Automatic driving method and device, electronic equipment and storage medium

Abstract

The invention provides an automatic driving method and device, electronic equipment and a storage medium, and relates to the technical field of automatic driving, a vehicle receives a first request broadcasted by roadside equipment, the first request is used for requesting to collaboratively perform model processing with vehicles within a preset range of the roadside equipment, and the roadside equipment is installed at a fixed position beside a road; in response to the first request, loading a first driving decision-making module of the first driving decision-making model, so as to cooperatively perform model processing through the first driving decision-making module and a second driving decision-making module of the first driving decision-making model pre-loaded by the roadside equipment, so that the vehicle can cooperatively perform automatic driving decision-making with the roadside equipment, and the driving efficiency of the vehicle is improved. The image processing effect can be improved, the decision accuracy of automatic driving is improved, and the risk of automatic driving is reduced.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an autonomous driving method, device, electronic device and storage medium. Background Art

[0002] With the rapid development of autonomous driving, how to improve the accuracy of autonomous driving decisions is becoming increasingly important. In related technologies, vehicles collect data and then input the collected data into a trained model to obtain the vehicle's driving decision.

[0003] However, the limited performance of vehicles leads to poor decision-making accuracy in autonomous driving, which in turn leads to certain risks in autonomous driving. Summary of the invention

[0004] In view of this, an object of the present invention is to provide an autonomous driving method, device, electronic device and storage medium to improve the decision-making accuracy of autonomous driving and reduce the risk of autonomous driving.

[0005] In a first aspect, an embodiment of the present invention provides an automatic driving method, which is applied to a vehicle, and the method includes: receiving a first request broadcast by a roadside device, the first request being used to request collaborative model processing with vehicles within a preset range of the roadside device, and the roadside device being installed at a fixed position beside the road; in response to the first request, loading a first driving decision module of a first driving decision model, so as to collaboratively perform model processing through the first driving decision module and a second driving decision module of the first driving decision model pre-loaded by the roadside device, wherein the second driving decision module is different from the first driving decision module, and the second driving decision module and one of the first driving decision modules are used to process input perception data to obtain intermediate perception data, and the second driving decision module and the other of the first driving decision module are used to process the intermediate perception data to obtain a first decision result of automatic driving.

[0006] In a possible implementation, model processing is performed collaboratively by a first driving decision module and a second driving decision module loaded on a roadside device, including: acquiring input perception data obtained by environmental perception; processing the input perception data by the first driving decision module to obtain intermediate perception data, and sending the intermediate perception data to the roadside device; receiving a first decision result of autonomous driving from the roadside device, wherein the first decision result of autonomous driving is obtained by processing the intermediate perception data by the second driving decision module.

[0007] In a possible implementation, model processing is performed collaboratively by a first driving decision module and a second driving decision module loaded on a roadside device, including: acquiring input perception data obtained by environmental perception; sending the input perception data to a roadside device; receiving intermediate perception data from the roadside device, the intermediate perception data being obtained by the roadside device processing the input perception data based on the second driving decision module; and processing the intermediate perception data by the first driving decision module to obtain a first decision result of autonomous driving.

[0008] In a possible implementation, the first request carries a module identifier of a first driving decision module, and in response to the first request, the first driving decision module of the first driving decision model is loaded, including: in response to the first request, obtaining the first driving decision module of the first driving decision model from a server based on the module identifier, and loading the first driving decision module; or, in response to the first request, obtaining the first driving decision module of the first driving decision model from a roadside device based on the module identifier, and loading the first driving decision module.

[0009] In a possible implementation, in response to a first request, obtaining a first driving decision module of a first driving decision model from a roadside device based on a module identifier includes: in response to the first request carrying a first indication or not carrying a second indication, obtaining the first driving decision module of the first driving decision model from the roadside device based on the module identifier; or, in response to the first request, obtaining the first driving decision module of the first driving decision model from a server based on the module identifier includes: in response to the first request not carrying the first indication or carrying the second indication, obtaining the first driving decision module of the first driving decision model from the server based on the module identifier; wherein the first indication is used to indicate that the roadside device stores the first driving decision module, and the second indication is used to indicate that the roadside device does not store the first driving decision module.

[0010] In a possible implementation, the first request carries parameter quantity information of the first driving decision module, and in response to the first request, the first driving decision module of the first driving decision model is loaded, including: obtaining resource information of the vehicle, the resource information is used to indicate the data processing capability of the vehicle; based on the resource information and the parameter quantity information, judging whether the data processing capability of the vehicle can meet the parameter quantity of the first driving decision module; when the data processing capability of the vehicle can meet the parameter quantity of the first driving decision module, in response to the first request, loading the first driving decision module of the first driving decision model.

[0011] In a possible implementation, the method also includes: when the data processing capability of the vehicle cannot meet the parameter quantity of the first driving decision module, loading a second driving decision model to process the input perception data through the second driving decision model to obtain a second decision result of autonomous driving, wherein the data processing capability of the vehicle can meet the parameter quantity of the second driving decision model.

[0012] In one possible implementation, the method also includes: in response to the first request, sending a first message to the roadside device, the first message being used to indicate permission to perform model processing in collaboration with the roadside device, so that the roadside device performs model processing in collaboration with the vehicle based on the second driving decision module loaded thereon.

[0013] In a second aspect, an embodiment of the present invention provides another autonomous driving method, which is applied to a roadside device, wherein the roadside device is installed at a fixed position beside the road, and the roadside device is pre-loaded with a second driving decision module of a first driving decision model. The method includes: broadcasting a first request, wherein the first request is used to request collaborative model processing with vehicles within a preset range of the roadside device; receiving a first message from the vehicle, and collaboratively performing model processing through the second driving decision module loaded by the roadside device and the first driving decision module of the first driving decision model loaded by the vehicle, wherein the second driving decision module is different from the first driving decision module, and the second driving decision module and one of the first driving decision modules are used to process input perception data to obtain intermediate perception data, and the second driving decision module and the other of the first driving decision module are used to process the intermediate perception data to obtain a first decision result of autonomous driving.

[0014] In a third aspect, an embodiment of the present invention provides an automatic driving device, which is applied to a vehicle, and the device includes: a receiving module, which is used to receive a first request broadcast by a roadside device, and the first request is used to request collaborative model processing with vehicles within a preset range of the roadside device; a responding module, which is used to load a first driving decision module of a first driving decision model in response to the first request, so as to collaboratively perform model processing through the first driving decision module and a second driving decision module of the first driving decision model pre-loaded by the roadside device, wherein the second driving decision module is different from the first driving decision module, and the second driving decision module and one of the first driving decision modules are used to process input perception data to obtain intermediate perception data, and the second driving decision module and the other of the first driving decision module are used to process the intermediate perception data to obtain a first decision result of automatic driving.

[0015] In a fourth aspect, an embodiment of the present invention provides another autonomous driving device, which is applied to roadside equipment, wherein the roadside equipment is installed at a fixed position beside the road, and the roadside equipment is pre-loaded with a second driving decision module of a first driving decision model, and the device includes: a broadcast module, which is used to broadcast a first request, and the first request is used to request collaborative model processing with vehicles within a preset range of the roadside equipment; a driving decision module, which is used to receive a first message from the vehicle, and collaboratively perform model processing with the second driving decision module loaded by the roadside equipment and the first driving decision module of the first driving decision model loaded by the vehicle, wherein the second driving decision module is different from the first driving decision module, and the second driving decision module and one of the first driving decision modules are used to process the input perception data to obtain intermediate perception data, and the second driving decision module and the other of the first driving decision module are used to process the intermediate perception data to obtain a first decision result of autonomous driving.

[0016] In a fifth aspect, an embodiment of the present invention provides an electronic device comprising a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method of the first aspect or the second aspect.

[0017] In a sixth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method of the first aspect or the second aspect.

[0018] The embodiment of the present invention brings the following beneficial effects: a first request broadcast by a roadside device is received by a vehicle, the first request is used to request collaborative model processing with vehicles within a preset range of the roadside device, and the roadside device is installed at a fixed position beside the road; in response to the first request, a first driving decision module of the first driving decision model is loaded, so as to collaboratively perform model processing through the first driving decision module and a second driving decision module of the first driving decision model pre-loaded by the roadside device, wherein the second driving decision module is different from the first driving decision module, the second driving decision module and one of the first driving decision modules are used to process input perception data to obtain intermediate perception data, the second driving decision module and another of the first driving decision modules are used to process the intermediate perception data to obtain a first decision result of autonomous driving, so that the vehicle can collaborate with the roadside device to make decisions on autonomous driving, so that the effect of image processing can be improved, the accuracy of autonomous driving decisions can be improved, and the risk of autonomous driving can be reduced.

[0019] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 A schematic diagram of a flow chart of an automatic driving method provided by an embodiment of the present invention;

[0023] Figure 2 A schematic diagram of a flow chart of another automatic driving method provided by an embodiment of the present invention;

[0024] Figure 3 A schematic diagram of the structure of an automatic driving device provided by an embodiment of the present invention;

[0025] Figure 4 A schematic diagram of the structure of another automatic driving device provided by an embodiment of the present invention;

[0026] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0028] In related technologies, when a vehicle is driving, it is necessary to use a driving decision model to process images collected by the vehicle to obtain the vehicle's driving decision, thereby guiding the vehicle's automatic driving.

[0029] However, the performance of the vehicle is limited, and the accuracy of the autonomous driving decisions made by the driving decision model run by the vehicle is limited.

[0030] In view of this, an embodiment of the present invention provides a method, device, electronic device and storage medium for multi-vehicle image processing, which can improve the effect of image processing.

[0031] To facilitate understanding of this embodiment, the application scenario of the embodiment of the present invention is first exemplified. In this embodiment, it is applicable to the situation where the roadside equipment and the vehicle cooperate to make autonomous driving decisions. Generally speaking, the roadside equipment is installed at a fixed position beside the road, and the vehicle can make autonomous driving decisions in collaboration with the roadside equipment close to it.

[0032] See also Figure 1 , Figure 1 A flowchart of an automatic driving method provided by an embodiment of the invention. Figure 1 The method shown may be applied to a vehicle and may include:

[0033] S110. Receive a first request broadcast by a roadside device, where the first request is used to request collaborative model processing with vehicles within a preset range of the roadside device, and the roadside device is installed at a fixed position beside the road.

[0034] Among them, roadside equipment refers to equipment installed on both sides of the road or near the road, which is used to realize functions such as automatic vehicle identification, traffic monitoring, and information transmission. According to different functions and uses, roadside equipment may include but is not limited to: communication network equipment, perception equipment, and vehicle-road cooperative system equipment. Among them, communication network equipment is used to achieve full coverage of the communication network and provide low-latency, high-reliability, and high-speed services for information and data transmission. Perception equipment: such as cameras, lidars, millimeter-wave radars, etc., are used to monitor the operation status of traffic flow, real-time status of vehicles, highway infrastructure status information, and meteorological environment information. Vehicle-road cooperative system equipment includes roadside units (RSUs), edge computing units, video detection equipment, signal machines, traffic signs, traffic guardrails, lighting equipment, etc., which are used to realize collaborative interaction between vehicles and roads. In this embodiment, the roadside equipment can be based on broadcasting the first request through the communication device.

[0035] S120. In response to the first request, load the first driving decision module of the first driving decision model, so as to perform model processing in collaboration with the second driving decision module of the first driving decision model pre-loaded by the roadside equipment through the first driving decision module, wherein the second driving decision module is different from the first driving decision module, and the second driving decision module and one of the first driving decision modules are used to process the input perception data to obtain intermediate perception data, and the second driving decision module and the other driving decision module of the first driving decision module are used to process the intermediate perception data to obtain a first decision result of the automatic driving.

[0036] Among them, the first driving decision model is used to determine the driving decision result (also referred to as the decision result) to control the automatic driving of the vehicle according to the driving decision structure. Optionally, the first driving decision model can be, for example, a multimodal large model, such as a multimodal large model that integrates images and laser radar. The driving decision result may include but is not limited to changing lanes, keeping straight, slowing down, accelerating or driving at a constant speed. In this embodiment, the roadside device can cooperate with one or more vehicles close to it to perform automatic driving to determine the driving decision of the vehicle. In this embodiment, the roadside device is pre-loaded with a second driving decision module of the first driving decision model. In other words, the roadside device can be fixedly loaded with the second driving decision module of the first driving decision model. The first decision result is used to guide the automatic driving of the vehicle. The input perception data can be data collected by the vehicle. Optionally, the data collected by the vehicle can include but is not limited to data collected by a radar or camera installed on the vehicle.

[0037] In this embodiment, when the vehicle and the roadside equipment cooperate to make a decision on automatic driving, the vehicle loads a part of the modules of the first driving decision model, and the roadside equipment loads another part of the modules of the first driving decision model, so that the vehicle and the roadside equipment can each process the input perception data of the input model through the modules loaded by them to obtain the first decision result. Optionally, the processing order of the first driving decision module can be after the second driving decision module, or the processing order of the first driving decision module can be before the second driving decision module, which is determined according to the actual situation and is not limited here.

[0038] Generally speaking, the larger the number of model parameters, the more accurate the model processing results. In other words, the larger the number of parameters of the first driving decision model, the more accurate the decision results obtained by the first driving decision model. Therefore, by cooperating with the vehicle and roadside equipment for autonomous driving, the sum of the performance of the vehicle and roadside equipment can be used to load a driving decision model with a larger number of parameters, thereby improving the accuracy of autonomous driving and reducing the risks brought by autonomous driving.

[0039] In this embodiment, a first request broadcast by a roadside device is received by a vehicle, and the first request is used to request collaborative model processing with vehicles within a preset range of the roadside device, and the roadside device is installed at a fixed position beside the road; in response to the first request, a first driving decision module of the first driving decision model is loaded, so that the model processing is collaboratively performed through the first driving decision module and a second driving decision module of the first driving decision model pre-loaded by the roadside device, wherein the second driving decision module is different from the first driving decision module, and the second driving decision module and one of the first driving decision modules are used to process the input perception data to obtain intermediate perception data, and the second driving decision module and the other driving decision module of the first driving decision module are used to process the intermediate perception data to obtain a first decision result of autonomous driving, so that the vehicle can collaborate with the roadside device to make decisions on autonomous driving, so that the effect of image processing can be improved, the accuracy of autonomous driving decisions can be improved, and the risk of autonomous driving can be reduced.

[0040] In a possible implementation, the first driving decision module and the second driving decision module loaded by the roadside equipment cooperate to perform model processing, including:

[0041] Acquire input perception data obtained through environmental perception; process the input perception data through a first driving decision module to obtain intermediate perception data, and send the intermediate perception data to a roadside device; receive a first decision result of automatic driving from the roadside device, the first decision result of automatic driving is obtained by processing the intermediate perception data through a second driving decision module.

[0042] In this embodiment, the first decision result is output by the second driving decision module. Specifically, after the vehicle processes the collected input perception data through the first driving decision module loaded thereon to obtain intermediate perception data, the intermediate perception data is sent to the roadside device. The roadside device processes the intermediate perception data based on the second driving decision module loaded thereon to obtain the first decision result, and then sends the first decision result to the vehicle. The vehicle can then perform automatic driving based on the first decision result.

[0043] In this embodiment, the vehicle may be in the process of driving, and the vehicle first processes the input perception data and then sends it to the roadside equipment. The roadside equipment then processes the intermediate perception data to obtain a first decision result. During this process, the distance between the vehicle and the roadside equipment gradually decreases. At this time, the vehicle receives the first decision result from the roadside equipment faster, which can improve the efficiency of the vehicle in obtaining the first decision result, thereby making timely automatic driving actions.

[0044] Optionally, the vehicle may include a first vehicle and a second vehicle, that is, the roadside device simultaneously cooperates with multiple vehicles to make decisions on autonomous driving. In this case, the roadside device may fuse the intermediate perception data sent by the first vehicle and the intermediate perception data sent by the second vehicle, and process the fused perception data through the second driving decision module, thereby obtaining the first driving result of the first vehicle and the first driving result of the second vehicle. In this embodiment, the intermediate perception data of the first vehicle can be used as a reference for obtaining the first decision result of the second vehicle, and the intermediate perception data of the second vehicle can be used as a reference for obtaining the first decision result of the first vehicle, which can improve the accuracy of autonomous driving.

[0045] In a possible implementation, the first driving decision module and the second driving decision module loaded by the roadside equipment cooperate to perform model processing, including:

[0046] Acquire input perception data obtained by environmental perception; send the input perception data to the roadside equipment; receive intermediate perception data from the roadside equipment, the intermediate perception data is obtained by the roadside equipment processing the input perception data based on the second driving decision module; process the intermediate perception data through the first driving decision module to obtain a first decision result of autonomous driving.

[0047] In this embodiment, the first decision result is output by the first driving decision module. Specifically, the vehicle sends the collected input perception data to the roadside device, and the roadside device processes the input perception data based on the second driving decision module loaded thereon to obtain intermediate perception data, and then sends the intermediate perception data to the vehicle, and the vehicle can obtain the first decision result based on the intermediate perception data and the first driving decision module.

[0048] In this embodiment, by loading the first driving decision module for outputting the first decision result on the vehicle, the vehicle can fine-tune the parameters of the first driving decision module according to its own situation, and obtain the first decision result based on the fine-tuned first driving decision module, so different vehicles can be fine-tuned in different aspects to meet the personalized requirements of different vehicles. For example, if the user sets the vehicle driving mode to economy, the parameters of the first driving decision module are fine-tuned based on the economy mode, and the driving style corresponding to the automatic driving decision guided by the obtained first decision result is also more gentle; if the vehicle driving mode set by the user is sports, the parameters of the first driving decision module are fine-tuned based on the sports mode, and the driving style corresponding to the automatic driving decision guided by the obtained first decision result is also more sporty.

[0049] In a possible implementation, the first request carries a module identifier of the first driving decision module, and in response to the first request, loading the first driving decision module of the first driving decision model includes:

[0050] In response to the first request, a first driving decision module of the first driving decision model is obtained from the server based on the module identifier, and the first driving decision module is loaded.

[0051] In this embodiment, the first driving decision model can be stored in the server, and the vehicle can obtain the first driving decision module from the server based on the module identifier for loading. Since it is stored in the server, the storage resources required for the roadside equipment can be reduced.

[0052] In another possible implementation, in response to the first request, loading a first driving decision module of the first driving decision model includes:

[0053] In response to the first request, a first driving decision module of a first driving decision model is obtained from the roadside equipment based on the module identifier, and the first driving decision module is loaded.

[0054] In this embodiment, the first driving decision model can be stored in the roadside equipment, and the vehicle can obtain the first driving decision module from the roadside equipment based on the module identifier for loading. Since it is stored in the roadside equipment, the time required to obtain the first driving decision module can be reduced, thereby improving the decision-making efficiency of autonomous driving.

[0055] In a possible implementation, in response to the first request, obtaining a first driving decision module of the first driving decision model from the roadside equipment based on the module identifier includes:

[0056] In response to the first request carrying the first indication or not carrying the second indication, a first driving decision module of the first driving decision model is acquired from the roadside equipment based on the module identifier.

[0057] The first indication is used to indicate that the roadside device stores the first driving decision module, and the second indication is used to indicate that the roadside device does not store the first driving decision module.

[0058] In this embodiment, if the first request carries the first indication or does not carry the second indication, it means that the roadside device stores the first driving decision module, and the vehicle can obtain the first driving decision module from the roadside device.

[0059] In another possible implementation, in response to the first request, obtaining a first driving decision module of the first driving decision model from the server based on the module identifier includes:

[0060] In response to the first request not carrying the first indication or carrying the second indication, acquiring a first driving decision module of the first driving decision model from the server based on the module identifier;

[0061] In this embodiment, if the first request does not carry the first indication or carries the second indication, it means that the roadside equipment does not store the first driving decision module, and the vehicle can obtain the first driving decision module from the server.

[0062] In this embodiment, the vehicle is informed by the roadside equipment whether the first driving decision module is stored, so that the vehicle can successfully load the first driving decision module, thereby improving the success rate of automatic driving.

[0063] In a possible implementation, the first request carries parameter information of the first driving decision module, and in response to the first request, loading the first driving decision module of the first driving decision model includes:

[0064] Obtain resource information of the vehicle, where the resource information is used to indicate the data processing capability of the vehicle; based on the resource information and parameter quantity information, determine whether the data processing capability of the vehicle can meet the parameter quantity of the first driving decision module; if the data processing capability of the vehicle can meet the parameter quantity of the first driving decision module, load the first driving decision module of the first driving decision model in response to the first request.

[0065] The resource information may include the number of cores, frequency or video memory, etc. To determine whether the data processing capability of the vehicle can meet the parameter quantity of the first driving decision module, for example, it may be determined whether the video memory is greater than the parameter quantity of the first driving decision module. If the video memory is greater than the parameter quantity of the first driving decision module, the data processing capability of the vehicle can meet the parameter quantity of the first driving decision module. If the video memory is less than the parameter quantity of the first driving decision module, the data processing capability of the vehicle cannot meet the parameter quantity of the first driving decision module.

[0066] In this embodiment, when the data processing capability of the vehicle can meet the parameter quantity of the first driving decision module, the first driving decision module of the first driving decision model is loaded in response to the first request. In this way, the situation where the loading failure of the first driving decision module due to the inability to load the first driving decision module can be reduced, thereby improving the success rate of automatic driving.

[0067] In a possible implementation, the method further includes:

[0068] When the data processing capability of the vehicle cannot meet the parameter quantity of the first driving decision module, a second driving decision model is loaded to process the input perception data through the second driving decision model to obtain a second decision result of autonomous driving, wherein the data processing capability of the vehicle can meet the parameter quantity of the second driving decision model.

[0069] In this embodiment, the second driving decision model may be, for example, a single-modal large model, such as a single-modal large model that uses an image or a laser as a model input. Optionally, the parameter amount of the second driving decision model may be less than the parameter amount of the first driving decision model. The second decision result may refer to the description of the driving decision result, which will not be described in detail here.

[0070] In this embodiment, when the data processing capability of the vehicle cannot meet the parameter quantity of the first driving decision module, the second driving decision model is loaded, so that the input perception data is processed by the second driving decision model that can meet the data processing capability to obtain a second decision result, and the second decision result is used to guide the automatic driving of the vehicle, thereby improving the success rate of automatic driving.

[0071] In a possible implementation, the method further includes:

[0072] In response to the first request, a first message is sent to the roadside device, where the first message is used to indicate that model processing is allowed to be performed in collaboration with the roadside device, so that the roadside device performs model processing in collaboration with the vehicle based on the second driving decision module loaded thereon.

[0073] In this embodiment, a first message is sent to the roadside device to inform the roadside device that it agrees to collaborate in model processing.

[0074] It should be noted that if the vehicle does not agree to collaborate with the roadside equipment to perform model processing, the vehicle may not send the first message to the roadside equipment or may send a second message, and the second message indicates that collaborative model processing with the roadside equipment is not allowed. The vehicle then obtains a second decision result through the second driving decision model.

[0075] Optionally, if the vehicle does not agree to perform model processing with the roadside equipment system, the roadside equipment can release resources for collaborative model processing to other vehicles to improve resource utilization of the roadside equipment.

[0076] The above embodiment is described by applying the method to a vehicle, and the following embodiment is described by exemplifying the method by applying it to a roadside device.

[0077] See also Figure 2 , Figure 2 A flowchart of another automatic driving method provided by an embodiment of the present invention is shown below. The method of this embodiment is applied to roadside equipment, such as Figure 2 The methods shown may include:

[0078] S210: Broadcast a first request, where the first request is used to request collaborative model processing with vehicles within a preset range of the roadside device.

[0079] S220. A first message is received from the vehicle, and model processing is performed collaboratively by a second driving decision module loaded by the roadside device and a first driving decision module of the first driving decision model loaded by the vehicle, wherein the second driving decision module is different from the first driving decision module, and the second driving decision module and one of the first driving decision modules are used to process input perception data to obtain intermediate perception data, and the second driving decision module and the other driving decision module of the first driving decision module are used to process the intermediate perception data to obtain a first decision result of autonomous driving.

[0080] Among them, this embodiment can refer to the description of the above embodiment, and will not be repeated here.

[0081] In this embodiment, the roadside equipment broadcasts a first request and receives a first message from the vehicle, and performs model processing in collaboration with a second driving decision module loaded on the roadside equipment and a first driving decision module of a first driving decision model loaded on the vehicle, wherein the second driving decision module is different from the first driving decision module, and the second driving decision module and one of the first driving decision modules are used to process the input perception data to obtain intermediate perception data, and the second driving decision module and the other driving decision module of the first driving decision module are used to process the intermediate perception data to obtain a first decision result of autonomous driving. In this way, the vehicle can collaborate with the roadside equipment to make decisions on autonomous driving, and in this way, the effect of image processing can be improved, the accuracy of autonomous driving decisions can be improved, and the risk of autonomous driving can be reduced.

[0082] See also Figure 3 , Figure 3 Schematic diagram of the structure of an automatic driving device provided by an embodiment of the present invention. The device of this embodiment is applied to a vehicle, such as Figure 3 The apparatus shown may include:

[0083] The receiving module 310 is used to receive a first request broadcast by a roadside device, wherein the first request is used to request collaborative model processing with vehicles within a preset range of the roadside device; the responding module 320 is used to load a first driving decision module of a first driving decision model in response to the first request, so as to collaboratively perform model processing through the first driving decision module and a second driving decision module of the first driving decision model pre-loaded by the roadside device, wherein the second driving decision module is different from the first driving decision module, and the second driving decision module and one of the first driving decision modules are used to process input perception data to obtain intermediate perception data, and the second driving decision module and the other of the first driving decision module are used to process the intermediate perception data to obtain a first decision result of autonomous driving.

[0084] See also Figure 4 , Figure 4 Schematic diagram of another automatic driving device provided by an embodiment of the present invention. The device of this embodiment is applied to roadside equipment, such as Figure 4 The apparatus shown may include:

[0085] The broadcast module 410 is used to broadcast a first request, where the first request is used to request collaborative model processing with vehicles within a preset range of the roadside device; the driving decision module 420 is used to receive a first message from the vehicle, and collaboratively perform model processing through a second driving decision module loaded by the roadside device and a first driving decision module of a first driving decision model loaded by the vehicle, wherein the second driving decision module is different from the first driving decision module, and the second driving decision module and one of the first driving decision modules are used to process input perception data to obtain intermediate perception data, and the second driving decision module and the other of the first driving decision module are used to process the intermediate perception data to obtain a first decision result of autonomous driving.

[0086] The automatic driving device provided in the embodiment of the present invention has the same technical features as the automatic driving method provided in the above embodiment, so it can also solve the same technical problems and achieve the same technical effects. The device of this embodiment can refer to the description of the above method embodiment, and will not be repeated here.

[0087] This embodiment also provides an electronic device, including a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the above-mentioned automatic driving method. The electronic device can be a server or a terminal device.

[0088] See also Figure 5 As shown, the electronic device includes a processor 100 and a memory 101, wherein the memory 101 stores computer executable instructions that can be executed by the processor 100, and the processor 100 executes the computer executable instructions to implement the above-mentioned autonomous driving method.

[0089] Further, Figure 5 The electronic device shown further includes a bus 102 and a communication interface 103 , and the processor 100 , the communication interface 103 and the memory 101 are connected via the bus 102 .

[0090] The memory 101 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 103 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus 102 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0091] The processor 100 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 100. The above processor 100 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present invention can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 101, and the processor 100 reads the information in the memory 101 and completes the steps of the method of the above embodiment in combination with its hardware.

[0092] The processor in the above-mentioned electronic device can implement the steps in the above-mentioned autonomous driving method by executing computer-executable instructions.

[0093] This embodiment also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the above-mentioned autonomous driving method.

[0094] The computer-executable instructions stored in the above-mentioned computer-readable storage medium can be executed to implement the steps in the above-mentioned automatic driving method.

[0095] This embodiment also provides a computer program product, including program code. The instructions included in the program code can be used to execute the method in the previous method embodiment. The specific implementation can be found in the method embodiment, which will not be described in detail here.

[0096] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0097] In addition, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0098] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0099] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0100] Finally, it should be noted that the above embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above embodiments, those skilled in the art should understand that any person skilled in the art can still modify the technical solutions recorded in the above embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An automatic driving method, characterized in that: Applied to a vehicle, the method comprises: Receiving a first request broadcasted by a roadside device, the first request being used to request collaborative model processing with a vehicle within a preset range of the roadside device, the roadside device being installed at a fixed position beside a road; In response to the first request, a first driving decision module of a first driving decision model is loaded, so as to collaboratively perform model processing through the first driving decision module and a second driving decision module of the first driving decision model pre-loaded by the roadside equipment, wherein the second driving decision module is different from the first driving decision module, and the second driving decision module and one of the first driving decision modules are used to process input perception data to obtain intermediate perception data, and the second driving decision module and the other driving decision module of the first driving decision module are used to process the intermediate perception data to obtain a first decision result of autonomous driving.

2. The method according to claim 1, characterized in that The first driving decision module and the second driving decision module loaded by the roadside equipment cooperate to perform model processing, including: Acquire input perception data obtained by performing environmental perception; Processing the input perception data through the first driving decision module to obtain intermediate perception data, and sending the intermediate perception data to the roadside device; A first decision result of the automatic driving is received from the roadside device, where the first decision result of the automatic driving is obtained by processing the intermediate perception data through the second driving decision module.

3. The method according to claim 1, characterized in that The first driving decision module and the second driving decision module loaded by the roadside equipment cooperate to perform model processing, including: Acquire input perception data obtained by performing environmental perception; Sending the input sensing data to the roadside device; receiving intermediate perception data from the roadside device, where the intermediate perception data is obtained by the roadside device processing the input perception data based on the second driving decision module; The intermediate perception data is processed by the first driving decision module to obtain a first decision result of autonomous driving.

4. The method according to claim 1, characterized in that The first request carries a module identifier of the first driving decision module, and the step of loading the first driving decision module of the first driving decision model in response to the first request includes: In response to the first request, obtaining a first driving decision module of a first driving decision model from a server based on the module identifier, and loading the first driving decision module; or, In response to the first request, a first driving decision module of a first driving decision model is obtained from the roadside equipment based on the module identifier, and the first driving decision module is loaded.

5. The method according to claim 4, characterized in that The step of acquiring, in response to the first request, a first driving decision module of a first driving decision model from the roadside equipment based on the module identifier includes: In response to the first request carrying the first indication or not carrying the second indication, obtaining a first driving decision module of a first driving decision model from the roadside equipment based on the module identifier; or, The step of obtaining, in response to the first request, a first driving decision module of a first driving decision model from a server based on the module identifier comprises: In response to the first request not carrying the first indication or carrying the second indication, acquiring a first driving decision module of a first driving decision model from a server based on the module identifier; The first indication is used to indicate that the roadside device stores the first driving decision module, and the second indication is used to indicate that the roadside device does not store the first driving decision module.

6. The method according to any one of claims 1 to 5, characterized in that The first request carries parameter information of the first driving decision module, and the step of loading the first driving decision module of the first driving decision model in response to the first request includes: Acquiring resource information of the vehicle, where the resource information is used to indicate a data processing capability of the vehicle; Based on the resource information and the parameter quantity information, determining whether the data processing capability of the vehicle can meet the parameter quantity of the first driving decision module; In a case where the data processing capability of the vehicle can satisfy the parameter quantity of the first driving decision module, in response to the first request, the first driving decision module of the first driving decision model is loaded.

7. The method according to claim 6, characterized in that The method further comprises: When the data processing capability of the vehicle cannot meet the parameter quantity of the first driving decision module, a second driving decision model is loaded to process the input perception data through the second driving decision model to obtain a second decision result of autonomous driving, wherein the data processing capability of the vehicle can meet the parameter quantity of the second driving decision model.

8. The method according to any one of claims 1 to 5, characterized in that The method further comprises: In response to the first request, a first message is sent to the roadside device, wherein the first message is used to indicate permission to collaborate with the roadside device to perform model processing, so that the roadside device collaborates with the vehicle to perform model processing based on the second driving decision module loaded thereon.

9. An automatic driving method, characterized in that: Applied to a roadside device, the roadside device is installed at a fixed position beside the road, and the roadside device is pre-loaded with a second driving decision module of a first driving decision model. The method includes: Broadcasting a first request, wherein the first request is used to request collaborative model processing with vehicles within a preset range of the roadside equipment; After receiving a first message from the vehicle, the second driving decision module loaded by the roadside device and the first driving decision module of the first driving decision model loaded by the vehicle cooperate to perform model processing, wherein the second driving decision module is different from the first driving decision module, and the second driving decision module and one of the first driving decision modules are used to process the input perception data to obtain intermediate perception data, and the second driving decision module and the other driving decision module of the first driving decision module are used to process the intermediate perception data to obtain a first decision result of automatic driving.

10. An automatic driving device, characterized in that: Applied to a vehicle, the device comprises: A receiving module, configured to receive a first request broadcasted by a roadside device, wherein the first request is used to request collaborative model processing with a vehicle within a preset range of the roadside device; A response module is used to load a first driving decision module of a first driving decision model in response to the first request, so as to collaboratively perform model processing through the first driving decision module and a second driving decision module of the first driving decision model pre-loaded by the roadside equipment, wherein the second driving decision module is different from the first driving decision module, and the second driving decision module and one of the first driving decision modules are used to process input perception data to obtain intermediate perception data, and the second driving decision module and the other driving decision module of the first driving decision module are used to process the intermediate perception data to obtain a first decision result of autonomous driving.

11. An automatic driving device, characterized in that: Applied to a roadside device, the roadside device is installed at a fixed position beside the road, the roadside device is pre-loaded with a second driving decision module of a first driving decision model, and the device comprises: A broadcast module, used for broadcasting a first request, wherein the first request is used for requesting to perform model processing in collaboration with vehicles within a preset range of the roadside equipment; A driving decision module is used to receive a first message from the vehicle, and to perform model processing in collaboration with the second driving decision module loaded by the roadside equipment and the first driving decision module of the first driving decision model loaded by the vehicle, wherein the second driving decision module is different from the first driving decision module, and the second driving decision module and one of the first driving decision modules are used to process input perception data to obtain intermediate perception data, and the second driving decision module and the other driving decision module of the first driving decision module are used to process the intermediate perception data to obtain a first decision result of automatic driving.

12. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method of any one of claims 1 to 8 or the method of claim 9.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method of any one of claims 1 to 8 or the method of claim 9.

Images