Driving scheme determination method, device and system and storage medium

Abstract

The invention relates to a driving scheme determination method, device and system and a storage medium, and is applied to the technical field of automatic driving, and the method comprises the steps: collecting perception data in a road section where a vehicle runs; under the condition that the state of the cloud is normal, sensing data is sent to the cloud, so that the cloud processes the sensing data and vehicle state data received from a vehicle-mounted system through a pre-trained driving model to obtain a first driving scheme, and the first driving scheme is sent to the vehicle-mounted system in the vehicle; and training and generating a motion model based on the sensing data and vehicle state data received from the vehicle-mounted system, and sending the motion model to the vehicle-mounted system under the condition that the state of the cloud is abnormal, so that the vehicle-mounted system analyzes and processes the motion model to obtain a second driving scheme. According to the application, the dependence on the cloud can be reduced, and congestion and accidents can be avoided under the condition that the state of the cloud is abnormal.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a driving plan determination method, device, system and storage medium. Background Art

[0002] Vehicle-road collaboration refers to the use of advanced wireless communications and new-generation information technology to realize all-round dynamic real-time information interaction between vehicles, vehicles and roads, and vehicles and people, and to carry out vehicle active safety control and road collaborative management based on the collection and integration of dynamic traffic information in all time and space, fully realizing the effective collaboration between people, vehicles and roads, ensuring traffic safety, and improving traffic efficiency, thus forming a safe, efficient and environmentally friendly smart transportation system.

[0003] In related technologies, the cloud is used to send instructions to the vehicle to achieve autonomous driving. Although the vehicle can be controlled, in the case of heavy traffic, due to signal concentration and large network occupancy, there is a high delay in the interaction between the vehicle-side information and the cloud, and data interaction is not timely, causing network congestion and untimely allocation of cloud computing power, resulting in delayed results and even accidents. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides a driving plan determination method, device, system and storage medium.

[0005] According to a first aspect of the present application, a driving plan determination method is provided, which is applied to a roadside end, and the method includes:

[0006] Collecting perception data on the road section where the vehicle is traveling;

[0007] When the state of the cloud is normal, sending the perception data to the cloud, so that the cloud processes the perception data and the vehicle state data received from the vehicle system through a pre-trained driving model to obtain a first driving plan, and sending the first driving plan to the vehicle system;

[0008] A motion model is generated based on the perception data and the vehicle status data received from the vehicle system, and when the cloud status is abnormal, the motion model is sent to the vehicle system so that the vehicle system analyzes and processes the motion model to obtain a second driving plan.

[0009] Optionally, the training and generating a motion model based on the perception data and the vehicle state data received from the vehicle-mounted system includes:

[0010] Acquire the road section information of the road section on which the vehicle is traveling and the traffic condition information of the road section on which the vehicle is traveling from the perception data;

[0011] Determine a traffic control plan that matches the road section information;

[0012] A motion model is trained and generated based on the traffic control plan, the traffic condition information of the road section on which the vehicle is traveling, and the vehicle status data received from the on-board system.

[0013] Optionally, collecting the perception data on the road section traveled by the vehicle includes:

[0014] Collect image data and radar data on the road section where the vehicle is traveling;

[0015] The sending the sensing data to the cloud comprises:

[0016] The image data and the radar data are fused to obtain fused data, and the fused data is sent to the cloud.

[0017] According to a second aspect of the present application, a driving plan determination method is provided, which is applied to an on-board system in a vehicle, and the method comprises:

[0018] When the state of the cloud is normal, the vehicle state data is sent to the cloud, so that the cloud processes the perception data received from the roadside terminal and the vehicle state data through a pre-trained driving model to obtain a first driving plan;

[0019] receiving the first driving plan sent by the cloud;

[0020] Sending the vehicle status data to a roadside terminal, so that the roadside terminal trains and generates a motion model according to the collected perception data and the vehicle status data;

[0021] In case of abnormal state of the cloud, receiving the motion model sent by the roadside end;

[0022] The motion model is analyzed and processed to obtain a second driving plan.

[0023] According to a third aspect of the present application, a driving plan determination device is provided, which is applied to a roadside end, and includes:

[0024] A perception data collection module is used to collect perception data on the road section where the vehicle is traveling;

[0025] a perception data sending module, configured to send the perception data to the cloud when the cloud is in a normal state, so that the cloud processes the perception data and the vehicle state data received from the vehicle-mounted system through a pre-trained driving model to obtain a first driving plan, and send the first driving plan to the vehicle-mounted system;

[0026] A motion model generation module, used for training and generating a motion model based on the perception data and the vehicle state data received from the vehicle-mounted system;

[0027] The motion model sending module is used to send the motion model to the vehicle-mounted system when the state of the cloud is abnormal, so that the vehicle-mounted system analyzes and processes the motion model to obtain a second driving plan.

[0028] Optionally, the motion model generation module is specifically used to obtain the section information of the road section on which the vehicle is traveling and the traffic condition information of the road section on which the vehicle is traveling from the perception data when the status of the cloud is abnormal; determine a traffic control plan that matches the section information; and train and generate a motion model based on the traffic control plan, the traffic condition information of the road section on which the vehicle is traveling, and the vehicle status data received from the on-board system.

[0029] Optionally, the perception data acquisition module is specifically used to collect image data and radar data in the road section where the vehicle is traveling;

[0030] The perception data sending module is specifically used to fuse the image data and the radar data to obtain fused data, and send the fused data to the cloud.

[0031] According to a fourth aspect of the present application, a driving plan determination device is provided, which is applied to an on-board system in a vehicle, comprising:

[0032] A vehicle status data sending module, used for sending the vehicle status data to the cloud when the cloud is in a normal state, so that the cloud processes the perception data received from the roadside terminal and the vehicle status data through a pre-trained driving model to obtain a first driving plan;

[0033] A driving plan receiving module, used for receiving the first driving plan sent by the cloud;

[0034] The vehicle status data sending module is further used to send the vehicle status data to the roadside end, so that the roadside end trains and generates a motion model according to the collected perception data and the vehicle status data;

[0035] A motion model receiving module, used for receiving the motion model sent by the roadside end when the cloud state is abnormal;

[0036] The driving plan generating module is used to analyze and process the motion model to obtain a second driving plan.

[0037] According to a fifth aspect of the present application, a driving plan determination system is provided, comprising: an onboard system in a vehicle, a roadside terminal, and a cloud terminal;

[0038] The vehicle-mounted system is used to send the vehicle status data to the roadside end, and when the status in the cloud is normal, send the vehicle status data to the cloud;

[0039] The roadside end is used to collect the perception data in the road section where the vehicle is traveling, train and generate a motion model based on the perception data and the vehicle status data, and send the motion model to the vehicle-mounted system when the status of the cloud is abnormal; and send the perception data to the cloud when the status of the cloud is normal;

[0040] The cloud is used to process the perception data and the vehicle status data through a pre-trained driving model to obtain a first driving plan, and send the first driving plan to the vehicle-mounted system;

[0041] The vehicle-mounted system is used to analyze and process the motion model to obtain a second driving plan.

[0042] Optionally, the roadside end is specifically used to obtain the section information of the road section on which the vehicle is traveling and the traffic condition information of the road section on which the vehicle is traveling from the perception data when the status of the cloud is abnormal; determine a traffic control plan that matches the section information; and train and generate a motion model based on the traffic control plan, the traffic condition information of the road section on which the vehicle is traveling, and the vehicle status data.

[0043] Optionally, the roadside end includes: a camera, a radar and a roadside computing unit;

[0044] The camera is used to collect image data of the road section on which the vehicle is traveling;

[0045] The radar is used to collect radar data on the road section where the vehicle is traveling;

[0046] The roadside computing unit is used to fuse the image data and the radar data to obtain fused data, and send the fused data to the cloud.

[0047] According to a sixth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first aspect or the second aspect is implemented.

[0048] According to a seventh aspect of the present application, a computer program product is provided. When the computer program product is run on a computer, the computer is caused to execute the method described in the first aspect or the second aspect.

[0049] Compared with the prior art, the technical solution provided by the embodiments of the present application has the following advantages:

[0050] The roadside end collects the perception data of the road section where the vehicle is traveling. When the cloud is in a normal state, the perception data is sent to the cloud. The cloud processes the perception data and the vehicle status data received from the vehicle system through a pre-trained driving model to obtain a first driving plan, and sends the first driving plan to the vehicle system in the vehicle, that is, the cloud can distribute driving plans that meet the real-time environment of the vehicle in real time. The motion model is trained and generated based on the perception data and the vehicle status data received from the vehicle system, and when the cloud is in an abnormal state, the motion model is sent to the vehicle system so that the vehicle system analyzes and processes the motion model to obtain a second driving plan. It can be seen that when the cloud is in an abnormal state, that is, when the cloud loses its coordination ability, self-control of the vehicle end and the roadside end can be achieved, reducing dependence on the cloud, and the vehicle system in the vehicle end can still obtain a better driving plan to avoid congestion and accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0053] Figure 1 A schematic diagram showing a system architecture of an exemplary application environment of the driving plan determination method that can be applied to an embodiment of the present application;

[0054] Figure 2 A flow chart of a method for determining a driving plan in an embodiment of the present application;

[0055] Figure 3 It is another flow chart of the driving plan determination method in the embodiment of the present application;

[0056] Figure 4 An interactive flow chart of a method for determining a driving plan in an embodiment of the present application;

[0057] Figure 5 A schematic diagram of the structure of a driving plan determination device in an embodiment of the present application;

[0058] Figure 6 This is another structural schematic diagram of the driving plan determination device in the embodiment of the present application;

[0059] Figure 7 A structural diagram of a driving plan determination system in an embodiment of the present application. DETAILED DESCRIPTION

[0060] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the scheme of the present application will be further described below. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0061] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only part of the embodiments of the present application, rather than all of the embodiments.

[0062] Figure 1 A schematic diagram showing a system architecture of an exemplary application environment that can be applied to the driving plan determination method of an embodiment of the present application.

[0063] like Figure 1 As shown, the system architecture 100 may include a roadside terminal 101, one or more of an onboard system 102, an onboard system 103, and an onboard system 104, a network 105, and a cloud 106. The network 105 is used as a medium for providing a communication link between the roadside terminal 101 and the onboard system 102, the onboard system 103, and the onboard system 104, between the roadside terminal 101 and the cloud 106, and between the onboard system 102, the onboard system 103, the onboard system 104 and the cloud 106.

[0064] It should be understood that Figure 1 The number of roadside terminals, vehicle systems, networks, and clouds in the embodiment is only illustrative. Any number of roadside terminals, vehicle systems, networks, and clouds may be provided as required.

[0065] In the embodiment of the present application, the driving plan of the vehicle can be obtained in both normal and abnormal cloud status scenarios. Specifically, in the case of normal cloud status, the cloud processes the perception data collected by the roadside end and the vehicle status data received from the vehicle-mounted system to obtain a first driving plan, and sends the first driving plan to the vehicle-mounted system in the vehicle. In the case of abnormal cloud status, the roadside end generates a motion model based on the perception data and the vehicle status data received from the vehicle-mounted system, and sends the motion model to the vehicle-mounted system. The vehicle-mounted system analyzes and processes the motion model to obtain a second driving plan. It can be seen that the embodiment of the present application can achieve self-control of the vehicle-mounted system and the roadside end, reducing dependence on the cloud. In the case of abnormal cloud status, the vehicle-mounted system can still obtain a better driving plan to avoid congestion and accidents.

[0066] The following first introduces in detail the driving plan determination method of an embodiment of the present application.

[0067] See also Figure 2 , Figure 2 This is a flow chart of a driving plan determination method in an embodiment of the present application, which is applied to a roadside end and includes the following steps:

[0068] Step S202, collecting perception data on the road section where the vehicle is traveling.

[0069] The roadside terminal is the key to breaking through the vehicle-road collaborative technology. Through the network and roadside sensing equipment, traffic lights, electronic signs and other terminal communications as well as cloud communications, it realizes vehicle-road-cloud interconnection, real-time interaction of traffic signals, road condition information collection and edge-side calculation, completes digital perception of road conditions and deployment of nearby cloud computing power, and assists drivers in driving, ensuring the safety of people and vehicles in the entire transportation field.

[0070] The roadside end may include cameras, radars (such as millimeter wave radars and laser radars, etc.) and other sensors. Among them, the camera can collect image data in the road section where the vehicle is traveling, and the radar can collect radar data in the road section where the vehicle is traveling. Both image data and radar data are perception data, and other sensors can collect other types of perception data.

[0071] Step S204: generating a motion model based on the perception data and the vehicle status data received from the vehicle system.

[0072] Regardless of whether the status of the cloud is normal, the vehicle system can send vehicle status data to the roadside. Vehicle status data includes: high-precision positioning data of the vehicle, unique identification code of the vehicle, vehicle indicator status, gear status, etc. The roadside can train and generate a motion model based on the perception data and the vehicle status data received from the vehicle system. In other words, regardless of whether the status of the cloud is normal, the motion model of the roadside can be continuously updated. The more data used, the higher the accuracy of the trained motion model.

[0073] The motion model may include radar models, image recognition models, driving decision models, traffic control schemes (speed limits, traffic restrictions, etc.), etc. The motion model includes the location information of the vehicle, the current traffic conditions, the status information of the traffic lights, etc.

[0074] It is understandable that for different road sections, the corresponding traffic control schemes are usually different, so different motion models can be generated according to different traffic control schemes. In some embodiments, the road section information of the road section where the vehicle is traveling and the traffic condition information of the road section where the vehicle is traveling can be obtained from the perception data; the traffic control scheme matching the road section information is determined; and the motion model is trained and generated according to the traffic control scheme, the traffic condition information of the road section where the vehicle is traveling, and the vehicle status data.

[0075] Step S206, determining whether the cloud status is normal.

[0076] The cloud is the commander in vehicle-road collaboration and the basic support platform for the actual application needs of intelligent connected vehicles. The cloud has powerful data analysis and model training capabilities, and can generate a variety of different driving models based on a large amount of data training. Driving models include traffic control plans for each section of the road (speed limit, traffic restriction, etc.), image models of intersections, and image models of vehicles.

[0077] Since the cloud has powerful data analysis and model training capabilities, when the cloud is in a normal state, step S208 is executed, that is, the vehicle's driving plan is still obtained through the cloud to obtain a more accurate driving plan. When the cloud is in an abnormal state, step S210 is executed, that is, a better driving plan is obtained through the self-control of the roadside end and the vehicle-mounted system, avoiding congestion and accidents caused by failure to obtain a better driving plan through the cloud.

[0078] In the embodiment of the present application, the method of judging whether the status of the cloud is normal includes: judging whether the network between the cloud and the roadside end and the vehicle system meets the data interaction requirements, and whether the cloud is paralyzed. For example, when the roadside end communicates with the cloud, it is unable to receive a reply from the cloud, or although it can receive a reply from the cloud, the delay time is long, and the cloud status is considered abnormal. If the roadside end can receive a reply from the cloud without delay or with a short delay time, the cloud status is considered normal.

[0079] Step S208, sending the perception data to the cloud, so that the cloud processes the perception data and the vehicle status data received from the onboard system through a pre-trained driving model, obtains a first driving plan, and sends the first driving plan to the onboard system in the vehicle.

[0080] In some embodiments, after the roadside end collects image data and radar data in the road section where the vehicle is traveling, the image data and radar data can be fused to obtain fused data, and the fused data can be sent to the cloud. The roadside end can also include a roadside computing unit, and each sensor can send the collected perception data to the roadside computing unit through the protocol corresponding to each sensor. The roadside computing unit fuses the various types of perception data received to obtain fused data, and sends the fused data to the cloud through a standard network protocol.

[0081] The vehicle system can also determine the status of the cloud. When the status of the cloud is normal, the vehicle system can send vehicle status data to the cloud. The cloud stores a variety of pre-trained driving models locally, and the driving models corresponding to different road sections are usually different. The input of the driving model is various perception data and vehicle status data collected by the roadside end, and the output is the driving plan. The perception data and vehicle status data are processed by the driving model to obtain a driving plan that meets the real-time environment of the vehicle. The driving plan includes avoidance or parking, the lane the vehicle is traveling in when avoiding, the speed of the vehicle, etc.

[0082] Step S210: sending the motion model to the vehicle-mounted system so that the vehicle-mounted system analyzes and processes the motion model to obtain a second driving plan.

[0083] In the event of an abnormal state in the cloud, the roadside terminal can send the motion model to the vehicle system. Since the motion model is constantly updated, the current motion model has the highest accuracy. After receiving the motion model, the vehicle system analyzes and processes the motion model through its own computing power to obtain the optimal driving plan.

[0084] In the method for determining a driving plan in an embodiment of the present application, when the state of the cloud is normal, the roadside end sends perception data to the cloud, and the cloud processes the perception data through a pre-trained driving model to obtain a driving plan, and sends the driving plan to the vehicle-mounted system. In the case of an abnormal state of the cloud, that is, when the cloud loses its coordination ability, the roadside end can generate a motion model based on the perception data, and send the motion model to the vehicle-mounted system. The vehicle-mounted system can analyze and process the motion model to obtain a driving plan. It can be seen that the embodiment of the present application reduces the dependence on the cloud, and the vehicle-mounted system in the vehicle end can still obtain a better driving plan to avoid congestion and accidents.

[0085] See also Figure 3 , Figure 3 This is another flow chart of the driving plan determination method in the embodiment of the present application, which is applied to the vehicle-mounted system in the vehicle and may include the following steps:

[0086] Step S302: Send the vehicle status data to the roadside end, so that the roadside end can train and generate a motion model based on the collected perception data and vehicle status data.

[0087] Step S304, determining whether the cloud status is normal.

[0088] If the cloud status is normal, execute step S306. If the cloud status is abnormal,

[0089] Step S306, sending the vehicle status data to the cloud, so that the cloud processes the perception data and vehicle status data received from the roadside end through a pre-trained driving model to obtain a first driving plan.

[0090] Step S308, receiving the first driving plan sent by the cloud.

[0091] Step S310: receiving a motion model sent by a roadside terminal.

[0092] Step S312: Analyze and process the motion model to obtain a second driving plan.

[0093] The driving plan determination method of the embodiment of the present application uses the powerful computing power of the cloud to obtain the driving plan when the cloud is in a normal state, and the vehicle-mounted system directly receives the driving plan from the cloud. When the cloud is in an abnormal state, the roadside terminal and the vehicle-mounted system generate the driving plan, which realizes the self-control of the vehicle-side terminal and the roadside terminal, reduces the dependence on the cloud, and avoids congestion and accidents.

[0094] See also Figure 4 , Figure 4 This is an interactive flow chart of the driving plan determination method in the embodiment of the present application, which may include the following steps:

[0095] Step S402: The roadside end collects the perception data of the road section on which the vehicle is traveling.

[0096] Step S404: The roadside determines whether the status of the cloud is normal.

[0097] When the cloud status is normal, execute step S406; when the cloud status is abnormal, execute step S418.

[0098] Step S406: The roadside terminal sends the sensing data to the cloud.

[0099] Step S408: The vehicle-mounted system determines whether the status of the cloud is normal.

[0100] When the status of the cloud is normal, step S410 is executed; when the status of the cloud is abnormal, the vehicle status data is not sent to the cloud.

[0101] Step S410: The vehicle system sends vehicle status data to the cloud.

[0102] In step S412, the cloud processes the perception data and vehicle status data through a pre-trained driving model to obtain a first driving plan.

[0103] Step S414: the cloud sends a first driving plan to the onboard system in the vehicle.

[0104] Step S416: The vehicle-mounted system sends the vehicle status data to the roadside end.

[0105] Step S418: Generate a motion model based on the perception data and vehicle status data training.

[0106] Step S420: sending the motion model to the vehicle-mounted system.

[0107] Step S422: The vehicle-mounted system analyzes and processes the motion model to obtain a second driving plan.

[0108] Above Figure 3 and Figure 4 For the specific process in the embodiment, see Figure 2 The description in the embodiments is sufficient and will not be repeated here.

[0109] It should be noted that although the steps of the method in the present application are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0110] Corresponding to the above method embodiment, the present application embodiment also provides a driving plan determination device. Figure 5 , Figure 5 This is a schematic diagram of a driving plan determination device in an embodiment of the present application, which is applied to a roadside end. The driving plan determination device 500 includes:

[0111] The perception data collection module 501 is used to collect the perception data of the road section where the vehicle is traveling;

[0112] The sensing data sending module 502 is used to send the sensing data to the cloud when the cloud is in a normal state, so that the cloud processes the sensing data and the vehicle state data received from the vehicle-mounted system through a pre-trained driving model to obtain a first driving plan, and sends the first driving plan to the vehicle-mounted system in the vehicle;

[0113] A motion model generation module 503, used for training and generating a motion model based on the perception data and the vehicle state data received from the vehicle system;

[0114] The motion model sending module 504 is used to send the motion model to the vehicle-mounted system when the cloud status is abnormal, so that the vehicle-mounted system analyzes and processes the motion model to obtain a second driving plan.

[0115] Optionally, the motion model generation module 503 is specifically used to obtain the section information of the road section on which the vehicle is traveling and the traffic condition information of the road section on which the vehicle is traveling from the perception data when the status of the cloud is abnormal; determine the traffic control plan that matches the section information; and train and generate the motion model based on the traffic control plan, the traffic condition information of the road section on which the vehicle is traveling, and the vehicle status data received from the vehicle-mounted system.

[0116] Optionally, the perception data acquisition module 501 is specifically used to collect image data and radar data in the road section where the vehicle is traveling;

[0117] The perception data sending module 502 is specifically used to fuse the image data and the radar data to obtain fused data, and send the fused data to the cloud.

[0118] See also Figure 6 , Figure 6 This is another structural diagram of a driving plan determination device in an embodiment of the present application, which is applied to an on-board system in a vehicle. The driving plan determination device 600 includes:

[0119] The vehicle status data sending module 601 is used to send the vehicle status data to the cloud when the cloud is in a normal state, so that the cloud processes the perception data received from the roadside terminal and the vehicle status data through a pre-trained driving model to obtain a first driving plan;

[0120] A driving plan receiving module 602 is used to receive a first driving plan sent by the cloud;

[0121] The vehicle status data sending module 601 is further used to send the vehicle status data to the roadside end, so that the roadside end can train and generate a motion model based on the collected perception data and the vehicle status data;

[0122] The motion model receiving module 603 is used to receive the motion model sent by the roadside end when the state of the cloud is abnormal;

[0123] The driving plan generating module 604 is used to analyze and process the motion model to obtain a second driving plan.

[0124] The specific details of each module or unit in the above device have been described in detail in the corresponding method, so they will not be repeated here.

[0125] The present application also provides a driving plan determination system. Figure 7 , the driving plan determination system 700 includes: an on-board system 701 in the vehicle, a roadside terminal 702 and a cloud 703;

[0126] The vehicle-mounted system 701 is used to send the vehicle status data to the roadside end, and when the status in the cloud is normal, send the vehicle status data to the cloud;

[0127] The roadside terminal 702 is used to collect the perception data of the road section where the vehicle is traveling, train and generate a motion model based on the perception data and the vehicle status data, and send the motion model to the vehicle system when the status of the cloud is abnormal; and send the perception data to the cloud when the status of the cloud is normal;

[0128] The cloud 703 is used to process the perception data and the vehicle state data through a pre-trained driving model to obtain a first driving plan, and send the first driving plan to the vehicle system;

[0129] The vehicle-mounted system 701 is used to analyze and process the motion model to obtain a second driving plan.

[0130] Optionally, the roadside end 702 is specifically used to obtain the section information of the road section on which the vehicle is traveling and the traffic condition information of the road section on which the vehicle is traveling from the perception data when the status of the cloud is abnormal; determine the traffic control plan that matches the section information; and train and generate a motion model based on the traffic control plan, the traffic condition information of the road section on which the vehicle is traveling, and the vehicle status data.

[0131] Optionally, the roadside end 702 may include: a camera, a radar, and a roadside computing unit;

[0132] A camera, used to collect image data of the road section on which the vehicle is traveling;

[0133] Radar, used to collect radar data on the road section where the vehicle is traveling;

[0134] The roadside computing unit is used to fuse the image data and radar data to obtain fused data and send the fused data to the cloud.

[0135] The specific details of each device in the above system have been described in detail in the corresponding method, so they will not be repeated here.

[0136] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0137] In an embodiment of the present application, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned driving plan determination method is implemented.

[0138] It should be noted that the computer-readable storage medium shown in the present application may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, radio frequency, etc., or any suitable combination of the above.

[0139] In an embodiment of the present application, a computer program product is also provided. When the computer program product is run on a computer, the computer executes the above-mentioned driving plan determination method.

[0140] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0141] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining a driving plan, characterized in that: Applied to the roadside end, the method comprises: Collecting perception data on the road section where the vehicle is traveling; When the state of the cloud is normal, sending the perception data to the cloud, so that the cloud processes the perception data and the vehicle state data received from the vehicle system through a pre-trained driving model to obtain a first driving plan, and sending the first driving plan to the vehicle system; A motion model is generated based on the perception data and the vehicle status data received from the vehicle system, and when the cloud status is abnormal, the motion model is sent to the vehicle system so that the vehicle system analyzes and processes the motion model to obtain a second driving plan.

2. The method according to claim 1, characterized in that The training and generating of the motion model based on the perception data and the vehicle state data received from the vehicle-mounted system comprises: Acquire the road section information of the road section on which the vehicle is traveling and the traffic condition information of the road section on which the vehicle is traveling from the perception data; Determine a traffic control plan that matches the road section information; A motion model is trained and generated based on the traffic control plan, the traffic condition information of the road section on which the vehicle is traveling, and the vehicle status data received from the on-board system.

3. The method according to claim 1, characterized in that: The collecting of the perception data on the road section traveled by the vehicle includes: Collect image data and radar data on the road section where the vehicle is traveling; The sending the sensing data to the cloud comprises: The image data and the radar data are fused to obtain fused data, and the fused data is sent to the cloud.

4. A method for determining a driving plan, characterized in that: Applied to an on-board system in a vehicle, the method comprises: When the state of the cloud is normal, the vehicle state data is sent to the cloud, so that the cloud processes the perception data received from the roadside terminal and the vehicle state data through a pre-trained driving model to obtain a first driving plan; receiving the first driving plan sent by the cloud; Sending the vehicle status data to a roadside terminal, so that the roadside terminal trains and generates a motion model according to the collected perception data and the vehicle status data; In case of abnormal state of the cloud, receiving the motion model sent by the roadside end; The motion model is analyzed and processed to obtain a second driving plan.

5. A driving plan determination device, characterized in that: Applied to the roadside, including: A perception data collection module is used to collect perception data on the road section where the vehicle is traveling; a perception data sending module, configured to send the perception data to the cloud when the cloud is in a normal state, so that the cloud processes the perception data and the vehicle state data received from the vehicle-mounted system through a pre-trained driving model to obtain a first driving plan, and send the first driving plan to the vehicle-mounted system; A motion model generation module, used for training and generating a motion model based on the perception data and the vehicle state data received from the vehicle-mounted system; The motion model sending module is used to send the motion model to the vehicle-mounted system when the state of the cloud is abnormal, so that the vehicle-mounted system analyzes and processes the motion model to obtain a second driving plan.

6. A driving plan determination device, characterized in that: The on-board systems used in vehicles include: A vehicle status data sending module, used for sending the vehicle status data to the cloud when the cloud is in a normal state, so that the cloud processes the perception data received from the roadside terminal and the vehicle status data through a pre-trained driving model to obtain a first driving plan; A driving plan receiving module, used for receiving the first driving plan sent by the cloud; The vehicle status data sending module is further used to send the vehicle status data to the roadside end, so that the roadside end trains and generates a motion model according to the collected perception data and the vehicle status data; A motion model receiving module, used for receiving the motion model sent by the roadside end when the cloud state is abnormal; The driving plan generating module is used to analyze and process the motion model to obtain a second driving plan.

7. A driving plan determination system, characterized in that: include: Onboard systems in vehicles, roadside devices, and the cloud; The vehicle-mounted system is used to send the vehicle status data to the roadside end, and when the status in the cloud is normal, send the vehicle status data to the cloud; The roadside end is used to collect the perception data in the road section where the vehicle is traveling, train and generate a motion model based on the perception data and the vehicle status data, and send the motion model to the vehicle-mounted system when the status of the cloud is abnormal; and send the perception data to the cloud when the status of the cloud is normal; The cloud is used to process the perception data and the vehicle status data through a pre-trained driving model to obtain a first driving plan, and send the first driving plan to the vehicle-mounted system; The vehicle-mounted system is used to analyze and process the motion model to obtain a second driving plan.

8. The system according to claim 7, characterized in that The roadside end is specifically used to obtain the road section information of the road section on which the vehicle is traveling and the traffic condition information of the road section on which the vehicle is traveling from the perception data; Determine a traffic control plan that matches the road section information; A motion model is trained and generated based on the traffic control plan, the traffic condition information of the road section on which the vehicle is traveling, and the vehicle status data.

9. The system according to claim 7, characterized in that The roadside end includes: a camera, a radar and a roadside computing unit; The camera is used to collect image data of the road section on which the vehicle is traveling; The radar is used to collect radar data on the road section where the vehicle is traveling; The roadside computing unit is used to fuse the image data and the radar data to obtain fused data, and send the fused data to the cloud.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 3 or the method according to claim 4 is implemented.

Images