CN115956045A

CN115956045A - Vehicle automatic driving system, method, device, computer equipment and storage medium

Info

Publication number: CN115956045A
Application number: CN202180050153.5A
Authority: CN
Inventors: 庄奇
Original assignee: DeepRoute AI Ltd
Current assignee: DeepRoute AI Ltd
Priority date: 2021-06-10
Filing date: 2021-06-10
Publication date: 2023-04-11
Also published as: WO2022257056A1

Abstract

A vehicle automatic driving system, method, apparatus, computer device and storage medium. The system comprises: the system comprises a cloud reasoning server and an automatic driving vehicle; the automatic driving vehicle is connected with the cloud reasoning server through wireless communication; the automatic driving vehicle is used for generating and sending an inference request to the cloud inference server, receiving an inference result sent by the cloud inference server and executing a corresponding driving instruction according to the inference result; the cloud reasoning server is used for receiving a reasoning request sent by the automatic driving vehicle, generating a corresponding reasoning result according to the reasoning request and sending the reasoning result to the automatic driving vehicle; and the inference result is a command which is generated by the cloud inference server through the deep learning model according to the inference request and is used for controlling the automatic driving vehicle to run. The system can improve the protection of the core algorithm of the operation platform and avoid the risk of the leakage of the core algorithm.

Description

Vehicle automatic driving system, method, device, computer equipment and storage medium

Technical Field

The present application relates to the field of automatic driving technologies, and in particular, to a system, a method, an apparatus, a computer device, and a storage medium for automatic driving of a vehicle.

Background

In autonomous driving, artificial intelligence plays an important role. Deep learning is one of the most important solutions of artificial intelligence in the field of automated driving, especially in perception. The deep learning inference engine is designed to accelerate the deep learning model inference speed, and the deep learning model inference is completed by a GPU or an AI chip. At present, the realization of the perception module of automatic driving mainly adopts a deep learning method, the deep learning needs to use sensor information such as a vehicle-mounted laser radar and a camera as input, the output, namely a perception result, is obtained through the calculation of a neural network, and the calculation process of the neural network is also called an inference process.

In the prior art, computing platforms of autonomous automobile companies are all deployed on autonomous automobiles. The power of the computing platform is related to the level of automatic driving, and for the automatic driving of low-level L1-L3, a small computing chip or a camera integrated with the small chip can be realized. However, for the automatic driving vehicle of the L4 level, because the required deep learning model is more complex, more types and larger computation amount, the real-time computation cannot be performed only by one small chip. In this case, the solution for class L4 auto-pilot companies is to deploy high performance computing platforms directly in the vehicle, e.g., in the trunk, or on the roof. However, the prior art has resulted in a risk of the core algorithms of the computing platform being compromised because of the large number of core algorithms placed on the computing platform in the autonomous vehicle.

Disclosure of Invention

In view of the above, there is a need to provide a vehicle automatic driving system, method, apparatus, computer device and storage medium capable of avoiding leakage of an automatic driving core algorithm.

A vehicle autopilot system, the system comprising: the system comprises a cloud reasoning server and an automatic driving vehicle; the automatic driving vehicle is connected with the cloud reasoning server through wireless communication;

the automatic driving vehicle is used for generating and sending an inference request to the cloud inference server, receiving an inference result sent by the cloud inference server, and executing a corresponding driving instruction according to the inference result;

the cloud reasoning server is used for receiving a reasoning request sent by the automatic driving vehicle, generating a corresponding reasoning result according to the reasoning request and sending the reasoning result to the automatic driving vehicle;

the inference result is an instruction generated by the cloud inference server according to the inference request; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required for making inference according to the request type.

A method of automatic driving of a vehicle, the method comprising: receiving an inference request sent by an automatic driving vehicle; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required by inference according to the request type;

generating a corresponding reasoning result according to the reasoning request, and sending the reasoning result to the automatic driving vehicle; the inference result is a command which is generated by the cloud inference server through deep learning model processing according to the inference request and used for controlling the automatic driving vehicle to run.

In one embodiment, the method further comprises the following steps: analyzing the inference request, and selecting a corresponding deep learning model according to the inference request;

reasoning processing is carried out on the data packet according to the deep learning model, and a reasoning result is obtained;

and sending the inference result to the automatic driving vehicle.

In one embodiment, the method further comprises the following steps: analyzing the inference request, and judging whether a required deep learning model is selected in the inference request;

and if the needed deep learning model is selected in the inference request, selecting the selected deep learning model in the inference request as the deep learning model used in the inference process.

In one embodiment, the method further comprises the following steps: if the needed deep learning model is not selected in the inference request, acquiring an inference purpose according to the inference request;

and selecting a deep learning model with the highest prediction accuracy rate capable of realizing the reasoning purpose according to the content of the reasoning purpose.

In one embodiment, the method further comprises the following steps: receiving a registration inference engine service request sent by an automatic driving vehicle; the service request of the registration inference engine is offer information which is sent by the automatic driving vehicle and used for applying the cloud inference server to carry out inference processing on the inference request sent by the automatic driving vehicle;

and judging whether the automatic driving vehicle meets a preset registration condition, if so, agreeing to a registration inference engine service request of the automatic driving vehicle, and sending a registration agreement return message to the automatic driving vehicle.

A method of automatic driving of a vehicle, the method comprising: generating and sending an inference request to a cloud inference server; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required by inference according to the request type;

receiving an inference result sent by the cloud inference server, and executing a corresponding driving instruction according to the inference result; the inference result is a command which is generated by the cloud inference server through a deep learning model according to the inference request and is used for controlling the automatic driving vehicle to run.

In one embodiment, the method further comprises the following steps: when receiving an instruction of the inference request and/or the running state of the automatic driving vehicle accords with the inference request generation condition, generating a corresponding inference request;

and sending the inference request to the cloud inference server.

In one embodiment, the method further comprises the following steps: receiving an inference result sent by the cloud inference server;

analyzing the inference result to generate a driving instruction;

and controlling the automatic driving vehicle to run according to the driving instruction.

In one embodiment, the method further comprises the following steps: sending a registration inference engine service request to the cloud inference server; the service request of the registration inference engine is offer information which is sent by the automatic driving vehicle and used for applying the cloud inference server to carry out inference processing on the inference request sent by the automatic driving vehicle;

receiving return information sent by the cloud reasoning server; the return information includes return information of agreement to registration and return information of refusal to registration.

In one embodiment, the method further comprises the following steps: and acquiring a data packet through a vehicle-mounted road surface information acquisition device, wherein the data packet comprises road condition image information and road condition point cloud information.

An automatic driving apparatus for a vehicle, the apparatus comprising:

the reasoning request receiving module is used for receiving a reasoning request sent by the automatic driving vehicle; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required by inference according to the request type;

the reasoning result generating module is used for generating a corresponding reasoning result according to the reasoning request and sending the reasoning result to the automatic driving vehicle; the inference result is a command which is generated by the cloud inference server through a deep learning model according to the inference request and is used for controlling the automatic driving vehicle to run.

An automatic driving apparatus for a vehicle, the apparatus comprising:

the inference request generating module is used for generating and sending an inference request to the cloud inference server; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required by inference according to the request type;

the reasoning result receiving module is used for receiving the reasoning result sent by the cloud reasoning server and executing a corresponding driving instruction according to the reasoning result; the inference result is a command which is generated by the cloud inference server through a deep learning model according to the inference request and is used for controlling the automatic driving vehicle to run.

In one embodiment, the vehicle automatic driving apparatus further includes: the system comprises a vehicle-mounted road information acquisition device, a vehicle-mounted driving control device and a vehicle-mounted intelligent processing terminal;

the vehicle-mounted road information acquisition device is used for acquiring a data packet, and the data packet comprises road condition image information and road condition point cloud information;

the vehicle-mounted intelligent processing terminal is arranged in the inference request generation module and used for generating an inference request, sending the inference request to the cloud-end inference server and receiving an inference result generated by the cloud-end inference server;

the vehicle-mounted driving control device is connected with the reasoning result receiving module and used for controlling the automatic driving vehicle to drive according to the reasoning result generated by the cloud reasoning server.

In one embodiment, the vehicle-mounted road information acquisition device comprises a vehicle-mounted road image acquisition device and a vehicle-mounted radar system;

the vehicle-mounted road surface image acquisition device is used for acquiring road condition image information and sending the road condition image information to the vehicle-mounted intelligent processing terminal;

the vehicle-mounted radar system is used for acquiring road condition point cloud information and sending the road condition point cloud information to the vehicle-mounted intelligent processing terminal.

In one embodiment, the vehicle-mounted intelligent processing terminal includes:

the processor is used for receiving the road condition image information and the road condition point cloud information and generating an inference request;

and the communication device is used for realizing wireless communication between the vehicle-mounted intelligent processing and the cloud reasoning server.

In one embodiment, the onboard radar system comprises at least one of a laser radar system, an ultrasonic radar system, a millimeter wave radar system, and a microwave radar system.

In one embodiment, the communication device comprises at least one of a WIFI device, a bluetooth device, a GPRS device, a 3G, 4G, and 5G module connected to the processor.

A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

receiving an inference request sent by an automatic driving vehicle; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required by inference according to the request type;

generating a corresponding reasoning result according to the reasoning request, and sending the reasoning result to the automatic driving vehicle; the inference result is a command which is generated by the cloud inference server through deep learning model processing according to the inference request and is used for controlling the automatic driving vehicle to run.

generating and sending an inference request to a cloud inference server; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required by inference according to the request type;

A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:

The vehicle automatic driving system, the vehicle automatic driving method, the vehicle automatic driving device, the computer equipment and the storage medium generate and send the inference request to the cloud inference server wirelessly connected with the automatic driving vehicle through the automatic driving vehicle, receive the inference request sent by the automatic driving vehicle through the cloud inference server, generate a corresponding inference result according to the inference request, and send the inference result to the automatic driving vehicle; and finally, the automatic driving vehicle receives the inference result sent by the cloud inference server and executes a corresponding driving instruction according to the inference result. The core algorithm is arranged on the cloud reasoning server in wireless connection with the automatic driving vehicle, so that the core algorithm is prevented from being leaked.

Drawings

FIG. 1 is a block diagram of an exemplary vehicle autopilot system;

FIG. 2 is a diagram of information interaction between a cloud-side inference server and an autonomous vehicle in a vehicle autonomous system in one embodiment;

FIG. 3 is a flowchart illustrating information processing performed by an intelligent processing terminal of the vehicle-mounted automatic driving system according to an embodiment;

FIG. 4 is a diagram of inference request architecture in an automated vehicle driving system, according to one embodiment;

FIG. 5 is a flow diagram illustrating a method for automatic vehicle driving according to one embodiment;

FIG. 6 is a flow chart illustrating a method for automatic vehicle driving according to another embodiment;

FIG. 7 is a block diagram showing the construction of an automatic driving apparatus for a vehicle according to an embodiment;

FIG. 8 is a block diagram showing the construction of an automatic driving apparatus for a vehicle according to another embodiment;

FIG. 9 is a block diagram of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.

In one embodiment, as shown in fig. 1, there is provided a vehicle automatic driving system including: the system comprises a cloud reasoning server and an automatic driving vehicle; the automatic driving vehicle is connected with the cloud reasoning server through wireless communication;

in particular, the type of autonomous vehicle is not exclusive and may be in particular a car, a van, a truck or the like. The cloud reasoning server is a server device for executing the neural network calculation to obtain an output, namely a perception result, and the neural network calculation process is also called a reasoning process. The automatic vehicle driving system comprises a cloud reasoning server and an automatic driving vehicle; each autonomous vehicle is in wireless communication connection with the cloud inference server, and the method of wireless communication connection is not particularly limited, and for example, the autonomous vehicles may be in 5G communication connection.

The automatic driving vehicle is used for generating and sending an inference request to the cloud inference server, receiving an inference result sent by the cloud inference server and executing a corresponding driving instruction according to the inference result;

specifically, the inference request is an instruction sent by the autonomous vehicle to request the cloud inference server to execute the inference process, and includes a request type and/or a data packet. Wherein, the request type is not less than one, for example: the automatic driving vehicle applies for registering new reasoning engine service, selects a deep learning model which the automatic driving vehicle wants to reason, gives input data which needs to be inferred by the automatic driving vehicle, requests an output result after the cloud reasoning server is inferred by the automatic driving vehicle, and the automatic driving vehicle needs to obtain the last reasoning time. And the inference result sent by the cloud inference server is an indispensable instruction for the automatic driving of the automatic driving vehicle, and the control system of the automatic driving vehicle executes corresponding action according to the received inference result, so that the safe driving of the automatic driving vehicle is realized.

specifically, the cloud reasoning server is a server which is remotely connected with the automatic driving vehicle and is used for executing a reasoning process, and the cloud reasoning server can be one server or a server group consisting of a plurality of servers. Fig. 2 is a structural diagram of a cloud-side inference server in a vehicle automatic driving system, and as shown in fig. 2, the cloud-side inference server is connected with each of the automatically driven vehicles through wireless communication, and can receive inference requests including request types and/or data packets sent by each of the automatically driven vehicles in real time, perform corresponding processing according to the content of the inference requests and a preset program, generate inference results, and send the inference results to the corresponding automatically driven vehicles in real time, so that each of the automatically driven vehicles can execute corresponding actions according to the inference results in real time. For example, the cloud reasoning server processes data sent by the automatic driving vehicle and used for prejudging the driving track of the automatic driving vehicle according to the deep learning model type selected by the automatic driving vehicle, acquires track route information of the corresponding driving track of the automatic driving vehicle, and sends the track route information to the corresponding automatic driving vehicle so that the automatic driving vehicle can safely and stably drive.

Specifically, the reasoning result is that the cloud reasoning server generates instructions and information required by the automatic driving vehicle according to the reasoning request, the reasoning request is different, and the corresponding reasoning result is also different. For example, if the inference request is that the autonomous vehicle applies for registering a new inference engine service, the inference result is that the corresponding autonomous vehicle is successfully or unsuccessfully registered; if the inference request is that the automatic driving vehicle selects the deep learning model to be inferred, the inference result is the deep learning model selected by the automatic driving vehicle; if the inference request is an output result after the automatic driving vehicle requests the cloud inference server to infer, the corresponding inference result is a returned inference result; if the inference request is that the autonomous vehicle needs to obtain the last inference, the inference result is the time consumed by the last inference process.

The vehicle automatic driving system generates and sends an inference request to a cloud inference server in wireless connection with the automatic driving vehicle through the automatic driving vehicle, receives the inference request sent by the automatic driving vehicle through the cloud inference server, generates a corresponding inference result according to the inference request, and sends the inference result to the automatic driving vehicle; and finally, the automatic driving vehicle receives the reasoning result sent by the cloud reasoning server and executes a corresponding driving instruction according to the reasoning result. The core algorithm is arranged on the cloud reasoning server in wireless connection with the automatic driving vehicle, so that the core algorithm is prevented from being leaked.

In one embodiment, as shown in fig. 5, an automatic driving method for a vehicle is provided, which is described by taking the method as an example of being applied to a cloud reasoning server, and includes the following steps:

step 502, receiving an inference request sent by an autonomous vehicle; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required for inference according to the request type.

Specifically, the cloud reasoning server is a cloud reasoning server which is remotely connected with the automatic driving vehicle and is used for executing a reasoning process, and the cloud reasoning server can be one server or a server group consisting of a plurality of servers. The cloud reasoning server is connected with each automatic driving vehicle through wireless communication, and can receive reasoning requests including request types and/or data packets sent by each automatic driving vehicle in real time through a wireless communication mode.

The inference request is an instruction sent by the automatic driving vehicle and requesting the cloud inference server to execute an inference process, and comprises a request type and/or a data packet. Wherein, the request type is not less than one, for example: the automatic driving vehicle applies for registering new reasoning engine service, selects a deep learning model which the automatic driving vehicle wants to reason, gives input data which needs to be inferred by the automatic driving vehicle, requests an output result after the cloud reasoning server is inferred by the automatic driving vehicle, and the automatic driving vehicle needs to obtain the last reasoning time. The data packet is inference data required for inference according to the request type, and the type is not specifically limited, and includes, for example, road condition image information and road condition point cloud information.

Step 504, generating a corresponding reasoning result according to the reasoning request, and sending the reasoning result to the automatic driving vehicle; the inference result is a command which is generated by the cloud inference server through deep learning model processing according to the inference request and is used for controlling the automatic driving vehicle to run.

Specifically, after receiving an inference request sent by the automatic driving vehicle, the cloud-end inference server performs corresponding processing according to a preset program according to the content of the inference request to generate an inference result, and sends the inference result to the corresponding automatic driving vehicle in real time, so that the respective automatic driving vehicle can execute corresponding actions according to the inference result in real time. For example, the cloud reasoning server processes data sent by the automatic driving vehicle and used for prejudging the driving track of the automatic driving vehicle according to the deep learning model type selected by the automatic driving vehicle, acquires track route information of the corresponding driving track of the automatic driving vehicle, and sends the track route information to the corresponding automatic driving vehicle so that the automatic driving vehicle can safely and stably drive.

And the inference result sent by the cloud inference server is an indispensable instruction for the automatic driving of the automatic driving vehicle, and the control system of the automatic driving vehicle executes corresponding action according to the received inference result, so that the safe driving of the automatic driving vehicle is realized.

According to the vehicle automatic driving method, the cloud reasoning server receives the reasoning request sent by the automatic driving vehicle, generates the corresponding reasoning result according to the reasoning request, and sends the reasoning result to the automatic driving vehicle so that the automatic driving vehicle can execute the corresponding driving action according to the reasoning result. The core algorithm of the inference processing is arranged on the cloud inference server in wireless connection with the automatic driving vehicle, so that the core algorithm is prevented from being leaked.

In one embodiment, said generating a corresponding inference result from said inference request and sending said inference result to said autonomous vehicle comprises:

analyzing the inference request, and selecting a corresponding deep learning model according to the inference request;

performing reasoning processing on the data packet according to the deep learning model to obtain a reasoning result;

and sending the inference result to the automatic driving vehicle.

Specifically, after the cloud reasoning server receives a reasoning request sent by the automatic driving vehicle, the reasoning request needs to be analyzed, and a corresponding deep learning model is selected according to the specific content of the reasoning request. After the deep learning model is selected, the data packet is processed according to the deep learning model, and the data packet is generally input into the corresponding deep learning model to obtain a generated inference result. And finally, sending the inference result to the automatic driving vehicle so that the automatic driving vehicle executes a corresponding driving action instruction according to the content of the inference result.

In this embodiment, the cloud inference server parses the inference request, selects the corresponding deep learning model according to the inference request, performs inference processing on the data packet according to the deep learning model, obtains an inference result, and finally sends the inference result to the autonomous driving vehicle. The cloud reasoning server is used for processing the reasoning request, so that the risk that the core algorithm is leaked due to the fact that the core algorithm is arranged on the vehicle-mounted operation platform is avoided.

In one embodiment, the parsing the inference request and the selecting the corresponding deep learning model according to the inference request includes:

analyzing the inference request, and judging whether a required deep learning model is selected in the inference request;

and if the required deep learning model is selected in the inference request, selecting the selected deep learning model in the inference request as the deep learning model used in the inference processing.

Specifically, when the cloud reasoning platform selects the deep learning model, firstly analyzing a reasoning request, and judging whether the reasoning request contains related contents of the deep learning model selected by the automatic driving platform; and if the required deep learning model is selected in the inference request or the deep learning model selected by the automatic driving vehicle can be determined according to the content of the inference request, selecting the selected or determinable deep learning model in the inference request as the deep learning model used in the inference process.

In the embodiment, the inference request is analyzed, and whether the inference request contains the relevant content of the deep learning model selected by the automatic driving platform is judged, so that the inference request used by the inference processing can be quickly selected, and the efficiency of the inference processing on the inference request is improved.

In one embodiment, the parsing the inference request and selecting the corresponding deep learning model according to the inference request further includes:

if the needed deep learning model is not selected in the inference request, acquiring an inference purpose according to the inference request;

Specifically, if the required deep learning model is not selected in the inference request, or the deep learning model selected by the autonomous vehicle cannot be determined according to the content of the inference request, an inference purpose is obtained according to the inference request, wherein the inference purpose is a purpose to be achieved by the autonomous vehicle sending the inference request. After the inference purpose is obtained, a deep learning model with the highest prediction accuracy rate and capable of achieving the inference purpose is selected from the cloud inference server.

In this embodiment, the deep learning model with the highest prediction accuracy rate that can achieve the purpose of reasoning is selected as the deep learning model for the reasoning process when the deep learning model required for reasoning is not selected in the reasoning request or the deep learning model selected by the autonomous vehicle cannot be determined according to the content of the reasoning request, so that the accuracy rate of the reasoning process for the reasoning request is improved.

In one embodiment, the receiving of the inference request sent by the autonomous vehicle further comprises:

receiving a registration inference engine service request sent by an automatic driving vehicle; the service request of the registration inference engine is offer information which is sent by the automatic driving vehicle and used for applying the cloud inference server to carry out inference processing on the inference request sent by the automatic driving vehicle;

Specifically, before the cloud reasoning server receives and processes a reasoning request sent by the automatic driving vehicle, the cloud reasoning server also receives a registration reasoning engine service request sent by the automatic driving vehicle; the service request of the registration inference engine is offer information which is sent by the automatic driving vehicle and used for applying the inference request sent by the cloud inference server to carry out inference processing. And judging whether the automatic driving vehicle meets the preset registration condition, agreeing to a registration inference engine service request of the automatic driving vehicle when the automatic driving vehicle meets the preset registration condition, and sending a return message agreeing to registration to the automatic driving vehicle. Otherwise, sending a return message of refusing to register to the automatic driving vehicle.

In the embodiment, before the cloud-side reasoning server receives and processes the reasoning request sent by the automatic driving vehicle, the cloud-side reasoning server also receives a registration reasoning engine service request sent by the automatic driving vehicle, judges whether the automatic driving vehicle meets a preset registration condition, agrees to the registration reasoning engine service request of the automatic driving vehicle when the automatic driving vehicle meets the preset registration condition, and sends a registration agreement return message to the automatic driving vehicle. The safety of the cloud reasoning server is improved.

In one embodiment, as shown in fig. 6, there is provided a method for automatic driving of a vehicle, which is described by taking the method as an example for an automatic driving vehicle, and comprises the following steps:

step 602, generating and sending an inference request to a cloud inference server; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required for making inference according to the request type.

Specifically, the automatic driving vehicle generates an inference request when needed, and the inference request is sent to the cloud inference server through the wireless communication device arranged on the automatic driving vehicle. The inference request is an instruction sent by the automatic driving vehicle and requesting the cloud inference server to execute an inference process, and comprises a request type and/or a data packet. Wherein, the request type is not less than one, for example: the method comprises the steps that the automatic driving vehicle applies for registering new inference engine service, the automatic driving vehicle selects a deep learning model needing to be inferred, the automatic driving vehicle gives input data needing to be inferred, the automatic driving vehicle requests an output result after the cloud inference server infers, the automatic driving vehicle needs to obtain last inference time, and the like. The data packet is inference data required for inference according to the request type, and the type is not specifically limited, and includes, for example, road condition image information and road condition point cloud information.

Step 604, receiving the inference result sent by the cloud inference server, and executing a corresponding driving instruction according to the inference result; the inference result is a command which is generated by the cloud inference server through a deep learning model according to the inference request and is used for controlling the automatic driving vehicle to run.

Specifically, after the cloud reasoning server processes the reasoning request, a corresponding reasoning result is generated and sent to the automatic driving vehicle. The inference result is a command for the automatic driving vehicle to run, which is generated by the cloud inference server through the deep learning model according to the inference request, and the inference request is different and the corresponding inference result is also different. And after receiving the inference result sent by the cloud inference server, the automatic driving vehicle executes a corresponding driving instruction according to the inference result. For example, the cloud reasoning server processes data sent by the automatic driving vehicle and used for prejudging the driving track of the automatic driving vehicle according to the deep learning model type selected by the automatic driving vehicle, acquires track route information of the corresponding driving track of the automatic driving vehicle, and sends the track route information to the corresponding automatic driving vehicle so that the automatic driving vehicle can safely and stably drive.

In the vehicle automatic driving method, the automatic driving vehicle sends the inference request to the cloud inference server, the cloud inference server receives the inference request sent by the automatic driving vehicle, generates the corresponding inference result according to the inference request, and sends the inference result to the automatic driving vehicle so that the automatic driving vehicle can execute the corresponding driving action according to the inference result. The core algorithm of the inference processing is arranged on the cloud inference server in wireless connection with the automatic driving vehicle, so that the core algorithm is prevented from being leaked.

In one embodiment, the generating and sending the inference request to the cloud inference server includes:

when receiving an instruction of the inference request and/or the running state of the automatic driving vehicle accords with the inference request generation condition, generating a corresponding inference request;

and sending the inference request to the cloud inference server.

Specifically, when the automatically-driven vehicle generates the inference request, the method comprises the steps of receiving an artificially generated inference request instruction and generating a corresponding inference request according to the artificially generated inference request instruction. For example, a vehicle-mounted intelligent processing terminal is installed in the automatic driving vehicle, and when the vehicle-mounted intelligent processing terminal of the automatic driving vehicle receives an instruction for manually generating the inference request and/or the running state of the automatic driving vehicle meets the inference request generation condition, a corresponding inference request is generated.

And/or when the running state of the automatic driving vehicle meets the inference request generating condition, the automatic driving vehicle generates a corresponding inference request, for example, when the running state of the automatic driving vehicle meets the inference request generating condition, for example, when the running state of the vehicle is abnormal, the automatic driving vehicle sends the corresponding inference request to the cloud-end inference server, so that the cloud-end inference server processes the inference request to generate an inference result.

In the embodiment, when the vehicle-mounted intelligent processing terminal of the automatic driving vehicle receives the instruction of manually generating the inference request and/or the running state of the automatic driving vehicle conforms to the inference request generation condition, the corresponding inference request is generated, and the inference request is sent to the cloud-end inference server for processing, so that the process that the cloud-end inference server processes the inference request is realized, and the risk that the core algorithm of the operation platform is leaked is avoided.

In one embodiment, the receiving the inference result sent by the cloud inference server and executing the corresponding driving instruction according to the inference result includes:

receiving an inference result sent by the cloud inference server;

analyzing the inference result to generate a driving instruction;

Specifically, after receiving the inference result sent by the cloud inference server, the automatic driving vehicle analyzes the inference result through the vehicle-mounted intelligent processing terminal to generate a driving instruction corresponding to the inference result; and the driving instruction is sent to the vehicle-mounted driving control device, and finally the vehicle-mounted driving control device controls the automatic driving vehicle to drive according to the driving instruction. The vehicle-mounted running control device is used for controlling the automatic driving vehicle to run according to the inference result generated by the cloud-end inference server, is connected with the vehicle-mounted intelligent processing terminal, can receive the inference result sent by the cloud-end vehicle server through the vehicle-mounted intelligent processing terminal, controls the running state of the automatic driving vehicle according to the inference result, and executes corresponding control action.

In the embodiment, the automatic driving vehicle receives the inference result sent by the cloud inference server, analyzes and processes the inference result, generates the driving instruction, and finally controls the automatic driving vehicle to run according to the driving instruction, so that the inference processing of the inference request by the cloud inference server is realized, and the processing speed of the inference request is improved.

In one embodiment, the generating and sending the inference request to the cloud inference server further includes:

sending a registration inference engine service request to the cloud inference server; the service request of the registration inference engine is offer information which is sent by the automatic driving vehicle and used for applying the inference server to carry out inference processing on the inference request sent by the cloud inference server;

Specifically, in order to enable the automatic driving vehicle to perform inference processing on an inference request of the automatic driving vehicle through the cloud-end inference server, the automatic driving vehicle needs to send a service request of a registration inference engine to the cloud-end inference server before the cloud-end inference server receives and processes the inference request sent by the automatic driving vehicle; the service request of the registration inference engine is offer information which is sent by the automatic driving vehicle and used for applying the inference request sent by the cloud inference server to carry out inference processing. The cloud reasoning server needs to judge whether the automatic driving vehicle meets preset registration conditions, agrees to a registration reasoning engine service request of the automatic driving vehicle when the automatic driving vehicle meets the preset registration conditions, and sends a return message of agreeing to registration to the automatic driving vehicle. Otherwise, sending a return message of refusing to register to the automatic driving vehicle.

In this embodiment, before the autonomous driving vehicle sends the inference request to the cloud-based inference server and requests the cloud-based inference server to process the inference request, the autonomous driving vehicle is further required to send a registration inference engine service request to the cloud-based inference server and judge whether the autonomous driving vehicle meets the preset registration condition, and when the autonomous driving vehicle meets the preset registration condition, the cloud-based inference server agrees to the registration inference engine service request of the autonomous driving vehicle and sends the return information agreeing to registration to the autonomous driving vehicle, so that the safety of the cloud-based inference server is improved.

In one embodiment, the sending the inference request to the cloud inference server further includes:

and acquiring a data packet through a vehicle-mounted road information acquisition device, wherein the data packet comprises road condition image information and road condition point cloud information.

Specifically, the automatic driving vehicle is provided with a vehicle-mounted road information acquisition device for acquiring data packets including road condition image information and road condition point cloud information. The vehicle-mounted road surface information acquisition device specifically includes: vehicle-mounted road surface image acquisition device and vehicle-mounted radar system. The vehicle-mounted road surface image acquisition device is used for acquiring road condition image information and sending the road condition image information to the vehicle-mounted intelligent processing terminal; the road condition image information is information of road conditions around the autonomous vehicle, and mainly includes information of surrounding road surfaces, information of surrounding vehicles, information of surrounding obstacles, information of pedestrians, and the like. The vehicle-mounted radar system is used for acquiring road condition point cloud information and sending the road condition point cloud information to the vehicle-mounted intelligent processing terminal; the vehicle-mounted radar system can not only detect the road condition information in the surrounding range, but also detect the road condition information in a far area through the radar, and is favorable for the safe driving of the automatic driving vehicle.

In this embodiment, the data packet is acquired by the vehicle-mounted road information acquisition device, and the data packet includes road condition image information and road condition point cloud information, so that the cloud reasoning server can perform reasoning according to the road condition image information and the road condition point cloud information.

It should be understood that although the various steps in the flowcharts of fig. 5-6 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 5-6 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.

In one embodiment, as shown in fig. 7, there is provided a vehicle automatic driving apparatus including: inference request receiving module 701 and inference result generating module 702, wherein:

an inference request receiving module 701, configured to receive an inference request sent by an autonomous vehicle; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required by inference according to the request type;

an inference result generation module 702, configured to generate a corresponding inference result according to the inference request, and send the inference result to the autonomous vehicle; the inference result is a command which is generated by the cloud inference server through a deep learning model according to the inference request and is used for controlling the automatic driving vehicle to run.

In one embodiment, the inference result generating module 702 is further configured to: analyzing the inference request, and selecting a corresponding deep learning model according to the inference request; performing reasoning processing on the data packet according to the deep learning model to obtain a reasoning result; and sending the inference result to the automatic driving vehicle.

In one embodiment, the inference result generation module 702 is further configured to: analyzing the inference request, and judging whether a required deep learning model is selected in the inference request; and if the required deep learning model is selected in the inference request, selecting the selected deep learning model in the inference request as the deep learning model used in the inference processing.

In one embodiment, the inference result generating module 702 is further configured to: if the needed deep learning model is not selected in the inference request, acquiring an inference purpose according to the inference request; and selecting a deep learning model with the highest prediction accuracy rate capable of realizing the reasoning purpose according to the content of the reasoning purpose.

In one embodiment, the inference request receiving module 701 is further configured to: receiving a registration inference engine service request sent by an automatic driving vehicle; the service request of the registration inference engine is offer information which is sent by the automatic driving vehicle and used for applying the cloud inference server to carry out inference processing on the inference request sent by the automatic driving vehicle; and judging whether the automatic driving vehicle meets a preset registration condition, if so, agreeing to a registration inference engine service request of the automatic driving vehicle, and sending a registration agreement return message to the automatic driving vehicle.

The vehicle automatic driving system device generates and sends an inference request to a cloud inference server in wireless connection with the automatic driving vehicle through the automatic driving vehicle, receives the inference request sent by the automatic driving vehicle through the cloud inference server, generates a corresponding inference result according to the inference request, and sends the inference result to the automatic driving vehicle; and finally, the automatic driving vehicle receives the inference result sent by the cloud inference server and executes a corresponding driving instruction according to the inference result. The core algorithm is arranged on the cloud reasoning server in wireless connection with the automatic driving vehicle, so that the core algorithm is prevented from being leaked.

In one embodiment, as shown in fig. 8, there is provided a vehicle automatic driving apparatus including: inference request generation module 801 and inference result receiving module 802, wherein:

an inference request generating module 801, configured to generate and send an inference request to a cloud inference server; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required by inference according to the request type;

the inference result receiving module 802 is configured to receive an inference result sent by the cloud inference server, and execute a corresponding driving instruction according to the inference result; the inference result is a command which is generated by the cloud inference server through a deep learning model according to the inference request and is used for controlling the automatic driving vehicle to run.

In one embodiment, the inference request generating module 801 is further configured to: when receiving an instruction of the inference request and/or the running state of the automatic driving vehicle accords with the inference request generation condition, generating a corresponding inference request; and sending the inference request to the cloud inference server.

In one embodiment, the inference result receiving module 802 is further configured to: receiving an inference result sent by the cloud inference server; analyzing the inference result to generate a driving instruction; and controlling the automatic driving vehicle to run according to the driving instruction.

In one embodiment, the inference request generating module 801 is further configured to: sending a service request of a registration inference engine to the cloud inference server; the service request of the registration inference engine is offer information which is sent by the automatic driving vehicle and used for applying the cloud inference server to carry out inference processing on the inference request sent by the automatic driving vehicle; receiving return information sent by the cloud reasoning server; the return information includes return information of agreement to registration and return information of refusal to registration.

In one embodiment, the inference request generating module 801 is further configured to: and acquiring a data packet through a vehicle-mounted road surface information acquisition device, wherein the data packet comprises road condition image information and road condition point cloud information.

In one embodiment, the vehicle automatic driving system apparatus further comprises: the system comprises a vehicle-mounted road information acquisition device, a vehicle-mounted driving control device and a vehicle-mounted intelligent processing terminal;

the vehicle-mounted running control device is connected with the inference result receiving module and used for controlling the running of the automatic driving vehicle according to the inference result generated by the cloud inference server

the vehicle-mounted intelligent processing terminal is used for generating an inference request, sending the inference request to the cloud-end inference server and receiving an inference result generated by the cloud-end inference server;

and the vehicle-mounted running control device is used for controlling the automatic driving vehicle to run according to the inference result generated by the cloud inference server.

Specifically, the automatic driving vehicle comprises a vehicle-mounted road surface information acquisition device, a vehicle-mounted driving control device and a vehicle-mounted intelligent processing terminal. The vehicle-mounted road information acquisition device is used for acquiring a data packet, and the data packet comprises road condition image information and road condition point cloud information. The data packet not only includes road condition image information and road condition point cloud information, but also includes different inference request data packets, for example, driving state information of the vehicle, and the like. The vehicle-mounted intelligent processing terminal is used for generating an inference request, sending the inference request to the cloud end inference server and receiving an inference result generated by the cloud end inference server.

Fig. 3 is a flow chart of information processing of an on-board intelligent processing terminal in the vehicle automatic driving system in an embodiment, as shown in fig. 3, the on-board intelligent processing terminal is an operable terminal installed in and operable in the vehicle, and is capable of receiving an external instruction and information sent by the cloud-based reasoning server, including an instruction of an artificial operation or a preset instruction caused by an interrupted operation; and the information can be sent to the cloud reasoning server according to the received instruction. The vehicle-mounted running control device is used for controlling the automatic driving vehicle to run according to the inference result generated by the cloud-end inference server, is connected with the vehicle-mounted intelligent processing terminal, can receive the inference result sent by the cloud-end vehicle server through the vehicle-mounted intelligent processing terminal, controls the running state of the automatic driving vehicle according to the inference result, and executes corresponding control action.

In the embodiment, the data packet is acquired through the vehicle-mounted road information acquisition device, the inference request is generated through the vehicle-mounted intelligent processing terminal, the inference request is sent to the cloud end inference server, and the inference result generated by the cloud end inference server is received. And the vehicle-mounted running control device controls the running of the automatic driving vehicle according to the inference result generated by the cloud-end inference server, so that the inference result is generated by the cloud-end inference server and the automatic driving vehicle is controlled.

Specifically, the vehicle-mounted road information acquisition device comprises a vehicle-mounted road image acquisition device and a vehicle-mounted radar system. The vehicle-mounted road surface image acquisition device is used for acquiring road condition image information and sending the road condition image information to the vehicle-mounted intelligent processing terminal; the road condition image information is road condition information around the automatic driving vehicle, and mainly comprises surrounding road surface information, surrounding vehicle information, surrounding obstacles, pedestrian information and the like. The vehicle-mounted radar system is used for acquiring road condition point cloud information and sending the road condition point cloud information to the vehicle-mounted intelligent processing terminal; for example, the laser radar system is used for collecting road condition laser radar point cloud information and sending the road condition laser radar point cloud information to the vehicle-mounted intelligent processing terminal. The vehicle-mounted radar system can not only detect the road condition information in the surrounding range, but also detect the road condition information in a far area through the radar, and is favorable for the safe driving of the automatic driving vehicle.

In the embodiment, the vehicle-mounted road surface image acquisition device acquires road condition image information and sends the road condition image information to the vehicle-mounted intelligent processing terminal; the vehicle-mounted radar system is used for acquiring road condition point cloud information and sending the road condition point cloud information to the vehicle-mounted intelligent processing terminal, so that the cloud reasoning information can be used for reasoning according to the road condition image information and the road condition point cloud information.

In one embodiment, the vehicle-mounted intelligent processing terminal comprises: the processor is used for receiving the road condition image information and the road condition point cloud information and generating an inference request; and the communication device is used for realizing wireless communication between the vehicle-mounted intelligent processing and the cloud reasoning server.

Specifically, fig. 4 is a diagram illustrating an inference request structure in the automatic vehicle driving system according to an embodiment, as shown in fig. 4, the inference request includes a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required for making inference according to the request type. The vehicle-mounted intelligent processing terminal comprises a processor and a communication device, wherein the processor is connected with the vehicle-mounted road information acquisition device and the vehicle-mounted driving control device and is used for processing information, for example, the information acquired by the road information acquisition device is processed; the communication device is connected with the processor and is used for communicating with the cloud reasoning server according to the instruction of the processor, for example, the reasoning request generated by the processor or the road information acquired by the vehicle-mounted road information acquisition device is sent to the cloud reasoning server. The processor is also connected with the vehicle-mounted running control device so as to control the vehicle-mounted running control device to execute the corresponding running instruction according to the inference result.

In the embodiment, the processor in the vehicle-mounted intelligent processing terminal is connected with the vehicle-mounted road information acquisition device, the vehicle-mounted driving control device and the communication device, so that the road condition information is acquired and processed, and the communication with the cloud reasoning server is realized.

In one embodiment, the onboard radar system includes at least one of a laser radar system, an ultrasonic radar system, a millimeter wave radar system, and a microwave radar system.

In particular, when the autonomous vehicle is in a high-speed driving state, there may be a case where a broken or stepped section ahead cannot be seen in time due to weather or a view. Through the vehicle-mounted radar system, abnormal road conditions in front can be scanned, abnormal road conditions are sent to the vehicle-mounted intelligent processing terminal of the automatic driving vehicle in time, abnormal road information is sent to the cloud reasoning server through the communication device, and a reasoning result is generated through reasoning of the cloud reasoning server and sent to the automatic driving vehicle. Under such a road condition, the autonomous vehicle acquires the road surface abnormality information mainly by a vehicle-mounted radar system capable of detecting a long distance, and the type of the vehicle-mounted radar system includes at least one of a laser radar system, an ultrasonic radar system, and a microwave radar system. For example, when the vehicle-mounted radar system is a laser radar system, the vehicle-mounted radar system generates road condition laser radar point cloud information.

In the embodiment, the abnormal road section in front of the automatic driving vehicle is detected through the vehicle-mounted radar system, the abnormal road information is sent to the cloud reasoning server, the reasoning result is generated and sent to the automatic driving vehicle through processing of the cloud reasoning server so that the automatic driving vehicle can carry out corresponding actions, and the driving safety of the automatic driving vehicle is improved.

In one embodiment, the communication device includes at least one of a WIFI device, a bluetooth device, a GPRS device, a 3G, 4G, and 5G module connected to the processor.

Specifically, a suitable wireless communication device can be selected according to actual needs, and the applicability is wide. For example, the wireless communication device of the vehicle-mounted intelligent processing terminal uses at least one of a WIFI device, a bluetooth device, a GPRS device, a 3G, 4G, and 5G module connected to the processor; the WIFI device and the Bluetooth device are suitable for the situation that the wireless communication distance is short, for example, an automatic driving vehicle automatically runs in a relatively closed and narrow area such as a park; GPRS devices, 3G, 4G and 5G modules are suitable for long distance communication, such as driving on roads between cities.

In this embodiment, carry out wireless connection through at least one of WIFI device, bluetooth device, GPRS device, 3G, 4G and 5G module between the autonomous driving vehicle and the high in the clouds inference server, realized the stable wireless communication between autonomous driving vehicle and the high in the clouds inference server, avoided the risk that the core algorithm of operation platform leads to in depositing the autonomous driving vehicle is revealed.

For specific limitations of the vehicle autopilot device, reference may be made to the above limitations of the vehicle autopilot method, which are not described in detail herein. The respective modules in the above-described automatic vehicle driving apparatus may be wholly or partially implemented by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

The vehicle automatic driving device generates and sends an inference request to a cloud inference server in wireless connection with the automatic driving vehicle through the automatic driving vehicle, receives the inference request sent by the automatic driving vehicle through the cloud inference server, generates a corresponding inference result according to the inference request, and sends the inference result to the automatic driving vehicle; and finally, the automatic driving vehicle receives the inference result sent by the cloud inference server and executes a corresponding driving instruction according to the inference result. The core algorithm is arranged on the cloud reasoning server in wireless connection with the automatic driving vehicle, so that the core algorithm is prevented from being leaked.

In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a video service distribution method.

It will be appreciated by those skilled in the art that the configuration shown in fig. 9 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:

In one embodiment, the processor, when executing the computer program, further performs the steps of: analyzing the inference request, and selecting a corresponding deep learning model according to the inference request; performing reasoning processing on the data packet according to the deep learning model to obtain a reasoning result; and sending the inference result to the automatic driving vehicle.

In one embodiment, the processor, when executing the computer program, further performs the steps of: analyzing the inference request, and judging whether a required deep learning model is selected in the inference request; and if the required deep learning model is selected in the inference request, selecting the selected deep learning model in the inference request as the deep learning model used in the inference processing.

In one embodiment, the processor when executing the computer program further performs the steps of: if the needed deep learning model is not selected in the inference request, acquiring an inference purpose according to the inference request; and selecting a deep learning model with the highest prediction accuracy rate capable of realizing the reasoning purpose according to the content of the reasoning purpose.

In one embodiment, the processor, when executing the computer program, further performs the steps of: receiving a registration inference engine service request sent by an automatic driving vehicle; the service request of the registration inference engine is offer information which is sent by the automatic driving vehicle and used for applying the cloud inference server to carry out inference processing on the inference request sent by the automatic driving vehicle; and judging whether the automatic driving vehicle meets a preset registration condition, if so, agreeing to a registration inference engine service request of the automatic driving vehicle, and sending a registration agreement return message to the automatic driving vehicle.

The computer equipment generates and sends an inference request to a cloud inference server in wireless connection with the automatic driving vehicle through the automatic driving vehicle, receives the inference request sent by the automatic driving vehicle through the cloud inference server, generates a corresponding inference result according to the inference request, and sends the inference result to the automatic driving vehicle; and finally, the automatic driving vehicle receives the inference result sent by the cloud inference server and executes a corresponding driving instruction according to the inference result. The core algorithm is arranged on the cloud reasoning server in wireless connection with the automatic driving vehicle, so that the core algorithm is prevented from being leaked.

In one embodiment, the processor, when executing the computer program, further performs the steps of: when receiving an instruction of the inference request and/or the running state of the automatic driving vehicle accords with the inference request generation condition, generating a corresponding inference request; and sending the inference request to the cloud inference server.

In one embodiment, the processor, when executing the computer program, further performs the steps of: receiving an inference result sent by the cloud inference server; analyzing the inference result to generate a driving instruction; and controlling the automatic driving vehicle to run according to the driving instruction.

In one embodiment, the processor, when executing the computer program, further performs the steps of: sending a registration inference engine service request to the cloud inference server; the service request of the registration inference engine is offer information which is sent by the automatic driving vehicle and used for applying the inference server to carry out inference processing on the inference request sent by the cloud inference server; receiving return information sent by the cloud reasoning server; the return information includes return information of approving registration and return information of refusing registration.

In one embodiment, the processor, when executing the computer program, further performs the steps of: and acquiring a data packet through a vehicle-mounted road surface information acquisition device, wherein the data packet comprises road condition image information and road condition point cloud information.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:

In one embodiment, the computer program when executed by the processor further performs the steps of: analyzing the inference request, and selecting a corresponding deep learning model according to the inference request; reasoning processing is carried out on the data packet according to the deep learning model, and a reasoning result is obtained; and sending the inference result to the automatic driving vehicle.

In one embodiment, the computer program when executed by the processor further performs the steps of: analyzing the inference request, and judging whether a required deep learning model is selected in the inference request; and if the required deep learning model is selected in the inference request, selecting the selected deep learning model in the inference request as the deep learning model used in the inference processing.

In one embodiment, the computer program when executed by the processor further performs the steps of: if the needed deep learning model is not selected in the inference request, acquiring an inference purpose according to the inference request; and selecting a deep learning model with the highest prediction accuracy rate capable of realizing the reasoning purpose according to the content of the reasoning purpose.

In one embodiment, the computer program when executed by the processor further performs the steps of: receiving a registration inference engine service request sent by an automatic driving vehicle; the service request of the registration inference engine is offer information which is sent by the automatic driving vehicle and used for applying the cloud inference server to carry out inference processing on the inference request sent by the automatic driving vehicle; and judging whether the automatic driving vehicle meets a preset registration condition, if so, agreeing to a registration inference engine service request of the automatic driving vehicle, and sending a registration agreement return message to the automatic driving vehicle.

The storage medium generates and sends an inference request to a cloud inference server in wireless connection with the automatic driving vehicle through the automatic driving vehicle, receives the inference request sent by the automatic driving vehicle through the cloud inference server, generates a corresponding inference result according to the inference request, and sends the inference result to the automatic driving vehicle; and finally, the automatic driving vehicle receives the inference result sent by the cloud inference server and executes a corresponding driving instruction according to the inference result. The core algorithm is arranged on the cloud reasoning server in wireless connection with the automatic driving vehicle, so that the core algorithm is prevented from being leaked.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, performs the steps of:

In one embodiment, the computer program when executed by the processor further performs the steps of: when receiving an instruction of the inference request and/or the running state of the automatic driving vehicle accords with the inference request generation condition, generating a corresponding inference request; and sending the inference request to the cloud inference server.

In one embodiment, the computer program when executed by the processor further performs the steps of: receiving an inference result sent by the cloud inference server; analyzing the inference result to generate a driving instruction; and controlling the automatic driving vehicle to run according to the driving instruction.

In one embodiment, the computer program when executed by the processor further performs the steps of: sending a service request of a registration inference engine to the cloud inference server; the service request of the registration inference engine is offer information which is sent by the automatic driving vehicle and used for applying the cloud inference server to carry out inference processing on the inference request sent by the automatic driving vehicle; receiving return information sent by the cloud reasoning server; the return information includes return information of approving registration and return information of refusing registration.

In one embodiment, the computer program when executed by the processor further performs the steps of: and acquiring a data packet through a vehicle-mounted road surface information acquisition device, wherein the data packet comprises road condition image information and road condition point cloud information.

The storage medium generates and sends an inference request to a cloud inference server wirelessly connected with the autonomous vehicle through the autonomous vehicle, receives the inference request sent by the autonomous vehicle through the cloud inference server, generates a corresponding inference result according to the inference request, and sends the inference result to the autonomous vehicle; and finally, the automatic driving vehicle receives the inference result sent by the cloud inference server and executes a corresponding driving instruction according to the inference result. The core algorithm is arranged on the cloud reasoning server in wireless connection with the automatic driving vehicle, so that the core algorithm is prevented from being leaked.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.

All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not to be understood as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

An automatic driving system for a vehicle, the system comprising: the system comprises a cloud reasoning server and an automatic driving vehicle; the automatic driving vehicle is connected with the cloud reasoning server through wireless communication;

the automatic driving vehicle is used for generating and sending an inference request to the cloud inference server, receiving an inference result sent by the cloud inference server, and executing a corresponding driving instruction according to the inference result;

the cloud reasoning server is used for receiving a reasoning request sent by the automatic driving vehicle, generating a corresponding reasoning result according to the reasoning request and sending the reasoning result to the automatic driving vehicle;

the inference result is an instruction generated by the cloud inference server according to the inference request; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required for making inference according to the request type.
A method of automatically driving a vehicle, the method comprising:

receiving an inference request sent by an automatic driving vehicle; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required by inference according to the request type;

generating a corresponding reasoning result according to the reasoning request, and sending the reasoning result to the automatic driving vehicle; the inference result is a command which is generated by the cloud inference server through deep learning model processing according to the inference request and is used for controlling the automatic driving vehicle to run.
The method of claim 2, wherein generating the corresponding inference result from the inference request and sending the inference result to the autonomous vehicle comprises:

analyzing the inference request, and selecting a corresponding deep learning model according to the inference request;

reasoning processing is carried out on the data packet according to the deep learning model, and a reasoning result is obtained;

and sending the inference result to the automatic driving vehicle.
The method of claim 3, wherein parsing the inference request and selecting a corresponding deep learning model according to the inference request comprises:

analyzing the inference request, and judging whether a required deep learning model is selected in the inference request;

and if the needed deep learning model is selected in the inference request, selecting the selected deep learning model in the inference request as the deep learning model used in the inference process.
The method of claim 4, wherein parsing the inference request and selecting a corresponding deep learning model according to the inference request further comprises:

if the needed deep learning model is not selected in the inference request, acquiring an inference purpose according to the inference request;

and selecting a deep learning model with the highest prediction accuracy rate capable of realizing the reasoning purpose according to the content of the reasoning purpose.
The method of claim 2, wherein receiving the inference request sent by the autonomous vehicle further comprises:

receiving a registration inference engine service request sent by an automatic driving vehicle; the service request of the registration inference engine is offer information which is sent by the automatic driving vehicle and used for applying the cloud inference server to carry out inference processing on the inference request sent by the automatic driving vehicle;

and judging whether the automatic driving vehicle meets a preset registration condition, if so, agreeing to a registration inference engine service request of the automatic driving vehicle, and sending a registration agreement return message to the automatic driving vehicle.
A method of automatically driving a vehicle, the method comprising:

generating and sending an inference request to a cloud inference server; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required by inference according to the request type;

receiving an inference result sent by the cloud inference server, and executing a corresponding driving instruction according to the inference result; the inference result is a command which is generated by the cloud inference server through a deep learning model according to the inference request and is used for controlling the automatic driving vehicle to run.
The method of claim 7, wherein generating and sending inference requests to a cloud inference server comprises:

when receiving an instruction of the inference request and/or the running state of the automatic driving vehicle accords with the inference request generation condition, generating a corresponding inference request;

and sending the inference request to the cloud inference server.
The method of claim 7, wherein the receiving the inference result sent by the cloud inference server and executing the corresponding driving instruction according to the inference result comprises:

receiving an inference result sent by the cloud inference server;

analyzing the inference result to generate a driving instruction;

and controlling the automatic driving vehicle to run according to the driving instruction.
The method of claim 7, wherein generating and sending the inference request to a cloud inference server further comprises:

sending a service request of a registration inference engine to the cloud inference server; the service request of the registration inference engine is offer information which is sent by the automatic driving vehicle and used for applying the cloud inference server to carry out inference processing on the inference request sent by the automatic driving vehicle;

receiving return information sent by the cloud reasoning server; the return information includes return information of agreement to registration and return information of refusal to registration.
The method of claim 8, wherein sending the inference request to the cloud inference server further comprises:

and acquiring a data packet through a vehicle-mounted road information acquisition device, wherein the data packet comprises road condition image information and road condition point cloud information.
An automatic driving apparatus for a vehicle, characterized in that the apparatus comprises:

the reasoning request receiving module is used for receiving a reasoning request sent by the automatic driving vehicle; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required by inference according to the request type;

the reasoning result generating module is used for generating a corresponding reasoning result according to the reasoning request and sending the reasoning result to the automatic driving vehicle; the inference result is a command which is generated by the cloud inference server through a deep learning model according to the inference request and is used for controlling the automatic driving vehicle to run.
An automatic driving apparatus for a vehicle, characterized in that the apparatus comprises:

the inference request generating module is used for generating and sending an inference request to the cloud inference server; the inference request comprises a request type and/or a data packet; the request type is the type requiring the cloud reasoning server to carry out reasoning service; the data packet is inference data required by inference according to the request type;

the reasoning result receiving module is used for receiving the reasoning result sent by the cloud reasoning server and executing a corresponding driving instruction according to the reasoning result; the inference result is a command which is generated by the cloud inference server through a deep learning model according to the inference request and is used for controlling the automatic driving vehicle to run.
The device of claim 13, further comprising a vehicle-mounted road information acquisition device, a vehicle-mounted driving control device and a vehicle-mounted intelligent processing terminal;

the vehicle-mounted road surface information acquisition device is used for acquiring a data packet, and the data packet comprises road condition image information and road condition point cloud information;

the vehicle-mounted intelligent processing terminal is arranged in the inference request generation module and used for generating an inference request, sending the inference request to the cloud-end inference server and receiving an inference result generated by the cloud-end inference server;

the vehicle-mounted driving control device is connected with the reasoning result receiving module and used for controlling the automatic driving vehicle to drive according to the reasoning result generated by the cloud reasoning server.
The system according to claim 14, characterized in that the vehicle-mounted road surface information acquisition device comprises a vehicle-mounted road surface image acquisition device and a vehicle-mounted radar system;

the vehicle-mounted road surface image acquisition device is used for acquiring road condition image information and sending the road condition image information to the vehicle-mounted intelligent processing terminal;

the vehicle-mounted radar system is used for acquiring road condition point cloud information and sending the road condition point cloud information to the vehicle-mounted intelligent processing terminal.
The system of claim 15, wherein the vehicle-mounted intelligent processing terminal comprises:

the processor is used for receiving the road condition image information and the road condition point cloud information and generating an inference request;

and the communication device is used for realizing wireless communication between the vehicle-mounted intelligent processing and the cloud reasoning server.
The system of claim 15, wherein the onboard radar system comprises at least one of a laser radar system, an ultrasonic radar system, a millimeter wave radar system, and a microwave radar system.
The system of claim 16, wherein the communication device comprises at least one of a WIFI device, a bluetooth device, a GPRS device, a 3G, 4G, and 5G module coupled to the processor.
A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 2 to 11 when executing the computer program.
A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 2 to 11.