A method, apparatus, electronic device, and storage medium for vehicle path planning.

Abstract

This application provides a vehicle path planning method, apparatus, electronic device, and storage medium. The method is applied to an intelligent driving domain controller and includes: acquiring global path information sent by the cockpit domain controller; comparing the real-time vehicle location information and real-time road environment information acquired by the intelligent driving domain controller with the global path information to obtain a road comparison result; if the road comparison result indicates a road deviation, determining a positioning deviation value, lane matching value, driving intention, and road legality value based on the real-time vehicle location information and real-time road environment information acquired by the intelligent driving domain controller; determining a comprehensive deviation confidence level based on the positioning deviation, lane matching value, driving intention, and road legality value; and determining whether to replan the global path information based on the confidence level corresponding to the comprehensive deviation confidence level.

Description

Technical Field

[0001] This application relates to the field of vehicle navigation technology, and more specifically, to a method, apparatus, electronic device, and storage medium for vehicle route planning. Background Technology

[0002] With the development of intelligent vehicles and the increasing collaboration among multiple systems, navigation information has become an essential tool for many users, and online in-vehicle navigation provides significant convenience. Navigation systems are typically integrated into the vehicle's cabin, providing travel guidance to users through the central control screen.

[0003] Because the GNSS and IMU components accessed by the cockpit domain controller are generally of standard performance level, when users miss intersections, take the wrong turn on or under overpasses, or go the wrong way on main or auxiliary roads, the vehicle navigation system is either limited by the resolution of the positioning components and cannot correct the mistake, or it needs to travel a considerable distance along an unknown route before recognizing the error and replanning a new navigation path. Due to slow navigation updates and relatively insufficient accuracy, users are prone to taking wrong turns and cannot quickly correct them, reducing travel efficiency. Summary of the Invention

[0004] The purpose of this application is to provide a vehicle path planning method, device, electronic device, and storage medium to improve the accuracy of navigation in intelligent driving of vehicles.

[0005] In a first aspect, the present invention provides a vehicle path planning method, applied to an intelligent driving domain controller, the method comprising: Obtain the global path information sent by the cockpit domain controller; The road comparison results are obtained by comparing the real-time vehicle location information, real-time road environment information and global path information obtained by the intelligent driving domain controller; If the road comparison result is a road deviation, the positioning deviation value, lane matching value, driving intention, and road legality value are determined based on the real-time vehicle location information and real-time road environment information obtained by the intelligent driving domain controller. The overall deviation confidence level is determined based on positioning deviation, lane matching value, driving intention, and road legality value. Based on the confidence level corresponding to the overall deviation confidence level, determine whether to replan the global path information.

[0006] In an optional implementation, a road comparison result is obtained by comparing the real-time vehicle location information, real-time road environment information, and global path information acquired by the intelligent driving domain controller, including: The road position deviation value is obtained by comparing the real-time vehicle location information obtained by the intelligent driving domain controller with the global path information; the real-time vehicle location information includes GNSS data and IMU data; The road scene deviation value is obtained by comparing the real-time road environment information obtained by the intelligent driving domain controller with the global path information. The real-time road environment information includes at least vehicle camera data, millimeter-wave radar data, and lidar data. The road comparison results are determined by the road location deviation value and the road scene deviation value.

[0007] In an optional implementation, the road comparison result is determined by the road position deviation value and the road scene deviation value, including: Determine whether the road position deviation exceeds the preset safety range, and determine whether the road scene deviation is less than the preset deviation value; If the road position deviation value exceeds the preset safety range and the road scene deviation value is less than the first preset deviation value, then the road comparison result is determined to be a road deviation. If the road location deviation value does not exceed the preset safety range and the road scene deviation value is less than the first preset deviation value, then the road comparison result is determined to be a positioning anomaly; wherein, the second preset deviation value is greater than the first preset deviation value; If the road location deviation exceeds the preset safety range and the road scene deviation is greater than the second preset deviation value, then the road comparison result is determined to be a perception anomaly.

[0008] In an optional implementation, the road comparison result is determined by the road position deviation value and the road scene deviation value, including: The weighted deviation value is obtained by weighting the road position deviation value and the road scene deviation value. If the weighted deviation value is greater than the target value, the road comparison result is determined to be a road deviation.

[0009] In an optional implementation, the comprehensive deviation confidence level is determined based on positioning deviation, lane matching value, driving intention, and road legality value, including: The overall deviation confidence level is obtained by weighting the positioning deviation, lane matching value, driving intention, and road legality value.

[0010] In an optional implementation, based on the confidence level corresponding to the comprehensive deviation confidence level, it is determined whether to replan the global path information, including: When the overall deviation confidence level is less than the first preset confidence level, the confidence level is considered to be severely deviated, indicating that the global path information needs to be replanned. When the overall deviation confidence level is greater than or equal to the first preset confidence level and less than the second preset confidence level, the confidence level is determined to be moderate deviation, a vehicle deviation risk warning is generated and provided to the user; When the overall deviation confidence level is greater than or equal to the second preset confidence level, the confidence level is determined to be slightly deviated, and it is determined that there is no need to replan the global path information.

[0011] In an optional implementation, it further includes: Determine whether the user's consent to the route replanning has been received; If so, then proceed with the step of replanning the global path information.

[0012] Secondly, the present invention provides a vehicle path planning device, the device comprising: The acquisition module obtains global path information sent by the cockpit domain controller; The comparison module compares the real-time vehicle location information, real-time road environment information, and global path information obtained by the intelligent driving domain controller to obtain the road comparison result; The analysis module determines the positioning deviation value, lane matching value, driving intention, and road legality value based on the real-time vehicle location information and real-time road environment information obtained by the intelligent driving domain controller if the road comparison result is a road deviation. The calculation module performs a weighted calculation on the positioning deviation, lane matching value, driving intention, and road legality value to obtain the comprehensive deviation confidence level; The planning module determines whether to replan the global path information based on the confidence level corresponding to the comprehensive deviation confidence level.

[0013] Thirdly, the present invention provides an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate via the bus. The machine-readable instructions are executed by the processor to perform the steps of the vehicle path planning method as described in any of the foregoing embodiments.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of a vehicle path planning method as described in any of the foregoing embodiments.

[0015] This application provides a vehicle path planning method, device, electronic device, and storage medium. The method is applied to an intelligent driving domain controller and includes: acquiring global path information sent by the cockpit domain controller; comparing the real-time vehicle location information, real-time road environment information, and global path information acquired by the intelligent driving domain controller to obtain a road comparison result; if the road comparison result indicates a road deviation, determining a positioning deviation value, lane matching value, driving intention, and road legality value based on the real-time vehicle location information and real-time road environment information acquired by the intelligent driving domain controller; determining a comprehensive deviation confidence level based on the positioning deviation, lane matching value, driving intention, and road legality value; and determining whether to replan the global path information based on the confidence level corresponding to the comprehensive deviation confidence level. By using multi-source perception and high-precision positioning from the intelligent driving domain controller to feed back into the cockpit navigation, real-time identification of route deviations, quantitative classification of confidence levels, and human-machine collaborative replanning are achieved, significantly improving the correction response speed, bridge / under-bridge recognition accuracy, and false trigger rate control. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A schematic diagram of the structure of a vehicle navigation replanning system provided in an embodiment of this application; Figure 2 A flowchart illustrating a vehicle path planning method provided in an embodiment of this application; Figure 3 A schematic diagram of a vehicle path planning method apparatus provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0019] Example 1 Figure 1 This is a schematic diagram of the structure of a vehicle navigation replanning system provided in an embodiment of this application. Figure 1 As shown in the figure, this application provides a vehicle that includes at least a driving domain controller and a cockpit domain controller.

[0020] The cockpit domain controller here can deploy navigation maps, providing users with online navigation map services based on the vehicle's GNSS and IMU. The cockpit domain controller can transmit global navigation path information and real-time dynamic information of the navigation map to the intelligent driving domain controller via Ethernet communication (for the integrated cockpit-driver domain controller, this is transmission between different modules within the same module).

[0021] The intelligent driving domain controller here receives all the vehicle's cameras (including at least one forward-facing 2-8 megapixel camera), LiDAR, intelligent driving GNSS, and IMU (which can be built into the domain controller / sensor or externally deployed in the vehicle).

[0022] The intelligent driving domain controller has software modules deployed inside to perceive the road environment and accurately locate the vehicle. According to the destination set in the global navigation path information received from the cockpit domain controller, it realizes real-time dynamic path planning and has the ability to control the whole vehicle, realizing longitudinal (forward, reverse, parking) and lateral (lane change, overtaking, left and right turns at intersections, etc.). Of course, if the intelligent driving system's vehicle control function is not activated, the intelligent driving system runs silently inside but does not execute vehicle control commands.

[0023] When the intelligent driving domain controller perceives the road environment through sensors such as cameras and LiDAR, and compares it with the real-time dynamic information sent by the cockpit domain controller, it determines that the vehicle has deviated from the navigation route when a discrepancy is found. Combining this with the accessed high-precision positioning GNSS and IMU modules, if the navigation route deviates significantly, it sends a command to the navigation module inside the cockpit domain controller to replan the navigation route, while simultaneously prompting the user to pay attention to road conditions. If the navigation route deviation is not serious, it does not actively adjust the navigation route, but only prompts the user to check if the current route is correct, allowing the user to decide whether to reset the navigation route, switch routes between main and auxiliary roads, or on and under bridges.

[0024] Figure 2 A flowchart illustrating a vehicle path planning method provided in an embodiment of this application. Figure 2 As shown, in one feasible implementation, the vehicle path planning method provided in this application is applied to an intelligent driving domain controller, including: S1. Obtain the global path information sent by the cockpit domain controller.

[0025] S2. The road comparison result is obtained by comparing the real-time vehicle location information, real-time road environment information and global path information obtained by the intelligent driving domain controller.

[0026] In step S2, the road comparison result is obtained by comparing the real-time vehicle location information, real-time road environment information, and global path information obtained by the intelligent driving domain controller, including: The road position deviation value is obtained by comparing the real-time vehicle location information acquired by the intelligent driving domain controller with the global path information; the real-time vehicle location information includes GNSS data and IMU data. The road scene deviation value is obtained by comparing the real-time road environment information acquired by the intelligent driving domain controller with the global path information; the real-time road environment information includes at least vehicle-mounted camera data, millimeter-wave radar data, and lidar data. The road comparison result is determined by the road position deviation value and the road scene deviation value.

[0027] Specifically, the road comparison results are determined by the road location deviation value and the road scene deviation value, including: The system determines whether the road position deviation exceeds a preset safety range and whether the road scene deviation is less than a preset deviation value. If the road position deviation exceeds the preset safety range and the road scene deviation is less than the first preset deviation value, the road comparison result is determined to be a road deviation. If the road position deviation does not exceed the preset safety range and the road scene deviation is less than the first preset deviation value, the road comparison result is determined to be a positioning anomaly; wherein, the second preset deviation value is greater than the first preset deviation value. If the road position deviation exceeds the preset safety range and the road scene deviation is greater than the second preset deviation value, the road comparison result is determined to be a perception anomaly.

[0028] The system calculates a weighted deviation value by weighting the road position deviation value and the road scene deviation value. If the weighted deviation value is greater than the target value, the road comparison result is determined to be a road deviation.

[0029] For example, high-precision satellite-based positioning (GNSS) and inertial navigation (IMU) can be used to continuously obtain the vehicle's actual location information and compare it in real time with the planned driving path issued by the vehicle navigation system. The spatial deviation values ​​between the vehicle's actual position and the planned path in the lateral and longitudinal directions are calculated. When the deviation exceeds the preset safety range, it is marked as a suspected route deviation state, and a multi-source information verification process is initiated to exclude non-real deviation situations such as temporary obstacle avoidance or instantaneous positioning drift.

[0030] This system utilizes sensors such as onboard cameras, millimeter-wave radar, and lidar to collaboratively collect real-time information about the surrounding road environment, including lane markings, driving arrows, roadside facilities, traffic signs, and other road users. The real-time perception results are then structurally matched with the planned route to determine if the vehicle has engaged in genuine deviation behaviors such as turning at the wrong exit, missing a ramp, or entering an unplanned lane. Simultaneously, reasonable deviation scenarios such as lane changes due to construction or emergency avoidance are filtered out. Combining vehicle speed, steering angle, and turn signal status, a comprehensive assessment is conducted to determine whether a valid wrong-way event has occurred. Once confirmed, the system proceeds to the deviation level evaluation stage.

[0031] S3. If the road comparison result is a road deviation, then the positioning deviation value, lane matching value, driving intention, and road legality value are determined based on the real-time vehicle location information and real-time road environment information obtained by the intelligent driving domain controller.

[0032] The positioning deviation here is calculated based on the distance difference between the vehicle's actual location and the planned path. The greater the deviation, the lower the score.

[0033] The lane matching value can be calculated based on the consistency between the lane identified by the sensor and the planned lane. The score drops significantly when the lane does not match.

[0034] Driving intention can be judged based on steering amplitude, lane change behavior, and speed changes. Unnatural and deliberate deviations will lower the score for this item.

[0035] The road legality score determines whether a vehicle is in an illegal area such as an emergency lane, a restricted area, or the wrong lane. When a vehicle is in an illegal area, this score is the lowest.

[0036] S4. Determine the overall deviation confidence level based on positioning deviation, lane matching value, driving intention, and road legality value.

[0037] The comprehensive deviation confidence score is determined based on positioning deviation, lane matching value, driving intention, and road legality value. This involves weighting the positioning deviation, lane matching value, driving intention, and road legality value to obtain the comprehensive deviation confidence score. The comprehensive confidence score is obtained by weighted fusion of the above four items. The weights can be adaptively adjusted according to vehicle type, intelligent driving level, and road condition scenario. The result is normalized to the [0,1] interval.

[0038] The overall deviation confidence level C here ranges from [0,1]. A higher value indicates that the vehicle's trajectory closely matches the planned route; a lower value indicates a more severe deviation and a higher probability of taking the wrong turn.

[0039] S5. Based on the confidence level corresponding to the comprehensive deviation confidence level, determine whether to replan the global path information.

[0040] Based on the confidence level corresponding to the overall deviation confidence level, determine whether to replan the global path information, including: When the overall deviation confidence level is less than the first preset confidence level, the confidence level is considered to be severely deviated, indicating that the global path information needs to be replanned. When the overall deviation confidence level is greater than or equal to the first preset confidence level and less than the second preset confidence level, the confidence level is determined to be moderate deviation, a vehicle deviation risk warning is generated and provided to the user; When the overall deviation confidence level is greater than or equal to the second preset confidence level, the confidence level is determined to be slightly deviated, and it is determined that there is no need to replan the global path information.

[0041] The first pre-specified reliability here is less than the second pre-specified reliability.

[0042] In a specific embodiment, the first preset confidence level can be 0.3, and the second preset confidence level can be 0.7.

[0043] The deviation confidence model quantifies the deviation level design as follows: High confidence level (C≥0.7): Slight deviation, mostly small deviations within the lane or temporary avoidance, which do not affect the overall route; Medium confidence level (0.3≤C<0.7): Moderate deviation, the vehicle has deviated from the planned lane and there is a risk of taking the wrong route. Users are advised to pay attention. Low confidence (C < 0.3): Severe deviation, judged as a wrong turn, requiring route replanning. To avoid misjudgments caused by road bumps and sensor noise, a time-series sliding window filtering method is used. The final deviation level is only confirmed after multiple consecutive frames meet the level conditions, improving system robustness.

[0044] Next, differentiated driving strategies can be generated based on the level of deviation. For minor deviations, no navigation replanning is needed; the system automatically fine-tunes the direction to smoothly return the vehicle to the center of the lane. For moderate deviations, a warning is issued via the vehicle's infotainment system, and the vehicle gradually corrects its trajectory within a safe range, without triggering a global replanning. For severe deviations, traffic rules must be strictly followed, and dangerous maneuvers such as reversing or driving against traffic must be avoided. A legal detour route is quickly planned, and the next safe point to merge back into the correct road is determined.

[0045] The intelligent driving system synchronizes with the in-vehicle navigation system to update the route. The system sends the corrected driving route or detour plan to the in-vehicle navigation system, which then replans the overall route based on the new path and updates the map display, turn prompts, and voice prompts. If the scenario is complex and the system cannot correct itself, it raises the warning level, prompting the driver to take over the vehicle to ensure driving safety.

[0046] This application provides a vehicle path planning method that uses multi-source perception and high-precision positioning of intelligent driving domain control to feed back into the cockpit navigation, thereby achieving real-time identification of route deviations, quantitative classification of confidence levels, and human-machine collaborative replanning, significantly improving the speed of deviation correction response, the accuracy of bridge / under-bridge identification, and the control of false trigger rate.

[0047] Example 2 In one embodiment of this application, the vehicle can return to normal driving mode after the route is restored. When the vehicle returns to the planned path and the confidence level returns to the normal range, the system exits the error correction mode, resumes normal navigation assistance driving, and records the deviation event data for algorithm iteration and optimization.

[0048] Furthermore, before replanning the route, it can be determined whether the user has given their consent to the route replanning. If so, the step of replanning the global route information is then performed.

[0049] As mentioned above, the cockpit domain controller redesigns its functions based on the perception and positioning information of the intelligent driving domain controller. Users can choose to turn these functions on or off. Regarding confidence level, the vehicle system will provide a default recommended value to the user based on the calibration results. Users can also adjust the confidence level while keeping the above switches on to meet the needs of different users in different regions.

[0050] The vehicle path planning method provided in this application addresses scenarios such as route deviation and wrong turns during vehicle operation. Through real-time linkage and verification of environmental perception, high-precision positioning, and navigation paths, it achieves automatic identification of wrong-way behavior, quantitative judgment of deviation degree, and dynamic correction of the navigation route. The system requires pre-integration of multi-sensor perception units, high-precision positioning modules, vehicle navigation systems, and high-precision map databases to establish a unified spatiotemporal benchmark and safety judgment rules, ensuring the real-time performance, safety, and stability of the route correction process.

[0051] Example 3 Figure 3 This is a schematic diagram of a vehicle path planning method apparatus provided in an embodiment of this application. Figure 3 As shown, based on the same inventive concept, this application also provides a vehicle path planning device 30, which includes: The acquisition module 310 is used to acquire global path information sent by the cockpit domain controller; The comparison module 320 is used to compare the real-time vehicle location information, real-time road environment information and global path information obtained by the intelligent driving domain controller to obtain the road comparison result; The analysis module 330 is used to determine the positioning deviation value, lane matching value, driving intention, and road legality value based on the real-time vehicle location information and real-time road environment information obtained by the intelligent driving domain controller if the road comparison result is a road deviation. Calculation module 340 is used to perform weighted calculations on positioning deviation, lane matching value, driving intention, and road legality value to obtain a comprehensive deviation confidence level; The planning module 350 is used to determine whether to replan the global path information based on the confidence level corresponding to the comprehensive deviation confidence level.

[0052] In an optional implementation, the comparison module is used to compare the real-time vehicle location information obtained by the intelligent driving domain controller with the global path information to obtain the road location deviation value; the real-time vehicle location information includes GNSS data and IMU data; The road scene deviation value is obtained by comparing the real-time road environment information obtained by the intelligent driving domain controller with the global path information. The real-time road environment information includes at least vehicle camera data, millimeter-wave radar data, and lidar data. The road comparison results are determined by the road location deviation value and the road scene deviation value.

[0053] In a preferred embodiment, the comparison module is used to determine whether the road position deviation value exceeds a preset safety range and whether the road scene deviation value is less than a preset deviation value; If the road position deviation value exceeds the preset safety range and the road scene deviation value is less than the first preset deviation value, then the road comparison result is determined to be a road deviation. If the road location deviation value does not exceed the preset safety range and the road scene deviation value is less than the first preset deviation value, then the road comparison result is determined to be a positioning anomaly; wherein, the second preset deviation value is greater than the first preset deviation value; If the road location deviation exceeds the preset safety range and the road scene deviation is greater than the second preset deviation value, then the road comparison result is determined to be a perception anomaly.

[0054] In a preferred embodiment, the comparison module is used to perform a weighted calculation on the road position deviation value and the road scene deviation value to obtain a weighted deviation value; If the weighted deviation value is greater than the target value, the road comparison result is determined to be a road deviation.

[0055] In a preferred embodiment, the comprehensive deviation confidence level is determined based on positioning deviation, lane matching value, driving intention, and road legality value, including: The overall deviation confidence level is obtained by weighting the positioning deviation, lane matching value, driving intention, and road legality value.

[0056] In a preferred embodiment, the planning module is used to determine that the global path information needs to be replanned when the overall deviation confidence level is less than a first preset confidence value, indicating a severe deviation. When the overall deviation confidence level is greater than or equal to the first preset confidence level and less than the second preset confidence level, the confidence level is determined to be moderate deviation, a vehicle deviation risk warning is generated and provided to the user; When the overall deviation confidence level is greater than or equal to the second preset confidence level, the confidence level is determined to be slightly deviated, and it is determined that there is no need to replan the global path information.

[0057] In a preferred embodiment, the planning module is further configured to determine whether a user's consent instruction for route replanning has been received; if so, a step of replanning the global route information is performed.

[0058] Example 3 Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 400 includes a processor 410, a memory 420, and a bus 430.

[0059] The memory 420 stores machine-readable instructions that can be executed by the processor 410. When the electronic device 400 is running, the processor 410 and the memory 420 communicate via the bus 430. When the machine-readable instructions are executed by the processor 410, the steps of a vehicle path planning method as described in the above method embodiment can be executed. For specific implementation details, please refer to the method embodiment, which will not be repeated here.

[0060] This application also provides a computer-readable storage medium storing a computer program. When the computer program is run by a processor, it can execute the steps of a vehicle path planning method as described in the above method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0061] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0062] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0063] Furthermore, the units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0064] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0065] It should be noted that if the function is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0066] In this document, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying any such actual relationship or order between these entities or operations.

[0067] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for vehicle path planning, characterized in that, The method is applied to an intelligent driving domain controller, and the method includes: Obtain the global path information sent by the cockpit domain controller; The road comparison result is obtained by comparing the real-time vehicle location information, real-time road environment information and global path information obtained by the intelligent driving domain controller. If the road comparison result is a road deviation, then the positioning deviation value, lane matching value, driving intention, and road legality value are determined based on the real-time vehicle location information and real-time road environment information obtained by the intelligent driving domain controller. The overall deviation confidence level is determined based on the positioning deviation, the lane matching value, the driving intention, and the road legality value. Based on the confidence level corresponding to the comprehensive deviation confidence level, determine whether to replan the global path information.

2. The method according to claim 1, characterized in that, The process of comparing the real-time vehicle location information, real-time road environment information, and global path information obtained from the intelligent driving domain controller to obtain the road comparison result includes: The road position deviation value is obtained by comparing the real-time vehicle location information obtained by the intelligent driving domain controller with the global path information; the real-time vehicle location information includes GNSS data and IMU data. The road scene deviation value is obtained by comparing the real-time road environment information and global path information obtained by the intelligent driving domain controller. The real-time road environment information includes at least vehicle camera data, millimeter-wave radar data, and lidar data. The road comparison result is determined by the road location deviation value and the road scene deviation value.

3. The method according to claim 2, characterized in that, Determining the road comparison result using the road location deviation value and the road scene deviation value includes: Determine whether the road position deviation value exceeds the preset safety range, and determine whether the road scene deviation value is less than the preset deviation value; If the road position deviation value exceeds the preset safety range and the road scene deviation value is less than the first preset deviation value, then the road comparison result is determined to be a road deviation. If the road position deviation value does not exceed the preset safety range, and the road scene deviation value is less than the first preset deviation value, then the road comparison result is determined to be a positioning anomaly; wherein, the second preset deviation value is greater than the first preset deviation value; If the road location deviation value exceeds the preset safety range, and the road scene deviation value is greater than the second preset deviation value, then the road comparison result is determined to be a perception anomaly.

4. The method according to claim 2, characterized in that, Determining the road comparison result using the road location deviation value and the road scene deviation value includes: The weighted deviation value is obtained by weighting the road position deviation value and the road scene deviation value. If the weighted deviation value is greater than the target value, then the road comparison result is determined to be a road deviation.

5. The method according to any one of claims 1-4, characterized in that, The step of determining the comprehensive deviation confidence level based on the positioning deviation, the lane matching value, the driving intention, and the road legality value includes: The overall deviation confidence level is obtained by weighting the positioning deviation, the lane matching value, the driving intention, and the road legality value.

6. The method according to claim 5, characterized in that, The step of determining whether to replan the global path information based on the confidence level corresponding to the comprehensive deviation confidence level includes: When the overall deviation confidence level is less than the first preset confidence level, the confidence level is considered to be severely deviated, indicating that the global path information needs to be replanned. When the overall deviation confidence level is greater than or equal to the first preset confidence level and less than the second preset confidence level, the confidence level is determined to be moderate deviation, a vehicle deviation risk warning is generated and provided to the user; When the overall deviation confidence level is greater than or equal to the second preset confidence level, the confidence level is determined to be slightly deviated, and it is determined that the global path information does not need to be replanned.

7. The method according to claim 6, characterized in that, Also includes: Determine whether the user's consent to the route replanning has been received; If so, then proceed with the step of replanning the global path information.

8. A path planning device for a vehicle, characterized in that, The device includes: The acquisition module obtains global path information sent by the cockpit domain controller; The comparison module compares the real-time vehicle location information, real-time road environment information, and global path information obtained by the intelligent driving domain controller to obtain the road comparison result; If the road comparison result is a road deviation, the analysis module determines the positioning deviation value, lane matching value, driving intention, and road legality value based on the real-time vehicle location information and real-time road environment information obtained by the intelligent driving domain controller. The calculation module performs a weighted calculation on the positioning deviation, the lane matching value, the driving intention, and the road legality value to obtain a comprehensive deviation confidence level; The planning module determines whether to replan the global path information based on the confidence level corresponding to the comprehensive deviation confidence level.

9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. The machine-readable instructions are executed by the processor to perform the steps of the vehicle path planning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the vehicle path planning method as described in any one of claims 1 to 7.

Images