Vehicle control method, apparatus, device, medium, and product

Abstract

The application relates to a vehicle control method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: firstly, acquiring obstacle information and road information collected by a vehicle perception device, wherein the vehicle perception device comprises a camera, a millimeter wave radar, a laser radar and an ultrasonic wave radar; then, planning a global path of the vehicle based on a high-precision map and a global satellite navigation system; next, determining a current vehicle speed and a current driving path based on the camera according to the obstacle information and the road information; and finally, adjusting lateral control and longitudinal control of the vehicle according to the global path, the current driving path, the current vehicle speed and the road information. The method provided by the application can determine the demand of the vehicle by acquiring the obstacle information, the road information, the global path, the vehicle speed and the current driving path in the driving process of the vehicle in real time, so as to analyze the demand of the vehicle in real time.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a vehicle control method, device, computer equipment, storage medium, and computer program product. Background Technology

[0002] With the development of intelligent driving technology, in order to better realize vehicle automation, it is necessary to develop intelligent driving software according to requirements.

[0003] Existing methods for developing intelligent driving software involve grouping systems, processes, and data, and establishing formal and visual requirements analysis models to organize the static and dynamic requirements of the software from different perspectives, thereby designing and developing the software. However, this method is very complex and can undergo significant changes when requirements change, making it difficult for the developed software to perform real-time analysis of constantly changing requirements. Summary of the Invention

[0004] Therefore, it is necessary to provide a vehicle control method, device, computer equipment, computer-readable storage medium, and computer program product that can analyze vehicle demand in real time to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides a vehicle control method, the method comprising:

[0006] Obstacle information and road information collected by vehicle sensing devices, including cameras, millimeter-wave radar, lidar, and ultrasonic radar;

[0007] Based on high-precision maps and the global satellite navigation system, the vehicle's global path is planned;

[0008] Based on the camera, and according to the obstacle information and the road information, the current vehicle speed and current driving path are determined;

[0009] The vehicle's lateral and longitudinal control are adjusted based on the global path, the current driving path, the current vehicle speed, and the road information.

[0010] In one embodiment, the planning of the vehicle's global path based on high-precision maps and a global satellite navigation system includes:

[0011] Determine whether the vehicle can acquire the high-precision map;

[0012] If the vehicle can acquire the high-precision map, then determine whether the signal of the global satellite navigation system is normal;

[0013] If the signal of the global satellite navigation system is normal, the vehicle's current location information is obtained based on the high-precision map and the global satellite navigation system.

[0014] Obtain vehicle origin and destination information;

[0015] Based on the high-precision map, the vehicle's global path is planned according to the vehicle's current location information, the vehicle's starting point information, and the vehicle's ending point information.

[0016] In one embodiment, after determining whether the vehicle can acquire the high-precision map, the method further includes:

[0017] If the vehicle cannot obtain the high-precision map, then obtain the vehicle's reference driving direction, the vehicle's previous position information, and the vehicle's acceleration.

[0018] Based on differential positioning technology, the current position information of the vehicle is determined according to the vehicle's reference driving direction, the vehicle's previous position information, and the vehicle's acceleration.

[0019] In one embodiment, after determining whether the signal of the global navigation satellite system is normal, the method further includes:

[0020] If the signal of the global satellite navigation system is abnormal, real-time point cloud data around the vehicle is obtained based on the lidar and inertial navigation system.

[0021] The vehicle location information is obtained by comparing the real-time point cloud data with the corresponding point cloud data in the point cloud map.

[0022] In one embodiment, determining the current vehicle speed and current travel path based on the camera, according to the obstacle information and the road information, includes:

[0023] Based on the obstacle information and the road information, predict the movement path of the obstacle;

[0024] Based on the camera, acquire the vehicle's current driving scene data;

[0025] The current vehicle speed and the current driving path are determined based on the vehicle's current driving scenario data, the movement path of the obstacle, and the road information.

[0026] In one embodiment, the method further includes:

[0027] Obtain vehicle driving faults;

[0028] The vehicle driving faults are classified according to preset fault types, which include vehicle perception faults, vehicle positioning faults, vehicle decision-making and planning faults, and vehicle control faults.

[0029] Based on the classification results, a preset fault handling method corresponding to each preset fault type is adopted to handle the vehicle driving fault. The preset fault handling method includes controlling the vehicle to decelerate, controlling the vehicle's functions to degrade, and controlling the vehicle to stop driving.

[0030] Secondly, this application also provides a vehicle control device, the device comprising:

[0031] The acquisition module is used to acquire obstacle information and road information collected by the vehicle sensing device, which includes a camera, millimeter-wave radar, lidar and ultrasonic radar.

[0032] The planning module is used to plan the vehicle's global path based on high-precision maps and the Global Navigation Satellite System;

[0033] The determination module is used to determine the current vehicle speed and current driving path based on the camera, the obstacle information, and the road information;

[0034] The adjustment module is used to adjust the lateral and longitudinal control of the vehicle based on the global path, the current driving path, the current vehicle speed, and the road information.

[0035] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the methods in any of the above embodiments.

[0036] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the methods in any of the above embodiments.

[0037] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the methods in any of the above embodiments.

[0038] The aforementioned vehicle control method, device, computer equipment, storage medium, and computer program product first acquire obstacle and road information collected by vehicle sensing devices, including cameras, millimeter-wave radar, lidar, and ultrasonic radar. Then, based on high-precision maps and a global satellite navigation system, a global path for the vehicle is planned. Next, based on the camera and obstacle and road information, the current vehicle speed and current driving path are determined. Finally, based on the global path, current driving path, current vehicle speed, and road information, the lateral and longitudinal control of the vehicle are adjusted. The method provided in this application can determine the vehicle's needs by acquiring obstacle information, road information, global path, vehicle speed, and current driving path in real time during vehicle operation, thereby enabling real-time analysis of vehicle needs. Attached Figure Description

[0039] Figure 1 This is a diagram illustrating the application environment of a vehicle control method in one embodiment.

[0040] Figure 2 This is a flowchart illustrating a vehicle control method in one embodiment;

[0041] Figure 3 This is a flowchart illustrating a global path planning method in one embodiment;

[0042] Figure 4 Here is a flowchart of a vehicle control method in another embodiment;

[0043] Figure 5 This is a structural block diagram of a vehicle control device in one embodiment;

[0044] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0046] The vehicle control method provided in this application embodiment can be applied to, for example, Figure 1 The application environment shown above includes a vehicle controller 102 and a vehicle sensing device 104. The vehicle controller 102 acquires obstacle information and road information collected by the vehicle sensing device 104. The vehicle sensing device includes a camera, millimeter-wave radar, lidar, and ultrasonic radar.

[0047] In one embodiment, such as Figure 2 As shown, a vehicle control method is provided, which is applied to... Figure 1 Taking the vehicle controller in the example, the explanation includes the following steps:

[0048] S202. Obtain obstacle and road information collected by vehicle sensing devices, including cameras, millimeter-wave radar, lidar, and ultrasonic radar.

[0049] The vehicle controller interprets different driving scenarios by acquiring image information from cameras; it detects static and dynamic obstacles in the current driving direction by acquiring video streams from cameras, and extracts lanes for ordinary roads and highways, thus recognizing and detecting drivable areas in the current driving direction; the vehicle controller can also recognize and judge traffic signs on the road ahead by acquiring video streams from cameras, and detect the slope and inclination angle of the road ahead.

[0050] The vehicle controller uses information from millimeter-wave radar to classify and identify obstacles ahead, and filters out false alarms, thereby determining the type, location, and speed of the obstacles.

[0051] The vehicle controller acquires point cloud information collected by the LiDAR and segments and stitches the point cloud to measure the position, size, and speed of obstacles. At the same time, the vehicle controller can also detect the drivable area in the direction of vehicle travel based on the point cloud information and detect the lane edge in the direction of travel ahead.

[0052] In parking scenarios, the vehicle controller acquires the distance measurement results of ultrasonic radar on obstacles around the vehicle that pose a potential collision risk, thereby providing parking accuracy.

[0053] After acquiring obstacle and road information collected by the vehicle sensing devices, the vehicle controller transmits the information collected by each vehicle sensing device to the perception fusion software. The perception fusion software performs fusion analysis on this information to determine the drivable area in the vehicle's driving direction and the accurate obstacle information under a single coordinate.

[0054] S204. Based on high-precision maps and the global satellite navigation system, the system plans the global path for vehicles.

[0055] The vehicle controller first determines the vehicle's current location based on whether it can acquire a high-precision map and whether the GPS signal is normal. Specifically, if the vehicle controller can acquire a high-precision map and the GPS signal is normal, it obtains the vehicle's current location and precise information about the vicinity of the vehicle based on the high-precision map and the GPS signal. If the vehicle controller can acquire a high-precision map but the GPS signal is abnormal, it acquires real-time point cloud data of the vehicle's surroundings based on LiDAR and inertial navigation system, and obtains the vehicle's location information by comparing the real-time point cloud data with the corresponding point cloud data in the point cloud map. If the vehicle controller cannot acquire a high-precision map, it determines the vehicle's location based on differential positioning and inertial navigation information.

[0056] After determining the vehicle's location information, the vehicle controller plans the vehicle's globally optimal route based on the location information, the vehicle's starting point information, the vehicle's ending point information, and map information.

[0057] S206. Based on the camera, the current vehicle speed and current driving path are determined according to obstacle information and road information.

[0058] The vehicle controller predicts the trajectory of dynamic obstacles in the vehicle's driving direction based on obstacle information, road information, and scene information collected by cameras. Based on the scene information and the predicted obstacle trajectory, it makes lane-level behavior decisions for the vehicle. Finally, based on the results of the behavior decisions, it plans the speed and path of the actions the vehicle is about to take according to the current road conditions.

[0059] S208. Adjust the vehicle's lateral and longitudinal control based on the global path, current driving path, current vehicle speed, and road information.

[0060] The vehicle controller automatically adjusts the lateral and longitudinal control of the vehicle based on the current vehicle status and road conditions, and tracks the input trajectory through multi-level closed-loop vehicle control.

[0061] The vehicle controller also determines the vehicle's functional requirements based on obstacle information, road information, global planning, vehicle speed, vehicle travel path, lateral and longitudinal control, and vehicle fault information, and uploads these functional requirements to the terminal. At the same time, the terminal also acquires the non-functional requirements during vehicle operation, including reliability, ease of use, efficiency, maintainability, and portability. Finally, the R&D personnel analyze the functional and non-functional requirements to design and develop intelligent driving software.

[0062] In the aforementioned vehicle control method, obstacle and road information collected by vehicle sensing devices, including cameras, millimeter-wave radar, lidar, and ultrasonic radar, is first acquired. Then, based on high-precision maps and a global satellite navigation system, the vehicle's global path is planned. Next, based on the camera and obstacle and road information, the current vehicle speed and current driving path are determined. Finally, based on the global path, current driving path, current speed, and road information, the vehicle's lateral and longitudinal control are adjusted. The method provided in this application can determine the vehicle's needs by acquiring obstacle information, road information, global path, vehicle speed, and current driving path in real time during the vehicle's driving process, thereby enabling real-time analysis of vehicle needs.

[0063] In some embodiments, such as Figure 3 As shown, Figure 3 This is a flowchart illustrating a global path planning method in one embodiment. Based on a high-precision map and a global navigation satellite system (GNSS), the method plans a global path for a vehicle, including: determining whether the vehicle can acquire a high-precision map; if the vehicle can acquire a high-precision map, determining whether the GNSS signal is normal; if the GNSS signal is normal, acquiring the vehicle's current location information based on the high-precision map and the GNSS; acquiring the vehicle's starting point information and ending point information; and planning the vehicle's global path based on the high-precision map, the vehicle's current location information, the vehicle's starting point information, and the vehicle's ending point information.

[0064] In this step, the vehicle's starting point and ending point information are entered into the vehicle controller in advance by staff.

[0065] The method provided in this step can more accurately plan the global path by using the vehicle's current location information, vehicle origin information, and vehicle destination information.

[0066] In some embodiments, after determining whether the vehicle can acquire a high-precision map, the method further includes: if the vehicle cannot acquire a high-precision map, acquiring the vehicle's reference driving direction, the vehicle's previous position information, and the vehicle's acceleration; and determining the vehicle's current position information based on differential positioning technology, according to the vehicle's reference driving direction, the vehicle's previous position information, and the vehicle's acceleration.

[0067] In this step, differential positioning technology is a positioning technology in the global satellite navigation system. Its principle is that the user station receives the correction data sent by the reference station and corrects the measurement results of the user station according to the correction data.

[0068] The method provided in this step determines the vehicle's current location information based on differential positioning technology, making the positioning results more accurate.

[0069] In some embodiments, after determining whether the signal of the global navigation satellite system is normal, the method further includes: if the signal of the global navigation satellite system is abnormal, acquiring real-time point cloud data around the vehicle based on lidar and inertial navigation system; and acquiring vehicle location information by comparing the real-time point cloud data with the corresponding point cloud data in the point cloud map.

[0070] In this step, the vehicle controller acquires real-time point cloud data around the vehicle and compares the real-time point cloud data with the pre-processed point cloud map to obtain the initial value of the vehicle's position. Then, the backend optimizes and corrects the vehicle's position to obtain a higher-precision vehicle positioning.

[0071] The method provided in this step, through comparison of point cloud data, can provide accuracy in vehicle positioning.

[0072] In some embodiments, determining the current vehicle speed and current driving path based on the camera, obstacle information, and road information includes: predicting the movement path of the obstacle based on the obstacle information and road information; acquiring the current driving scene data of the vehicle based on the camera; and determining the current vehicle speed and current driving path based on the current driving scene data of the vehicle, the movement path of the obstacle, and road information.

[0073] In this step, after determining the current vehicle speed and current driving path, the vehicle controller determines the vehicle's driving trajectory based on the current speed and current driving path, and optimizes the determined driving trajectory to ensure the smoothness and feasibility of the driving trajectory.

[0074] The method provided in this step determines the vehicle's trajectory based on the current speed and current driving path, which can save fuel consumption.

[0075] In some embodiments, the method further includes: acquiring vehicle driving faults; classifying vehicle driving faults according to preset fault types, the preset fault types including vehicle perception faults, vehicle positioning faults, vehicle decision-making and planning faults, and vehicle control faults; and, based on the classification results, using a preset fault handling method corresponding to each preset fault type to handle the vehicle driving faults, the preset fault handling methods including controlling vehicle deceleration, controlling vehicle function degradation, and controlling vehicle to stop driving.

[0076] In this step, vehicle perception faults include sensor hardware failure, sensor hardware signal distortion, sensor obstruction, low visibility due to rain, snow, fog, or smoke, false or missed detection of obstacles, false or missed detection of lane lines, and unresponsive perception software. Vehicle positioning faults include satellite signal reception failure, abnormal high-precision map acquisition, and abnormal positioning results. Vehicle decision-making and planning faults include intelligent domain controller hardware failure, abnormal decision state machine state, trajectory result collision, trajectory planning timeout, and unresponsive decision-making and planning module. Vehicle control faults include bus communication failure, abnormal vehicle state, vehicle control module calculation cycle timeout, and abnormal trajectory tracking.

[0077] After acquiring a vehicle fault, the vehicle controller will handle the fault in different ways according to the fault type and fault level. For example, when the vehicle hardware fails, the controller will stop the vehicle from moving; when the sensor fails, the controller will degrade the relevant functions of the vehicle.

[0078] The method provided in this step can handle vehicle malfunctions in real time using different strategies, ensuring vehicle safety during operation.

[0079] In one embodiment, such as Figure 4 As shown, another vehicle control method is provided. Figure 4 The flowchart of this method is shown in this embodiment, which includes two parts: software functional requirements analysis and software non-functional requirements analysis.

[0080] Software functional requirements specify the software functions that developers must implement to complete designated tasks and meet business needs. Based on the functional modules of intelligent driving software, software functional requirements analysis can be mainly divided into: perception software functional requirements analysis, localization software functional requirements analysis, decision-making and planning software functional requirements analysis, vehicle control software functional requirements analysis, and fault handling software functional requirements analysis.

[0081] (1) Software Functional Requirements Analysis

[0082] 1) Perception Software Functional Requirements Analysis

[0083] Based on the sensor selection in the intelligent driving system solution, the functional requirements analysis of perception software mainly includes camera perception software, millimeter-wave radar perception software, lidar perception software, ultrasonic radar perception software, and perception fusion software.

[0084] Camera perception software functional requirements: The camera perception software interprets different driving scenarios based on image information captured by the camera; it detects static and dynamic obstacles in the vehicle's direction of travel using the video stream captured by the camera, and extracts lane information for both ordinary roads and highways, enabling the identification and detection of drivable areas in the vehicle's direction of travel; the video stream captured by the camera can also identify and judge traffic signs on the road ahead and detect the slope and inclination angle of the road ahead. This provides support for subsequent decision-making and planning modules.

[0085] Millimeter-wave radar perception software functional requirements: The millimeter-wave radar perception software uses information fed back from the millimeter-wave radar to classify and identify obstacles ahead, filter false alarms, and determine the type, location, and speed of the obstacles.

[0086] Functional requirements of LiDAR perception software: The LiDAR perception software collects point cloud information through LiDAR, and completes the measurement of the position, size and speed of obstacles by segmenting and stitching the point cloud; completes the detection of drivable areas in the direction of travel; and completes the detection of lane edges in the direction of travel ahead.

[0087] Ultrasonic radar perception software functional requirements: In parking scenarios, use ultrasonic radar around the vehicle to measure the distance to obstacles with potential collision risks, thereby providing parking accuracy.

[0088] Perception fusion software functional requirements: Perception fusion software integrates information from different sources to obtain the drivable area in the direction of vehicle travel and accurate obstacle information in a single coordinate system.

[0089] 2) Location Software Functional Requirements Analysis

[0090] Based on the positioning method determined in the intelligent driving system solution, the functional requirements analysis of the positioning software mainly includes high-precision map fusion positioning software, integrated navigation positioning software, and laser SLAM positioning software.

[0091] Functional requirements for high-precision map fusion positioning software: The high-precision map fusion positioning software is used in application scenarios such as highways and fixed-point parking. It obtains the current location and nearby accurate information by fusing GNSS-RTK (Global Navigation Satellite System) with high-precision maps for subsequent decision-making and planning.

[0092] Functional requirements for integrated navigation and positioning software: When high-precision maps are unavailable, the location should be determined using GNSS-RTK differential positioning and IMU inertial navigation information.

[0093] Functional requirements of laser SLAM positioning software: Real-time point cloud data around the vehicle is obtained by fusing lidar and IMU. The initial position value is obtained by comparing the real-time point cloud with a pre-processed point cloud map. The vehicle position is then corrected by backend optimization to obtain a higher accuracy vehicle positioning. It is suitable for general roads and highways where there are high-precision maps but GNSS signals are interfered with.

[0094] 3) Functional Requirements Analysis of Decision Planning Software

[0095] The functional requirements analysis of decision planning software mainly includes global path planning software, prediction software, behavioral decision-making software, and action planning software.

[0096] Global path planning software functional requirements: Based on location information, externally input start and end point information, and map information, plan the optimal global route to complete all task points.

[0097] Predictive software functional requirements: Utilize the fusion results of obstacle information, road information, and scene information from the perception software to predict the dynamic obstacle trajectory in the vehicle's driving direction for subsequent path planning.

[0098] Functional requirements for behavioral decision-making software: Based on the vehicle's current driving scenario and real-time road information combined with obstacle prediction results, make lane-level behavioral decisions for the vehicle.

[0099] Motion planning software functional requirements: Based on the results of behavioral decisions, the software should plan the speed and path of the action to be taken according to the current road conditions, form a trajectory, and optimize it to ensure smoothness and feasibility. At the same time, the trajectory should take into account fuel efficiency and timeliness.

[0100] 4) Functional Requirements Analysis of Vehicle Control Software

[0101] The functional requirements analysis for vehicle control software mainly includes trajectory tracking software.

[0102] Trajectory tracking software: Based on the input of the decision-making software, combined with the current vehicle status and road conditions, it automatically adjusts the vehicle's lateral and longitudinal control, and achieves tracking of the input trajectory through multi-level closed-loop vehicle control.

[0103] 5) Functional Requirements Analysis of Fault Handling Software

[0104] The functional requirements analysis of fault handling software mainly includes fault detection software for perception, fault detection software for location, fault detection software for decision planning, fault detection software for vehicle control, and fault handling software.

[0105] Perception Fault Detection Software: Monitors and detects hardware and software faults in the perception component. Fault types include: sensor hardware failure, sensor hardware signal distortion, sensor obstruction, low visibility due to rain, snow, fog, or smoke, false or missed detection of obstacles, false or missed detection of lane lines, and unresponsive perception software.

[0106] Location fault detection software: Monitors and detects hardware and software faults in the location component. Fault types include: satellite signal reception failure, high-precision map acquisition anomaly, and abnormal location results.

[0107] Decision planning fault detection software: Monitors and detects hardware and software faults in the decision planning part. Fault types include: intelligent domain controller hardware faults, decision state machine state abnormality faults, trajectory result collision faults, trajectory planning timeout faults, decision planning module unresponsive faults, etc.

[0108] Vehicle control fault detection software: monitors and detects hardware and software faults in the vehicle control system. Fault types include: bus communication faults, abnormal vehicle status, vehicle control module calculation cycle timeout, trajectory tracking abnormalities, etc.

[0109] Fault handling software: The fault handling section is used to ensure the safety of the vehicle when a fault occurs. The fault handling strategy will adopt different handling methods according to the fault type and fault level, including deceleration strategy due to processing timeout, function degradation strategy due to partial sensor failure, and stopping strategy due to hardware failure.

[0110] (2) Software Non-functional Requirements Analysis

[0111] Non-functional requirements of software define the various characteristics that developers must implement while simultaneously fulfilling the software's functionalities. These non-functional requirements primarily include reliability, usability, efficiency, maintainability, and portability.

[0112] Reliability: Intelligent driving software needs to be reliable, which is mainly reflected in software maturity, fault tolerance, recoverability, and compliance with reliability.

[0113] Usability: Intelligent driving software needs to be easy to use, which is mainly reflected in the software's ease of understanding, ease of learning, ease of operation, and compliance with usability requirements.

[0114] Efficiency: Intelligent driving software needs to be efficient, mainly reflected in the software's time characteristics, resource utilization, and compliance with efficiency requirements.

[0115] Maintainability: Intelligent driving software needs to be maintainable, which is mainly reflected in the software's ease of analysis, ease of modification, stability, ease of testing, and compliance with maintainability requirements.

[0116] Portability: Intelligent driving software needs to be portable, which is mainly reflected in the software's adaptability, ease of installation, coexistence, ease of replacement, and portability compliance.

[0117] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0118] Based on the same inventive concept, this application also provides a vehicle control device for implementing the vehicle control method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more vehicle control device embodiments provided below can be found in the limitations of the vehicle control method described above, and will not be repeated here.

[0119] In one embodiment, such as Figure 5 As shown, a vehicle control device 500 is provided, including: an acquisition module 501, a planning module 502, a determination module 503, and an adjustment module 504, wherein:

[0120] The acquisition module 501 is used to acquire obstacle information and road information collected by the vehicle sensing device, which includes a camera, millimeter-wave radar, lidar and ultrasonic radar.

[0121] Planning module 502 is used to plan the global path of the vehicle based on high-precision maps and the Global Navigation Satellite System.

[0122] The determination module 503 is used to determine the current vehicle speed and the current driving path based on the camera, the obstacle information, and the road information.

[0123] The adjustment module 504 is used to adjust the lateral and longitudinal control of the vehicle based on the global path, the current driving path, the current vehicle speed, and the road information.

[0124] In some embodiments, the planning module 502 is further configured to: determine whether the vehicle can acquire the high-precision map; if the vehicle can acquire the high-precision map, determine whether the signal of the global navigation satellite system is normal; if the signal of the global navigation satellite system is normal, acquire the vehicle's current location information based on the high-precision map and the global navigation satellite system; acquire the vehicle's starting point information and the vehicle's ending point information; and plan the vehicle's global path based on the high-precision map, according to the vehicle's current location information, the vehicle's starting point information, and the vehicle's ending point information.

[0125] In some embodiments, the vehicle control device 500 is specifically used to: if the vehicle cannot obtain the high-precision map, obtain the vehicle's reference driving direction, the vehicle's previous position information, and the vehicle's acceleration; and determine the vehicle's current position information based on differential positioning technology, according to the vehicle's reference driving direction, the vehicle's previous position information, and the vehicle's acceleration.

[0126] In some embodiments, the vehicle control device 500 is further configured to: if the signal of the global satellite navigation system is abnormal, acquire real-time point cloud data around the vehicle based on the lidar and inertial navigation system; and acquire the vehicle location information by comparing the real-time point cloud data with the corresponding point cloud data in the point cloud map.

[0127] In some embodiments, the determining module 503 is further configured to: predict the movement path of the obstacle based on the obstacle information and the road information; acquire the current driving scene data of the vehicle based on the camera; and determine the current vehicle speed and the current driving path based on the current driving scene data of the vehicle, the movement path of the obstacle, and the road information.

[0128] In some embodiments, the vehicle control device 500 is further configured to: acquire vehicle driving faults; classify the vehicle driving faults according to preset fault types, the preset fault types including vehicle perception faults, vehicle positioning faults, vehicle decision-making and planning faults, and vehicle control faults; and based on the classification results, process the vehicle driving faults using preset fault processing methods corresponding to each preset fault type, the preset fault processing methods including controlling vehicle deceleration, controlling vehicle function degradation, and controlling vehicle to stop driving.

[0129] Each module in the aforementioned vehicle control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0130] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores vehicle driving data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When the computer program is executed by the processor, it implements a vehicle control method.

[0131] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0132] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: acquiring obstacle information and road information collected by a vehicle sensing device, the vehicle sensing device including a camera, millimeter-wave radar, lidar, and ultrasonic radar; planning a global path for the vehicle based on a high-precision map and a global satellite navigation system; determining the current vehicle speed and current driving path based on the camera, the obstacle information, and the road information; and adjusting the lateral and longitudinal control of the vehicle based on the global path, the current driving path, the current vehicle speed, and the road information.

[0133] In one embodiment, the process of a processor executing a computer program to plan a global path for a vehicle based on a high-precision map and a global navigation satellite system includes: determining whether the vehicle can acquire the high-precision map; if the vehicle can acquire the high-precision map, determining whether the signal of the global navigation satellite system is normal; if the signal of the global navigation satellite system is normal, acquiring the vehicle's current location information based on the high-precision map and the global navigation satellite system; acquiring the vehicle's starting point information and the vehicle's ending point information; and planning the vehicle's global path based on the high-precision map, according to the vehicle's current location information, the vehicle's starting point information, and the vehicle's ending point information.

[0134] In one embodiment, after the processor executes the computer program to determine whether the vehicle can acquire the high-precision map, the method further includes: if the vehicle cannot acquire the high-precision map, acquiring the vehicle's reference driving direction, the vehicle's previous position information, and the vehicle's acceleration; and determining the vehicle's current position information based on differential positioning technology, according to the vehicle's reference driving direction, the vehicle's previous position information, and the vehicle's acceleration.

[0135] In one embodiment, after the processor executes the computer program to determine whether the signal of the global navigation satellite system is normal, the method further includes: if the signal of the global navigation satellite system is abnormal, acquiring real-time point cloud data around the vehicle based on the lidar and inertial navigation system; and acquiring the vehicle location information by comparing the real-time point cloud data with the corresponding point cloud data in the point cloud map.

[0136] In one embodiment, the processor executing a computer program to determine the current vehicle speed and current driving path based on the camera, obstacle information, and road information includes: predicting the movement path of an obstacle based on the obstacle information and road information; acquiring current driving scene data of the vehicle based on the camera; and determining the current vehicle speed and current driving path based on the current driving scene data of the vehicle, the movement path of the obstacle, and the road information.

[0137] In one embodiment, the method implemented by the processor when executing the computer program further includes: acquiring a vehicle driving fault; classifying the vehicle driving fault according to a preset fault type, the preset fault type including vehicle perception fault, vehicle positioning fault, vehicle decision-making and planning fault, and vehicle control fault; and, based on the classification result, processing the vehicle driving fault using a preset fault processing method corresponding to each preset fault type, the preset fault processing method including controlling vehicle deceleration, controlling vehicle function degradation, and controlling vehicle to stop driving.

[0138] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon. When executed by a processor, the computer program performs the following steps: acquiring obstacle information and road information collected by vehicle sensing devices, the vehicle sensing devices including a camera, millimeter-wave radar, lidar, and ultrasonic radar; planning a global path for the vehicle based on a high-precision map and a global satellite navigation system; determining the current vehicle speed and current driving path based on the camera, the obstacle information, and the road information; and adjusting the lateral and longitudinal control of the vehicle based on the global path, the current driving path, the current vehicle speed, and the road information.

[0139] In one embodiment, the computer program, when executed by a processor, plans a global path for a vehicle based on a high-precision map and a global navigation satellite system (GNSS), including: determining whether the vehicle can acquire the high-precision map; if the vehicle can acquire the high-precision map, determining whether the GNSS signal is normal; if the GNSS signal is normal, acquiring the vehicle's current location information based on the high-precision map and the GNSS; acquiring the vehicle's starting point information and ending point information; and planning the vehicle's global path based on the high-precision map, the vehicle's current location information, the vehicle's starting point information, and the vehicle's ending point information.

[0140] In one embodiment, after the computer program is executed by the processor to determine whether the vehicle can acquire the high-precision map, it further includes: if the vehicle cannot acquire the high-precision map, acquiring the vehicle's reference driving direction, the vehicle's previous position information, and the vehicle's acceleration; and determining the vehicle's current position information based on differential positioning technology, according to the vehicle's reference driving direction, the vehicle's previous position information, and the vehicle's acceleration.

[0141] In one embodiment, after the computer program is executed by the processor to determine whether the signal of the global navigation satellite system is normal, it further includes: if the signal of the global navigation satellite system is abnormal, acquiring real-time point cloud data around the vehicle based on the lidar and inertial navigation system; and acquiring the vehicle location information by comparing the real-time point cloud data with the corresponding point cloud data in the point cloud map.

[0142] In one embodiment, the computer program, when executed by a processor, determines the current vehicle speed and current driving path based on the camera, obstacle information, and road information, including: predicting the movement path of an obstacle based on the obstacle information and road information; acquiring current driving scene data of the vehicle based on the camera; and determining the current vehicle speed and current driving path based on the current driving scene data of the vehicle, the movement path of the obstacle, and the road information.

[0143] In one embodiment, the method implemented when the computer program is executed by the processor further includes: acquiring a vehicle driving fault; classifying the vehicle driving fault according to a preset fault type, the preset fault type including vehicle perception fault, vehicle positioning fault, vehicle decision-making and planning fault, and vehicle control fault; and, based on the classification result, processing the vehicle driving fault using a preset fault processing method corresponding to each preset fault type, the preset fault processing method including controlling vehicle deceleration, controlling vehicle function degradation, and controlling vehicle to stop driving.

[0144] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps: acquiring obstacle information and road information collected by vehicle sensing devices, said vehicle sensing devices including cameras, millimeter-wave radar, lidar, and ultrasonic radar; planning a global path for the vehicle based on a high-precision map and a global satellite navigation system; determining the current vehicle speed and current driving path based on the camera, the obstacle information, and the road information; and adjusting the lateral and longitudinal control of the vehicle based on the global path, the current driving path, the current vehicle speed, and the road information.

[0145] In one embodiment, the computer program, when executed by a processor, plans a global path for a vehicle based on a high-precision map and a global navigation satellite system (GNSS), including: determining whether the vehicle can acquire the high-precision map; if the vehicle can acquire the high-precision map, determining whether the GNSS signal is normal; if the GNSS signal is normal, acquiring the vehicle's current location information based on the high-precision map and the GNSS; acquiring the vehicle's starting point information and ending point information; and planning the vehicle's global path based on the high-precision map, the vehicle's current location information, the vehicle's starting point information, and the vehicle's ending point information.

[0146] In one embodiment, after the computer program is executed by the processor to determine whether the vehicle can acquire the high-precision map, it further includes: if the vehicle cannot acquire the high-precision map, acquiring the vehicle's reference driving direction, the vehicle's previous position information, and the vehicle's acceleration; and determining the vehicle's current position information based on differential positioning technology, according to the vehicle's reference driving direction, the vehicle's previous position information, and the vehicle's acceleration.

[0147] In one embodiment, after the computer program is executed by the processor to determine whether the signal of the global navigation satellite system is normal, it further includes: if the signal of the global navigation satellite system is abnormal, acquiring real-time point cloud data around the vehicle based on the lidar and inertial navigation system; and acquiring the vehicle location information by comparing the real-time point cloud data with the corresponding point cloud data in the point cloud map.

[0148] In one embodiment, the computer program, when executed by a processor, determines the current vehicle speed and current driving path based on the camera, obstacle information, and road information, including: predicting the movement path of an obstacle based on the obstacle information and road information; acquiring current driving scene data of the vehicle based on the camera; and determining the current vehicle speed and current driving path based on the current driving scene data of the vehicle, the movement path of the obstacle, and the road information.

[0149] In one embodiment, the method implemented when the computer program is executed by the processor further includes: acquiring a vehicle driving fault; classifying the vehicle driving fault according to a preset fault type, the preset fault type including vehicle perception fault, vehicle positioning fault, vehicle decision-making and planning fault, and vehicle control fault; and, based on the classification result, processing the vehicle driving fault using a preset fault processing method corresponding to each preset fault type, the preset fault processing method including controlling vehicle deceleration, controlling vehicle function degradation, and controlling vehicle to stop driving.

[0150] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0151] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0152] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0153] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A vehicle control method, characterized in that, The method includes: Obstacle information and road information collected by vehicle sensing devices, including cameras, millimeter-wave radar, lidar, and ultrasonic radar; Based on high-precision maps and the global satellite navigation system, the vehicle's global path is planned; Based on the obstacle information, road information, and scene information collected by the camera, the trajectory of dynamic obstacles in the vehicle's driving direction is predicted. Based on the scene information and the predicted trajectory, a lane-level behavior decision is made for the vehicle. Based on the result of the behavior decision, speed planning and path planning are performed for the actions that the vehicle is about to take according to the current road conditions to obtain the current vehicle speed and current driving path. Based on the global path, the current driving path, the current vehicle speed, and the road information, adjust the vehicle's lateral and longitudinal control. Based on the obstacle information, road information, global planning, vehicle speed, vehicle driving path, lateral and longitudinal control, and vehicle fault information, the functional requirements of the vehicle are determined, and the functional requirements are uploaded to the terminal. This allows R&D personnel to design and develop intelligent driving software based on the functional requirements and the non-functional requirements obtained by the terminal during vehicle operation. The functional requirements include perception software functional requirements, positioning software functional requirements, decision planning software functional requirements, vehicle control software functional requirements, and fault handling software functional requirements. The non-functional requirements include reliability, ease of use, efficiency, maintainability, and portability. The method also includes: after obtaining a high-precision map, if the signal of the global satellite navigation system is abnormal, then based on the lidar and inertial navigation system, real-time point cloud data around the vehicle is obtained; The initial position of the vehicle is obtained by comparing real-time point cloud data with a pre-processed point cloud map, and then the vehicle position is corrected by backend optimization to obtain the vehicle location.

2. The method according to claim 1, characterized in that, The process of planning a vehicle's global path based on high-precision maps and a global satellite navigation system includes: Determine whether the vehicle can acquire the high-precision map; If the vehicle can acquire the high-precision map, then determine whether the signal of the global satellite navigation system is normal; If the signal of the global satellite navigation system is normal, the vehicle's current location information is obtained based on the high-precision map and the global satellite navigation system. Obtain vehicle origin and destination information; Based on the high-precision map, the vehicle's global path is planned according to the vehicle's current location information, the vehicle's starting point information, and the vehicle's ending point information.

3. The method according to claim 2, characterized in that, After determining whether the vehicle can acquire the high-precision map, the method further includes: If the vehicle cannot obtain the high-precision map, then obtain the vehicle's reference driving direction, the vehicle's previous position information, and the vehicle's acceleration. Based on differential positioning technology, the current position information of the vehicle is determined according to the vehicle's reference driving direction, the vehicle's previous position information, and the vehicle's acceleration.

4. The method according to claim 1, characterized in that, The method further includes: Obtain vehicle driving faults; The vehicle driving faults are classified according to preset fault types, which include vehicle perception faults, vehicle positioning faults, vehicle decision-making and planning faults, and vehicle control faults. Based on the classification results, a preset fault handling method corresponding to each preset fault type is adopted to handle the vehicle driving fault. The preset fault handling method includes controlling the vehicle to decelerate, controlling the vehicle's functions to degrade, and controlling the vehicle to stop driving.

5. A vehicle control device, characterized in that, The device includes: The acquisition module is used to acquire obstacle information and road information collected by the vehicle sensing device, which includes a camera, millimeter-wave radar, lidar and ultrasonic radar. The planning module is used to plan the vehicle's global path based on high-precision maps and the Global Navigation Satellite System; The determination module is used to predict the trajectory of dynamic obstacles in the vehicle's driving direction based on the obstacle information, road information, and scene information collected by the camera, and to make lane-level behavior decisions for the vehicle based on the scene information and the predicted trajectory. Based on the result of the behavior decisions, the module performs speed planning and path planning for the actions that the vehicle is about to take according to the current road conditions to obtain the current vehicle speed and current driving path. The adjustment module is used to adjust the lateral and longitudinal control of the vehicle based on the global path, the current driving path, the current vehicle speed, and the road information; and to determine the functional requirements of the vehicle based on obstacle information, road information, global planning, vehicle speed, vehicle driving path, lateral and longitudinal control, and vehicle fault information, and upload the functional requirements to the terminal so that developers can design and develop intelligent driving software based on the functional requirements and the non-functional requirements of the vehicle during driving obtained by the terminal. The functional requirements include perception software functional requirements, positioning software functional requirements, decision planning software functional requirements, vehicle control software functional requirements, and fault handling software functional requirements. The non-functional requirements include reliability, ease of use, efficiency, maintainability, and portability. The device is further configured to: after acquiring a high-precision map, if the signal of the global satellite navigation system is abnormal, acquire real-time point cloud data around the vehicle based on the lidar and inertial navigation system; compare the real-time point cloud data with the pre-processed point cloud map to obtain the initial position value of the vehicle, and then correct the vehicle position through back-end optimization to obtain the vehicle positioning.

6. The apparatus according to claim 5, characterized in that, The planning module is also used to determine whether the vehicle can obtain the high-precision map; if the vehicle can obtain the high-precision map, it determines whether the signal of the global satellite navigation system is normal; if the signal of the global satellite navigation system is normal, it obtains the vehicle's current location information based on the high-precision map and the global satellite navigation system. Obtain vehicle origin and destination information; Based on the high-precision map, the vehicle's global path is planned according to the vehicle's current location information, the vehicle's starting point information, and the vehicle's ending point information.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images