Operation escape method and device for automatic driving vehicle

Abstract

The invention relates to the technical field of automatic driving, in particular to an automatic driving vehicle operation escape method and device. The method comprises the steps of receiving an online car-hailing order; sending an order execution instruction to the vehicle end; the vehicle end is used for executing an automatic driving action based on the order execution instruction; receiving traffic parameter information and traffic event information sent by the roadside equipment side; receiving automatic driving data sent by the vehicle end; if the traffic event information comprises abnormal parking information, fusing the traffic parameter information and the automatic driving data to obtain fused data; and based on the fusion data, generating an out-of-trap strategy, and outputting an out-of-trap instruction to the vehicle end, so that the vehicle recovers to a normal state. The operation efficiency and safety of the unmanned vehicle in a complex traffic environment are realized, automatic escape of the vehicle in an abnormal parking state is realized, the manpower configuration for maintaining the operation of the vehicle is reduced, and the manpower operation cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method and device for autonomous driving vehicle operation escape. Background Art

[0002] With the development of autonomous driving technology, autonomous vehicles, such as the self-driving taxi Robotaxi, have gradually become an important part of urban transportation. However, in complex urban traffic environments, unmanned vehicles may encounter various operational obstacles, such as traffic congestion, road construction, and bad weather. In order to deal with these situations that may lead to abnormal parking, the role of cloud cabin safety officer is configured in unmanned operations. The cloud cabin safety officer is mainly responsible for real-time monitoring of the vehicle status and timely intervention in risky situations. When the vehicle is abnormal or fails, or other situations require takeover, the system will automatically cut out the vehicle screen and the cloud cabin safety officer will take over; takeover caused by vehicle abnormalities must also be recorded and feedback. Although this remote monitoring and manual intervention solution improves safety, it also has certain limitations.

[0003] Remote monitoring and manual intervention solutions have disadvantages such as delay risk, resource intensiveness and unpredictability. First, there may be delays in remote communications, which can be fatal in an emergency, affecting the response speed and effectiveness. Second, the solution requires well-trained operators and equipment support, involving high training and maintenance costs, and increasing the operational burden. Finally, the effectiveness of the solution depends on the operating experience and reaction ability of the safety officer, resulting in unstable intervention effects and difficulty in ensuring that the expected safety standards can be achieved every time.

[0004] Therefore, there is an urgent need for a method that can enable unmanned autonomous driving vehicles to automatically escape from trouble, so as to reduce the dependence of autonomous driving vehicles on cloud cabin safety officers during operation. Summary of the invention

[0005] In view of this, the embodiments of the present application provide a method and device for escaping from distress in the operation of an autonomous driving vehicle, which can realize automatic escape from distress in the autonomous driving vehicle, does not rely on cloud cabin safety officers, and reduces manpower allocation.

[0006] A first aspect of an embodiment of the present application provides a method for escaping from a difficult situation in an autonomous driving vehicle operation, which is applied to a service end, and the method includes:

[0007] Receive online ride-hailing orders;

[0008] Sending an order execution instruction to the vehicle end; the vehicle end is used to perform an automatic driving action based on the order execution instruction;

[0009] Receive traffic parameter information and traffic event information sent by roadside equipment;

[0010] Receive the autonomous driving driving data sent by the vehicle;

[0011] If the traffic event information includes abnormal parking information, fusing the traffic parameter information and the automatic driving driving data to obtain fused data;

[0012] Based on the fused data, an escape strategy is generated, and an escape instruction is output to the vehicle end to restore the vehicle to a normal state.

[0013] The embodiment of the present application ensures efficient order processing and task allocation by centrally managing online car-hailing orders on the service side and executing instructions on the vehicle side. The method not only receives traffic parameter information and traffic event information sent by roadside equipment, but also collects autonomous driving driving data on the vehicle side, and performs fusion processing when abnormal parking information is detected to generate fused data. An escape strategy is generated based on the fused data and an escape instruction is output to the vehicle side, so that the vehicle can quickly return to normal. This method realizes the operating efficiency and safety of unmanned vehicles in complex traffic environments, realizes the automatic escape of vehicles in abnormal parking states, reduces the manpower allocation used to maintain vehicle operations, and reduces manpower operating costs.

[0014] In one embodiment, the autonomous driving driving data is acquired through vehicle-mounted sensors, and the roadside equipment includes roadside sensors deployed on the roadside.

[0015] The embodiment of the present application obtains autonomous driving driving data through on-board sensors and obtains vehicle surrounding environment data through roadside sensors, thereby ensuring the diversity and reliability of data sources, thereby making subsequent judgments based on the data more accurate and providing a more reliable basis for decision-making in complex and changeable urban environments.

[0016] In one embodiment, the fusing the traffic parameter information and the autonomous driving driving data to obtain fused data includes:

[0017] Performing time series synchronization on the traffic parameter information and the autonomous driving driving data;

[0018] Synchronizing the spatial coordinates of the traffic parameter information and the autonomous driving driving data;

[0019] Extracting environmental features from the synchronized traffic parameter information, and extracting motion features from the synchronized autonomous driving driving data;

[0020] The environmental features and the motion features are fused using a filtering algorithm to obtain the fused data.

[0021] The embodiment of the present application ensures the temporal and spatial consistency of all data by performing time series synchronization and spatial coordinate synchronization processing on road state data and autonomous driving driving data, eliminating errors caused by asynchronous acquisition time or position differences of different sensors. In addition, by extracting environmental features and motion features from the synchronized data and fusing them using a filtering algorithm, the generated fused data has higher accuracy and reliability. This provides a reliable basis for subsequent abnormal parking cause analysis and escape strategies.

[0022] In one embodiment, generating an escape strategy based on the fused data includes:

[0023] Analyzing the cause of abnormal parking in combination with the fused data, the cause including at least one of vehicle failure, traffic accident, and pedestrian interference;

[0024] If the abnormal parking is caused by vehicle failure, a remote assistance request signal is output;

[0025] If the cause of the abnormal parking is a traffic accident, generating an escape strategy corresponding to the traffic accident;

[0026] If the cause of the abnormal parking is pedestrian interference, an escape strategy corresponding to the pedestrian interference is generated.

[0027] The embodiment of the present application analyzes the causes of abnormal parking (such as vehicle failure, traffic accident, pedestrian interference) and generates corresponding escape strategies for different causes. The ability to deal with different types of abnormalities is improved. Through pre-set strategies, the system can take the most appropriate measures immediately after detecting abnormal parking to ensure that the vehicle quickly resumes normal operation, ensuring the safety and comfort of passengers, while reducing unnecessary waiting time.

[0028] In one embodiment, the combining of fusion data to analyze the cause of abnormal parking includes:

[0029] Inputting the fused data into a pre-trained abnormal parking analysis model to analyze the cause of abnormal parking of the vehicle;

[0030] Outputting a prediction result, wherein the prediction result is at least one of a vehicle failure, a traffic accident, and a pedestrian interference;

[0031] The abnormal parking analysis model is trained based on traffic parameter information and autonomous driving driving data corresponding to the vehicle in different abnormal parking states.

[0032] The embodiment of the present application identifies the cause of abnormal parking by using a pre-trained abnormal parking analysis model. The model is trained based on the traffic parameter information corresponding to the vehicle in different abnormal parking states and the autonomous driving driving data, and can accurately distinguish between multiple causes such as vehicle failure, traffic accidents, and pedestrian interference. The analysis model obtained through training can immediately identify the specific cause of abnormal parking after it is detected, thereby quickly generating a corresponding escape strategy. This method not only improves the intelligence level of the system, but also enhances the ability to respond to emergencies, ensuring that the vehicle can take the most appropriate measures for different situations.

[0033] In one embodiment, if the cause of the abnormal parking is a traffic accident, generating an escape strategy corresponding to the traffic accident includes:

[0034] If the cause of the abnormal parking is a traffic accident, the severity level of the traffic accident is evaluated;

[0035] According to the evaluation result, any one of a detour instruction, an emergency stop instruction, and a remote assistance request instruction is sent to the vehicle end.

[0036] The embodiment of the present application sends a detour instruction, an emergency stop instruction, or a remote assistance request instruction to the vehicle end according to the traffic accident severity level assessment result. The actual traffic conditions are taken into consideration, unnecessary detours or waiting are avoided, and the efficiency of escape is improved. The flexible response strategy not only improves the response speed of the system, but also ensures the safety and comfort of passengers, especially providing more reliable decision support in complex and changing urban environments.

[0037] In one embodiment, if the abnormal parking is caused by pedestrian interference, generating an escape strategy corresponding to the pedestrian interference includes:

[0038] If the cause of the abnormal parking is pedestrian interference, a deceleration instruction or a stop waiting instruction is sent to the vehicle end according to the distance between the pedestrian and the vehicle.

[0039] In response to pedestrian interference, the embodiment of the present application proposes sending a deceleration command or a stop and wait command to the vehicle end according to the distance between the pedestrian and the vehicle. This method not only improves the intelligence level of the system, but also enhances the ability to respond to emergencies, ensuring that the vehicle can take the most appropriate measures for different situations. By monitoring the distance between pedestrians and vehicles in real time, the system can issue a deceleration command or a stop and wait command in a timely manner to ensure the safe passage of pedestrians. This method not only improves the flexibility and adaptability of the system, but also ensures the safety and comfort of passengers.

[0040] A second aspect of the present application provides an autonomous driving vehicle operation escape device, which is applied to a server, and the device includes:

[0041] An autonomous vehicle operation module for receiving online ride-hailing orders;

[0042] The autonomous driving cloud module is used to send an order execution instruction to the vehicle end; the vehicle end is used to perform the autonomous driving action based on the order execution instruction;

[0043] The road network cloud module is used to receive the traffic parameter information and traffic event information sent by the roadside equipment, and when it is determined that the traffic event information includes abnormal parking information, send the abnormal parking information and traffic parameter information to the autonomous driving vehicle operation module;

[0044] The autonomous driving vehicle operation module is also used to receive the autonomous driving driving data sent by the vehicle side, the abnormal parking information and traffic parameter information sent by the road network cloud module, and fuse the traffic parameter information and the autonomous driving driving data to obtain fused data; based on the fused data, an escape strategy is generated, and an escape instruction is output to the vehicle side to restore the vehicle to a normal state.

[0045] In one embodiment, the autonomous driving cloud module is further used to:

[0046] Receive the autonomous driving driving data sent by the vehicle, store the autonomous driving driving data, and synchronize it to the autonomous driving vehicle operation module.

[0047] In one embodiment, the autonomous driving vehicle operation module includes:

[0048] An abnormal parking analysis module is used to analyze the cause of abnormal parking in combination with the fused data, wherein the cause includes at least one of vehicle failure, traffic accident, and pedestrian interference;

[0049] The escape strategy generation module is used to output a signal requesting remote assistance if the cause of the abnormal parking is a vehicle failure; to generate an escape strategy corresponding to the traffic accident if the cause of the abnormal parking is a traffic accident; and to generate an escape strategy corresponding to the pedestrian interference if the cause of the abnormal parking is pedestrian interference.

[0050] The third aspect of an embodiment of the present application provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device implements the method for autonomous driving vehicle operation escape as provided in the first aspect of an embodiment of the present application.

[0051] A fourth aspect of the embodiments of the present application provides a computer program product, including a computer program. When the computer program is executed, the method according to the first aspect of the embodiments of the present application is executed.

[0052] The first aspect of the embodiment of the present application provides an autonomous driving vehicle operation escape method, which ensures efficient order processing and task allocation by centrally managing online car-hailing orders on the service side and executing instructions on the vehicle side. This method not only receives traffic parameter information and traffic event information sent by roadside equipment, but also collects autonomous driving driving data on the vehicle side, and performs fusion processing when abnormal parking information is detected to generate fused data. An escape strategy is generated based on the fused data and an escape instruction is output to the vehicle side, so that the vehicle can quickly return to normal. This method realizes the operating efficiency and safety of unmanned vehicles in complex traffic environments, realizes the automatic escape of vehicles in abnormal parking states, reduces the manpower allocation used to maintain vehicle operations, and reduces manpower operating costs.

[0053] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 This is a flow chart of a method for escaping a difficult situation for an autonomous driving vehicle provided in one embodiment of the present application;

[0056] Figure 2 This is a flow chart of a method for escaping a difficult situation for an autonomous driving vehicle provided by another embodiment of the present application;

[0057] Figure 3 This is a flow chart of a method for escaping a difficult situation for an autonomous driving vehicle provided by another embodiment of the present application;

[0058] Figure 4 It is a schematic diagram of the structure of the automatic driving vehicle operation escape device provided in an embodiment of the present application;

[0059] Figure 5 This is a flow chart of a method for escaping a difficult situation for an autonomous driving vehicle provided by another embodiment of the present application;

[0060] Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0062] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0063] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0064] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0065] The method for autonomous driving vehicle operation escape provided by the embodiment of the present application can be executed by the server when running a computer program with corresponding functions. The server centrally manages online car-hailing orders and vehicle-side execution instructions, ensuring efficient order processing and task allocation. This method not only receives traffic parameter information and traffic event information sent by roadside equipment, but also collects autonomous driving driving data from the vehicle side, and performs fusion processing when abnormal parking information is detected to generate fused data. An escape strategy is generated based on the fused data and an escape instruction is output to the vehicle side, so that the vehicle can quickly return to normal. This method realizes the operating efficiency and safety of unmanned vehicles in complex traffic environments, realizes the automatic escape of vehicles in abnormal parking states, reduces the manpower allocation used to maintain vehicle operations, and reduces the manpower operation cost. .

[0066] In the application, the server can interact with the vehicle and roadside equipment. The server can be a cloud server or a service group formed by a group of interconnected independent servers.

[0067] like Figure 1 As shown, the method for escaping from a difficult situation of an autonomous driving vehicle provided in the embodiment of the present application includes the following steps S101 to S106:

[0068] Step S101, receiving an online car-hailing order;

[0069] In the application, the server can accept online taxi orders sent by users from user terminals (such as mobile phones, computers and other user terminals). The order information includes the starting point, end point, passenger information, etc.

[0070] Step S102: sending an order execution instruction to the vehicle side; the vehicle side is used to perform the automatic driving action based on the order execution instruction.

[0071] In the application, the server selects the most suitable available Robotaxi based on the order information, generates detailed execution instructions (such as driving route, estimated arrival time, and safety precautions), and sends the instructions to the vehicle-side autonomous driving system.

[0072] Step S103: receiving traffic parameter information and traffic event information sent by the roadside equipment.

[0073] In the application, roadside equipment (such as cameras, radars or traffic lights) collects traffic parameter information in real time, such as at least one of the following information: queue length, lane occupancy, vehicle spacing, average vehicle speed, headway, turning flow, vehicle spacing, etc., and sends it to the server.

[0074] In the application, the roadside equipment also detects traffic events, including at least one of abnormal parking, congestion, traffic accidents, pedestrian interference, etc., and sends them to the server, which can be the road network cloud module in the server.

[0075] Step S104: receiving the autonomous driving driving data sent by the vehicle.

[0076] In the application, vehicle-side sensors (such as GPS, IMU, cameras or lidar) collect the vehicle's own driving data (such as at least one of position, speed, acceleration, steering angle, collision signals, emergency braking indications, image data, and point cloud data) in real time and send it to the server.

[0077] Step S105: If the traffic event information includes abnormal parking information, the traffic parameter information and the automatic driving driving data are fused to obtain fused data.

[0078] In the application, the road network cloud module parses the traffic event information uploaded by the roadside equipment to determine whether there is abnormal parking information. If so, the traffic parameter information and the autonomous driving driving data are integrated to obtain fused data.

[0079] In the application, the time series and spatial coordinates of the above two types of data are first synchronized to ensure that all data have a unified time base and geographic location reference. Then, environmental features (such as the position of other vehicles, pedestrian dynamics, and traffic light status) and motion features (such as vehicle speed, acceleration, and steering angle) are extracted, and filtering algorithms are used to achieve deep fusion of multi-sensor data to obtain a more accurate understanding of the surrounding environment and assessment of vehicle operation status. The filtering algorithm can use Kalman filtering, particle filtering, etc.

[0080] Step S106: Generate an escape strategy based on the fused data, and output an escape instruction to the vehicle to restore the vehicle to a normal state.

[0081] In the application, the reasons for abnormal parking are analyzed based on the fused data, and corresponding escape instructions are generated and sent to the vehicle based on different reasons, such as changing lanes, detouring, emergency parking, requesting remote assistance, slowing down or stopping and waiting, to guide the vehicle to quickly return to normal.

[0082] In one embodiment, the autonomous driving driving data is obtained through vehicle-mounted sensors, and the roadside equipment includes roadside sensors deployed on the roadside.

[0083] The embodiment of the present application obtains autonomous driving driving data through on-board sensors and obtains vehicle surrounding environment data through roadside sensors, thereby ensuring the diversity and reliability of data sources, thereby making subsequent judgments based on the data more accurate and providing a more reliable basis for decision-making in complex and changeable urban environments.

[0084] In one embodiment, Figure 2 As shown, step S103 includes the following steps S201 to S204:

[0085] Step S201: synchronize the traffic parameter information and the autonomous driving driving data in time series.

[0086] Step S202: synchronize the spatial coordinates of the traffic parameter information and the autonomous driving driving data.

[0087] Step S203: extracting environmental features from the synchronized traffic parameter information, and extracting motion features from the synchronized automatic driving driving data.

[0088] Step S204: Use a filtering algorithm to fuse the environmental features and the motion features to obtain fused data.

[0089] In the application, adjust the timestamps of all data to synchronize the time series so that they are based on a unified time reference, eliminating errors caused by asynchronous collection time. Perform spatial coordinate synchronization through GPS coordinate matching to ensure the consistency of geographical locations of data from different sources. In addition to the above fusion methods, other fusion methods can also be used, such as assigning different weights to different data based on their importance, and then extracting features based on the weights. The embodiments of the present application do not limit the specific means of data fusion, and any method that can comprehensively consider the fusion of vehicle-side data and roadside data can be applied to the method.

[0090] The embodiment of the present application ensures the temporal and spatial consistency of all data by performing time series synchronization and spatial coordinate synchronization processing on road state data and autonomous driving driving data, eliminating errors caused by asynchronous acquisition time or position differences of different sensors. In addition, by extracting environmental features and motion features from the synchronized data and fusing them using a filtering algorithm, the generated fused data has higher accuracy and reliability. This provides a reliable basis for subsequent abnormal parking cause analysis and escape strategies.

[0091] In one embodiment, Figure 3 As shown, step S106 includes the following steps S301 to S304:

[0092] Step S301: Analyze the cause of abnormal parking in combination with the fused data, where the cause includes at least one of vehicle failure, traffic accident, and pedestrian interference;

[0093] Step S302: if the abnormal parking is caused by a vehicle failure, outputting a remote assistance request signal;

[0094] Step S303: if the cause of the abnormal parking is a traffic accident, generating an escape strategy corresponding to the traffic accident;

[0095] Step S304: If the cause of the abnormal parking is pedestrian interference, an escape strategy corresponding to the pedestrian interference is generated.

[0096] In the application, when the cause of abnormal parking is vehicle failure, it is considered that automatic escape is impossible and human intervention is required. At this time, no escape strategy is generated, but remote assistance is requested.

[0097] The embodiment of the present application analyzes the causes of abnormal parking (such as vehicle failure, traffic accident, pedestrian interference) and generates corresponding escape strategies for different causes. The ability to deal with different abnormalities is improved. Through pre-set strategies, the system can take the most appropriate measures immediately after detecting abnormal parking to ensure that the vehicle quickly resumes normal operation, ensuring the safety and comfort of passengers, while reducing unnecessary waiting time.

[0098] In one embodiment, step S301 includes the following steps S3011 and S3012:

[0099] Step S3011, inputting the fused data into a pre-trained abnormal parking analysis model to analyze the cause of abnormal parking of the vehicle;

[0100] Step S3012: outputting a prediction result, where the prediction result is at least one of a vehicle failure, a traffic accident, and a pedestrian interference;

[0101] Among them, the abnormal parking analysis model is trained based on the traffic parameter information and autonomous driving driving data corresponding to the vehicle in different abnormal parking conditions.

[0102] In the application, collect the operational data of vehicles under different types of abnormal parking conditions, such as abnormal parking, traffic accidents, pedestrian interference, etc. Detailed annotation of the data for each type of abnormal parking is performed to ensure that the model can distinguish different abnormal parking conditions. Extract key features from the annotated data, such as vehicle position changes, speed changes, collision signals, pedestrian positions, etc. Select a machine learning model suitable for multi-classification tasks, such as random forest, gradient boosted tree (GBDT), convolutional neural network (CNN), or recurrent neural network (RNN). Then use the annotated historical data to train the selected model to obtain a usable abnormal parking analysis model.

[0103] In the application, the fused data is input into the trained abnormal parking analysis model. The model can output specific prediction results, such as vehicle failure, traffic accident, and pedestrian interference.

[0104] The embodiment of the present application identifies the cause of abnormal parking by using a pre-trained abnormal parking analysis model. The model is trained based on the traffic parameter information corresponding to the vehicle in different abnormal parking states and the autonomous driving driving data, and can accurately distinguish between multiple causes such as vehicle failure, traffic accidents, and pedestrian interference. The analysis model obtained through training can immediately identify the specific cause of abnormal parking after it is detected, thereby quickly generating a corresponding escape strategy. This method not only improves the intelligence level of the system, but also enhances the ability to respond to emergencies, ensuring that the vehicle can take the most appropriate measures for different situations.

[0105] In one embodiment, if the cause of abnormal parking is a traffic accident, an escape strategy corresponding to the traffic accident is generated, including:

[0106] If the cause of the abnormal parking is a traffic accident, the severity level of the traffic accident is evaluated;

[0107] According to the evaluation results, any one of the following instructions, including detour instructions, emergency stop instructions, and remote assistance request instructions, is sent to the vehicle.

[0108] In the application, if the accident does not affect the passage of other lanes, it is judged as a minor accident, and a detour route is generated and a detour instruction is sent to enable the vehicle to quickly leave the accident area. If the accident affects multiple lanes but does not cause serious consequences, it is judged as a moderate accident, an emergency stop instruction is issued to ensure that the vehicle stops safely, and remote assistance is requested (such as the dispatch center or cloud cabin safety officer). If the accident involves major casualties and affects multiple lanes, an emergency stop instruction is immediately issued, remote assistance is requested, and the emergency alarm system is activated at the same time.

[0109] The embodiment of the present application sends a detour instruction, an emergency stop instruction, or a remote assistance request instruction to the vehicle end according to the traffic accident severity level assessment result. The actual traffic conditions are taken into consideration, unnecessary detours or waiting are avoided, and the efficiency of escape is improved. The flexible response strategy not only improves the response speed of the system, but also ensures the safety and comfort of passengers, especially providing more reliable decision support in complex and changing urban environments.

[0110] In one embodiment, if the cause of abnormal parking is pedestrian interference, an escape strategy corresponding to pedestrian interference is generated, including:

[0111] If the abnormal parking is caused by pedestrian interference, a deceleration command or a stop waiting command will be sent to the vehicle end according to the distance between the pedestrian and the vehicle.

[0112] In the application, the severity level of the accident (minor, moderate, severe) is assessed based on image data from the accident scene, collision signals, emergency braking indications and other information.

[0113] In the application, the risk of pedestrian activities is assessed based on the distance between pedestrians and vehicles. If a pedestrian is crossing the road but has not completely passed, a deceleration command is sent to reduce the vehicle speed to ensure a safe distance. If the pedestrian has safely passed or stopped moving, a continue driving command is sent to resume normal driving. If the pedestrian continues to interfere or the behavior is unpredictable, a stop and wait command is issued to ensure that the vehicle stops in a safe location until the pedestrian activity ends or the environment returns to normal. After the vehicle executes the escape command, the execution result is fed back to the server to further evaluate and optimize the escape strategy.

[0114] In the embodiment of the present application, for traffic accidents, by evaluating the severity of the accident, a detour instruction, an emergency stop instruction, or a remote assistance request instruction is selected. For pedestrian interference, a deceleration instruction or a stop and wait instruction is issued in a timely manner according to the distance between the pedestrian and the vehicle to ensure the safe passage of pedestrians. This method not only improves the intelligence level of the system, but also enhances the ability to respond to emergencies and ensures the safety of vehicles and pedestrians.

[0115] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0116] The embodiment of the present application also provides an autonomous driving vehicle operation escape device, which is used to execute the steps in the above autonomous driving vehicle operation escape method embodiment. The autonomous driving vehicle operation escape device can be a virtual appliance in an electronic device, which is run by a processor of the electronic device, or it can be the electronic device itself.

[0117] like Figure 4 As shown, the autonomous driving vehicle operation escape device 100 provided in the embodiment of the present application is applied to the service end, and can interact with the vehicle end 400 and the roadside equipment 300, including:

[0118] The autonomous driving vehicle operation module 101 is used to receive online car-hailing orders;

[0119] The autonomous driving cloud module 102 is used to send an order execution instruction to the vehicle end; the vehicle end is used to execute the autonomous driving action based on the order execution instruction;

[0120] The road network cloud module 103 is used to receive the traffic parameter information and traffic event information sent by the roadside equipment, and when it is determined that the traffic event information includes abnormal parking information, send the abnormal parking information and traffic parameter information to the autonomous driving vehicle operation module;

[0121] The autonomous driving vehicle operation module 101 is also used to receive the autonomous driving driving data sent by the vehicle side, the abnormal parking information and traffic parameter information sent by the road network cloud module, and fuse the traffic parameter information and the autonomous driving driving data to obtain fused data; based on the fused data, an escape strategy is generated, and an escape instruction is output to the vehicle side to restore the vehicle to a normal state.

[0122] The embodiment of the present application integrates the autonomous driving vehicle operation module, the autonomous driving cloud module and the road network cloud module, realizing the full process automated management from order processing to the output of escape instructions. The device is not only responsible for receiving and processing online car-hailing orders, but also undertakes key tasks such as data fusion, abnormal parking cause analysis, and escape strategy generation. By combining centralized management and distributed processing, the device significantly improves the system's integration and collaborative efficiency, ensures the smoothness and efficiency of the entire operation process, and improves user experience and service quality.

[0123] In one embodiment, the autonomous driving cloud module 102 is further used to:

[0124] Receive the autonomous driving driving data sent by the vehicle, store the autonomous driving driving data, and synchronize it to the autonomous driving vehicle operation module.

[0125] The embodiment of the present application receives and stores the autonomous driving driving data sent by the vehicle, and synchronizes it to the autonomous driving vehicle operation module. It ensures the real-time update and sharing of all relevant data, so that the operation module can make accurate judgments and decisions based on the latest data. Through the data management capabilities of the cloud module, it can better support the operation and management of large-scale fleets, improve the speed and accuracy of data processing, reduce the pressure of local storage and computing, and enhance the scalability and flexibility of the system.

[0126] In one embodiment, the autonomous driving vehicle operation module 101 includes:

[0127] An abnormal parking analysis module is used to analyze the causes of abnormal parking in combination with fused data, the causes including at least one of vehicle failure, traffic accident, and pedestrian interference;

[0128] The escape strategy generation module is used to output a signal requesting remote assistance if the cause of the abnormal parking is a vehicle failure; to generate an escape strategy corresponding to the traffic accident if the cause of the abnormal parking is a traffic accident; and to generate an escape strategy corresponding to pedestrian interference if the cause of the abnormal parking is pedestrian interference.

[0129] In the application, the autonomous vehicle operation escape device adopts the design concept of combining distributed microservice architecture and cloud computing platform. It consists of multiple modules and interacts through efficient data communication protocols (such as gRPC and HTTP / 2), ensuring low latency and high reliability of data transmission. The system adopts containerized deployment (such as Docker and Kubernetes), supports dynamic expansion and service redundancy, and improves the maintainability and availability of the system.

[0130] The autonomous driving vehicle operation module of the embodiment of the present application includes an abnormal parking analysis module and an escape strategy generation module. This modular design not only clearly divides the functional responsibilities of each part, but also improves the maintainability and scalability of the system. Each submodule focuses on a specific task, ensuring the professionalism and efficiency of the operation. Through close collaboration between modules, the system can quickly respond to various operating conditions, accurately judge and generate the best escape strategy, significantly improve the operational efficiency and safety of autonomous driving vehicles, and lay a solid foundation for future intelligent transportation systems.

[0131] like Figure 5 As shown, the embodiment of the present application also provides an autonomous driving vehicle operation escape method implemented by using the autonomous driving vehicle operation escape device 100, which specifically includes the following steps:

[0132] Step 1: The online car-hailing order is sent to the autonomous driving vehicle operation module.

[0133] Step 2: The autonomous driving vehicle operation module sends the order information to the autonomous driving cloud module.

[0134] Step 3: The autonomous driving cloud module sends an order execution instruction to the autonomous driving vehicle.

[0135] Step 4: The autonomous driving vehicle starts to execute the order.

[0136] Step 5: Car-mounted sensors perform data fusion.

[0137] Step 6: The autonomous driving vehicle starts autonomous driving.

[0138] Step 7: The autonomous driving vehicle uploads the desensitized autonomous driving driving data to the autonomous driving cloud module.

[0139] Step 8. The autonomous driving cloud module stores these data, and the autonomous driving vehicle operation module synchronizes the driving operation status of the autonomous driving vehicle (including autonomous driving driving data).

[0140] Step 9: The roadside equipment performs data fusion through roadside sensors, detects traffic parameters and traffic events, and sends the traffic parameters and traffic events to the road network cloud module.

[0141] Step 10: If the road network cloud module detects abnormal parking during a traffic incident, it will perform data desensitization processing and send it to the autonomous driving vehicle operation module.

[0142] Step 11: The abnormal parking analysis module of the autonomous driving vehicle operation module performs abnormal parking analysis.

[0143] Step 12: The escape strategy generation module generates an escape strategy based on the abnormal parking analysis results.

[0144] Step 13: After the escape strategy is generated, the autonomous driving vehicle operation module sends an escape instruction to the autonomous driving cloud module.

[0145] Step 14: The autonomous driving cloud module sends an escape command to the autonomous driving vehicle.

[0146] Step 15: After receiving the escape instruction, the autonomous driving vehicle starts to execute the escape operation.

[0147] Step 16: If the escape is successful, the process ends. If the escape fails, the data will be uploaded to the autonomous driving cloud module again to generate a new escape strategy.

[0148] The third aspect of an embodiment of the present application provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device implements the method for autonomous driving vehicle operation escape as provided in the first aspect of an embodiment of the present application.

[0149] In application, each module in the autonomous driving vehicle operation escape device can be a software program module, or it can be implemented through different logic circuits integrated in the processor, or it can be implemented through multiple distributed processors.

[0150] like Figure 6 As shown, the embodiment of the present application further provides an electronic device 200, including: at least one processor 201 ( Figure 6 Only one processor is shown in the figure), a memory 202, and a computer program 203 stored in the memory 202 and executable on at least one processor 201, wherein the processor 201 implements the steps in the above-mentioned various method embodiments when executing the computer program 203.

[0151] In applications, electronic devices may include, but are not limited to, processors and memories. Those skilled in the art will appreciate that Figure 6 The electronic device is merely an example and does not limit the electronic device, and may include more or less components than those shown in the figure, or may combine certain components, or may include different components.

[0152] In applications, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0153] In application, the memory may be an internal storage unit of an electronic device in some embodiments, such as a hard disk or memory of the electronic device. The memory may also be an external storage device of the electronic device in other embodiments, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory may also include both an internal storage unit of the electronic device and an external storage device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as program code of a computer program, etc. The memory may also be used to temporarily store data that has been output or is to be output.

[0154] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0155] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0156] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0157] An embodiment of the present application provides a computer program product, including a computer program. When the computer program product runs on an electronic device, the electronic device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0158] If the integrated unit 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 present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the device / electronic device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0159] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0160] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0161] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0162] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0163] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for escaping from a difficult situation when operating an autonomous driving vehicle, characterized in that: Applied to the server, the method includes: Receive online ride-hailing orders; Sending an order execution instruction to the vehicle end; the vehicle end is used to perform an automatic driving action based on the order execution instruction; Receive traffic parameter information and traffic event information sent by roadside equipment; Receive the autonomous driving driving data sent by the vehicle; If the traffic event information includes abnormal parking information, fusing the traffic parameter information and the automatic driving driving data to obtain fused data; Based on the fused data, an escape strategy is generated, and an escape instruction is output to the vehicle end to restore the vehicle to a normal state.

2. The method for escaping from a difficult situation by operating an autonomous driving vehicle according to claim 1, characterized in that: The autonomous driving driving data is obtained through vehicle-mounted sensors, and the roadside equipment includes roadside sensors deployed on the roadside.

3. The method for escaping from a difficult situation by operating an autonomous driving vehicle according to claim 1, characterized in that: The fusing the traffic parameter information and the autonomous driving driving data to obtain fused data includes: Performing time series synchronization on the traffic parameter information and the autonomous driving driving data; Synchronizing the spatial coordinates of the traffic parameter information and the autonomous driving driving data; Extracting environmental features from the synchronized traffic parameter information, and extracting motion features from the synchronized autonomous driving driving data; The environmental features and the motion features are fused using a filtering algorithm to obtain the fused data.

4. The method for escaping from a difficult situation by operating an autonomous driving vehicle according to claim 1, characterized in that: The step of generating an escape strategy based on the fused data includes: Analyzing the cause of abnormal parking in combination with the fused data, the cause including at least one of vehicle failure, traffic accident, and pedestrian interference; If the abnormal parking is caused by vehicle failure, a remote assistance request signal is output; If the cause of the abnormal parking is a traffic accident, generating an escape strategy corresponding to the traffic accident; If the cause of the abnormal parking is pedestrian interference, an escape strategy corresponding to the pedestrian interference is generated.

5. The method for escaping from a difficult situation by operating an autonomous driving vehicle according to claim 4, characterized in that: The combined fusion data is used to analyze the causes of abnormal parking, including: Inputting the fused data into a pre-trained abnormal parking analysis model to analyze the cause of abnormal parking of the vehicle; Outputting a prediction result, wherein the prediction result is at least one of a vehicle failure, a traffic accident, and a pedestrian interference; The abnormal parking analysis model is trained based on traffic parameter information and autonomous driving driving data corresponding to the vehicle in different abnormal parking states.

6. The method for escaping from a difficult situation by operating an autonomous driving vehicle according to claim 4, characterized in that: If the abnormal parking is caused by a traffic accident, generating an escape strategy corresponding to the traffic accident includes: If the cause of the abnormal parking is a traffic accident, the severity level of the traffic accident is evaluated; According to the evaluation result, any one of a detour instruction, an emergency stop instruction, and a remote assistance request instruction is sent to the vehicle end.

7. The method for escaping from a difficult situation by operating an autonomous driving vehicle according to claim 4, characterized in that: If the abnormal parking is caused by pedestrian interference, generating an escape strategy corresponding to the pedestrian interference includes: If the cause of the abnormal parking is pedestrian interference, a deceleration instruction or a stop waiting instruction is sent to the vehicle end according to the distance between the pedestrian and the vehicle.

8. An automatic driving vehicle operation escape device, characterized in that: Applied to the server, the device comprises: An autonomous vehicle operation module for receiving online ride-hailing orders; The autonomous driving cloud module is used to send an order execution instruction to the vehicle end; the vehicle end is used to perform the autonomous driving action based on the order execution instruction; The road network cloud module is used to receive the traffic parameter information and traffic event information sent by the roadside equipment, and when it is determined that the traffic event information includes abnormal parking information, send the abnormal parking information and traffic parameter information to the autonomous driving vehicle operation module; The autonomous driving vehicle operation module is also used to receive the autonomous driving driving data sent by the vehicle side, the abnormal parking information and traffic parameter information sent by the road network cloud module, and fuse the traffic parameter information and the autonomous driving driving data to obtain fused data; based on the fused data, an escape strategy is generated, and an escape instruction is output to the vehicle side to restore the vehicle to a normal state.

9. The automatic driving vehicle operation escape device according to claim 8, characterized in that: The autonomous driving cloud module is also used for: Receive the autonomous driving driving data sent by the vehicle, store the autonomous driving driving data, and synchronize it to the autonomous driving vehicle operation module.

10. The automatic driving vehicle operation escape device according to claim 8, characterized in that: The autonomous driving vehicle operation module includes: An abnormal parking analysis module is used to analyze the cause of abnormal parking in combination with the fused data, wherein the cause includes at least one of vehicle failure, traffic accident, and pedestrian interference; The escape strategy generation module is used to output a signal requesting remote assistance if the cause of the abnormal parking is a vehicle failure; to generate an escape strategy corresponding to the traffic accident if the cause of the abnormal parking is a traffic accident; and to generate an escape strategy corresponding to the pedestrian interference if the cause of the abnormal parking is pedestrian interference.

Images