicles 100 located on a straight road in area 37 . This is because the degree of danger is expected to be higher on the confluence road than on the straight road. In the example of FIG. 4, the receiving unit 18 sets the cycle of receiving vehicle information from the vehicle 100 located in the range 39 to the first cycle, and sets the cycle of receiving the vehicle information from the vehicle 100 located in the range 37 to Then, the state is set to the second period.

Further, when the control unit 2 determines in S106 that the condition regarding network congestion is satisfied (S106: YES), the process of S108 is executed. In S<b>108 , the receiving unit 18 performs processing for returning the cycle of receiving vehicle information from all vehicles 100 to the first cycle. After the processing of S107 or S108 is executed, the processing from S101 is repeated.

According to the configuration of this example, the server system 1 reduces the amount of information acquired per unit time from some or all of the vehicles 100, and contributes to resolving network congestion.

Note that the configuration of the server system 1 is not limited to the configuration that extends or shortens the cycle in which the receiving unit 18 receives vehicle information from each vehicle 100 in steps S104, S107, and S108. For example, the server system 1 may be configured such that the transmission unit 16 transmits to each vehicle 100 a control signal for extending or shortening the vehicle information transmission cycle in the above process. From another aspect, in the vehicle 100, the receiving unit 118 receives from the server system 1 an instruction to change the vehicle information transmission period, and the transmitting unit 116 transmits the vehicle information in the transmission period according to the instruction. It may be configured to transmit to the server system 1 . As a result, the server system 1 reduces the amount of information transmitted from each vehicle 100 to the base station 200 and the amount of information transmitted from the base station 200 to the server system 1, thereby contributing to resolving network congestion. .

In the above process, the server system 1 sends a control signal to each vehicle 100 so that the receiving unit 18 extends or shortens the cycle of receiving vehicle information from each vehicle 100 and the transmitting unit 16 extends or shortens the transmission cycle of vehicle information. It may be configured to transmit.

Further, the control unit 2 is not limited to the configuration of determining in S103 whether or not there is a vehicle 100 for which the reception of vehicle information is delayed due to network congestion. As another aspect, in S103, the control unit 2 is configured to determine whether or not there is a delay in the calculation of the first control unit 4 due to a lack of container resources used for the operation of the control software. good too. That is, in the processing up to S105, the receiving unit 18 receives the vehicle information in the first cycle when the predetermined condition that the resource of the container is insufficient is not satisfied, and receives the vehicle information when the predetermined condition is satisfied. It may be configured to receive in the second period. This reduces the amount of information that the server system 1 acquires from some or all of the vehicles 100 per unit time, and contributes to resolving the shortage of container resources.

[3. Processing example 2 of server system 1]
Next, another example of the flow of processing executed by the server system 1 will be described. For convenience of description, the items that have already been described in the above example will not be repeated. Moreover, it is the same in the subsequent examples. In this example, a configuration will be described in which the server system 1 offloads calculations related to the behavior of each vehicle 100 to the first type vehicle. FIG. 5 is an example of a flowchart showing the flow of processing according to this example, which is mainly performed by the server system 1 . Further, during the processing shown in FIG. It is assumed that vehicle information has been received.

In S201, the third control unit 8 of the server system 1 sets or updates the specific range according to the position of the first class vehicle or the shape of the road. Here, it is desirable that the third control unit 8 sets the specific range corresponding to the position of the first class vehicle to a range centered on the first class vehicle.

The server system 1 treats the vehicles 100 included in the same specific range as a vehicle group. Also, the range corresponding to a single container exemplified by the container 23 or the like in FIG. 2 may include one or more of the specific ranges.

FIG. 6 is an example of a conceptual diagram of road traffic showing a specific range set by the third control unit 8. As shown in FIG. In FIG. 6, vehicles 100a and 100a' represent first-class vehicles, and vehicle 100 represents a non-first-class vehicle. Further, in FIG. 6, a specific range 41 exemplifies a specific range that is set according to the position of the vehicle 100a' and moves together with the vehicle 100a'. The third control unit 8 does not have to set the specific range corresponding to all the first class vehicles, and as illustrated in the specific range 41, a single specific range includes a plurality of first class vehicles. may be Moreover, the specific range 43 exemplifies an immovable specific range according to the shape of the road. The size of each specific range may be different from each other, but it is desirable that the size be such that vehicle-to-vehicle communication is effective between vehicles included in the same specific range.

In S202, based on the vehicle information received by the receiving unit 18, the control unit 2 determines whether or not the number of vehicles 100 included in the target specific range is equal to or greater than a predetermined number. Here, the number of the vehicles 100 includes the first type vehicles. Further, the predetermined number is the number determined from the viewpoint that the resource of the container for calculating the behavior of the vehicles 100 included in the specific range may be insufficient. When the control unit 2 determines that the number of vehicles 100 included in the specific range is equal to or greater than the predetermined number (S202: YES), in S203, the ratio of type 1 vehicles included in the specific range is equal to or greater than the predetermined number. Determine whether or not there is On the other hand, when the control unit 2 determines that the number of vehicles 100 included in the range is less than the predetermined number (S202: NO), the processing from S201 is repeated.

Moreover, when the control part 2 determines in S203 that the ratio of the first type vehicles included in the specific range is equal to or greater than the predetermined value (S203: YES), the process of S204 is executed. In S204, the third control unit 8 causes the type 1 vehicle included in the specific range to perform at least part of the calculation performed by the first control unit 4 targeting the vehicle 100 included in the specific range. process. That is, the third control unit 8 performs the off-road processing when a condition including that the ratio of the first type vehicles to the vehicles 100 included in a certain specific range is equal to or higher than a predetermined value is satisfied. Also, the second control unit 6 may reduce the amount of resources of the server system 1 allocated to the container for performing the calculation. By performing off-road processing, for example, the vehicle 100a' in FIG.

In addition, the transmission unit 116 of the first type vehicle described above transmits a control signal instructing the behavior calculated by the control unit 102 to the vehicle 100 capable of inter-vehicle communication included in the specific range. The arrows between the first class vehicles included in the specific range 43 of FIG. 6 indicate the inter-vehicle communication. In addition, the transmission unit 116 transmits to the server system 1 the calculation result for the vehicle 100 incapable of inter-vehicle communication. In addition, when a type 1 vehicle performs a calculation for its own vehicle, it behaves according to the calculation result.

Graph 45 of FIG. 7 illustrates the amount of resources allocated to each container prior to offload processing. Also, the graph 47 exemplifies the amount of resources allocated to each container after the offload processing that has been executed with the predetermined condition regarding the processing load in the server system 1 being satisfied. Graph 45 shows that 40%, 20%, 20% and 20% of the total resources allocatable by the second control unit 6 are allocated to containers corresponding to ranges A, B, C and D, respectively. is shown.

Graph 47 also shows that containers corresponding to ranges A and D are allocated 80% and 20% of the total resources, respectively. Here, the calculations performed by the first control unit 4 using the containers corresponding to the ranges B and C are offloaded by the third control unit 8 to the first class vehicles included in the specific range. As a result, the second control unit 6 can allocate resources freed up by the offload processing to other containers lacking resources.

In addition, the third control unit 8 determines whether or not to offload the calculations performed by the first control unit 4 using the container. etc. may be determined. For example, the third control unit 8 may preferentially perform off-road processing for a first-class vehicle located in a relatively safe range such as a straight road, or may perform off-road processing preferentially on a vehicle with poor visibility due to rain, fog, or the like. The priority of off-road processing may be lowered for the first class vehicles located within the range.

In addition, when the control unit 2 determines in S203 that the ratio of the type 1 vehicles included in the specific range is less than the predetermined value (S203: NO), in S205, one or a plurality of vehicle information corresponding to the latest or Input to the learning model. In addition, in S205, the control unit 2 acquires information indicating prediction related to the processing load in the server system 1, which is a prediction output from the learning model.

In S206, the second control unit 6 determines the amount of resource to be allocated to the container after a certain period of time based on the prediction output by the learning model. The second control unit 6 determines, for example, to decrease the amount of resources to be allocated to a container predicted to have sufficient resources and to increase the amount of resources to be allocated to a container predicted to be short of resources. In addition, the second control unit 6 reflects the determined amount of resources by increasing or decreasing the amount of resources allocated to each container, and then the process from S201 is repeated.

According to the configuration of this example, the server system 1 can reduce the processing load of calculations for the vehicles 100 included in the specific range. Furthermore, the server system 1 can appropriately allocate resources according to the state of the vehicle 100 and the processing load in calculations related to the behavior of the vehicle 100 .

In S203, the transmission unit 116 of the type 1 vehicle periodically transmits a response request to the other vehicles 100 included in the specific range until the control unit 102 completes the offloaded calculation. may Subsequently, the receiving unit 118 receives, as a response from each vehicle 100, information indicating the number of other vehicles 100 included in the specific range, In some cases, the configuration may be such that a request for performing the calculation in the server system 1 is transmitted to the server system 1 . The configuration described above contributes to centralized calculation in the server system 1 when the processing load of the calculation performed on the vehicle 100 included in the specific range is relatively small.

Further, the server system 1 may have a configuration in which the configurations of the processing examples 1 and 2 described above are combined. That is, the server system 1 extends the cycle of receiving the vehicle information or the cycle of transmitting the vehicle information to the vehicle 100 when the above-described predetermined conditions regarding network congestion or shortage of container resources are satisfied; It may be configured to perform both the processing of offloading the calculation related to the behavior of the vehicle 100 to the first type vehicle.

[Example of realization by software]
The function of the server system 1 (hereinafter referred to as "device") is a program for causing a computer to function as the device, and the computer functions as each control block of the device (especially each part included in the control unit 2). It can be realized by a program for

In this case, the apparatus comprises a computer having at least one control device (eg processor) and at least one storage device (eg memory) as hardware for executing the program. Each function described in each of the above embodiments is realized by executing the above program using the control device and the storage device.

The program may be recorded on one or more computer-readable recording media, not temporary. The recording medium may or may not be included in the device. In the latter case, the program may be supplied to the device via any transmission medium, wired or wireless.

Also, part or all of the functions of the above control blocks can be realized by logic circuits. For example, integrated circuits in which logic circuits functioning as the control blocks described above are formed are also included in the scope of the present invention. In addition, it is also possible to implement the functions of the control blocks described above by, for example, a quantum computer.

Further, each process described in each of the above embodiments may be executed by AI (Artificial Intelligence). In this case, the AI may operate on the control device, or may operate on another device (for example, an edge computer or a cloud server).

The present invention is not limited to the above-described embodiments, but can be modified in various ways within the scope of the claims, and can be obtained by appropriately combining technical means disclosed in different embodiments. is also included in the technical scope of the present invention.

1 server system 2 control unit 4 first control unit 6 second control unit 8 third control unit 10 learning unit 12 storage unit 14 communication unit 16 transmission unit 18 reception units 100, 100a, 100a′ vehicle 102 control unit 112 storage unit 114 Communication unit 116 Transmission unit 118 Reception unit

Claims (9)

a server system,
a receiving unit that receives vehicle information indicating the state of each vehicle from one or more vehicles;
a first control unit that uses control software to calculate the behavior of each vehicle;
A container for operating the control software is defined by a unit according to at least one of a use case of each vehicle corresponding to the vehicle information and a range in which each vehicle is located, and the control software is stored for each container. a second control unit that allocates resources used for operations and increases or decreases the amount of resources allocated to at least one of the containers when a predetermined condition regarding the processing load on the server system is satisfied;
A server system, comprising: a transmission unit that transmits a control signal instructing the behavior calculated by the first control unit to each vehicle. The second control unit is
2. The server system according to claim 1, wherein a container defined by a unit corresponding to a range in which each vehicle is located is allocated a resource of an amount corresponding to the shape of a road included in said range. The second control unit is
Allocate resources to containers specified by units according to the use case of each vehicle, depending on whether the use case involves vehicle acceleration, traveling at a predetermined speed or higher, or turning. A server system according to claim 1 or 2. Some or all of the one or more vehicles are
a control unit that uses control software to calculate the behavior of each vehicle;
A first-class vehicle comprising a communication unit that performs inter-vehicle communication with another vehicle,
The server system is
When a specific range is set according to the position of the type 1 vehicle or the shape of the road, and the ratio of the type 1 vehicle to the vehicles included in the specific range is a predetermined or more condition is satisfied , from claim 1, further comprising a third control unit that causes a type 1 vehicle included in the specific range to execute at least part of the calculation performed by the first control unit for vehicles included in the specific range. 4. A server system according to any one of Clauses 3 to 3. The receiving unit
receiving the vehicle information in a first period if the predetermined condition is not satisfied;
5. The server system according to any one of claims 1 to 4, wherein said vehicle information is received in a second period when said predetermined condition is satisfied. A learning model that receives one or more of the vehicle information as input and outputs a prediction about the processing load on the server system, and a set of one or more of the vehicle information and information indicating the processing load on the server system as teacher data. 6. The server system according to any one of claims 1 to 5, further comprising a learning unit for learning by using as . A vehicle associated with the server system,
a receiving unit that receives from the server system an instruction to perform calculations related to the behavior of one or more vehicles included in a specific range including the own vehicle;
a control unit that performs the calculation using control software when the receiving unit receives the instruction;
A transmission unit for transmitting vehicle information indicating a state of the own vehicle to the server system, the transmission unit transmitting a control signal instructing the behavior calculated by the control unit to other vehicles included in the specific range by inter-vehicle communication. and a vehicle. The receiving unit
receiving an instruction from the server system to change the transmission cycle of the vehicle information;
The transmission unit
8. The vehicle according to claim 7, wherein said vehicle information is transmitted to said server system at a transmission cycle according to said instruction. The receiving unit
receiving information indicating the number of other vehicles included in the specific range;
The transmission unit
9. The vehicle according to claim 7 or 8, wherein, when the number of said other vehicles is equal to or less than a predetermined number, a request for performing said calculation in said server system is transmitted to said server system.

Images