Path planning method, device and equipment and computer program product

Abstract

The invention discloses a path planning method, apparatus and device, and a computer program product. The path planning method comprises the steps of obtaining a basic path planning result of an autonomous vehicle, real-time state data of the autonomous vehicle and traffic data of a lane level; according to the real-time state data of the autonomous vehicle and the traffic data of the lane level, generating a multi-dimensional path planning weight factor by using a preset lane level path planning strategy; and according to the basic path planning result and the multi-dimensional path planning weight factor, performing path planning by using a preset path planning algorithm to obtain an optimized path planning result of the autonomous vehicle. According to the path planning method, on the basis of considering the path time and distance, the basic path planning result is further adjusted and optimized by introducing the multi-dimensional lane-level path planning weight factor, and the driving experience and safety are optimized.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a path planning method, device and equipment, and a computer program product. Background Art

[0002] In the field of autonomous driving, high-precision maps (HD maps) are a key component of autonomous driving systems. The quality of their route calculation methods directly impacts the accuracy and efficiency of autonomous vehicle navigation. HD maps not only contain the road topology information of traditional maps but also record a wealth of road details such as lane markings, traffic signs, and traffic lights, providing a more accurate foundation for autonomous vehicles to perceive the environment. Route calculation methods, based on this high-precision information, plan the driving route from the starting point to the destination, and are a core component of autonomous navigation for autonomous vehicles.

[0003] Existing HD map routing methods primarily rely on traditional path planning algorithms, such as Dijkstra's algorithm or the A* algorithm. While these algorithms can theoretically find the shortest path, they often overlook factors such as lane selection and lane change control during driving. This can lead to problems such as detours, poor lane selection, and inappropriate lane change timing in real-world applications, impacting both the driving experience and safety. Summary of the Invention

[0004] The embodiments of the present application provide a path planning method, apparatus and equipment, and a computer program product to improve path planning effects and optimize driving experience and safety.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a path planning method, the path planning method comprising:

[0007] Obtain the basic path planning results of the autonomous vehicle, as well as the real-time status data and lane-level traffic data of the autonomous vehicle;

[0008] Generating a multi-dimensional path planning weight factor using a preset lane-level path planning strategy based on the real-time status data of the autonomous driving vehicle and lane-level traffic data;

[0009] According to the basic path planning result and the multi-dimensional path planning weight factors, a preset path planning algorithm is used to perform path planning to obtain an optimized path planning result for the autonomous driving vehicle.

[0010] Optionally, obtaining a basic path planning result of the autonomous driving vehicle includes:

[0011] Obtaining basic path planning data, including the starting and ending points of the autonomous driving vehicle and high-precision map data;

[0012] Based on the path planning basic data, a preset path planning algorithm is used to perform path planning to obtain a basic path planning result for the autonomous driving vehicle.

[0013] Optionally, the preset lane-level path planning strategy includes a lane selection strategy, the multi-dimensional path planning weight factor includes a lane selection weight factor, and generating the multi-dimensional path planning weight factor using the preset lane-level path planning strategy according to the real-time status data of the autonomous driving vehicle and the lane-level traffic data includes:

[0014] generating a lane selection rule using the lane selection strategy based on the lane-level traffic data;

[0015] A lane selection weighting factor is generated according to the lane selection rule.

[0016] Optionally, the preset lane-level path planning strategy includes a lane change timing strategy, the multi-dimensional path planning weight factor includes a lane change timing weight factor, and generating the multi-dimensional path planning weight factor using the preset lane-level path planning strategy based on the real-time status data of the autonomous driving vehicle and lane-level traffic data includes:

[0017] determining the feasibility of lane changing based on real-time status data of the autonomous vehicle;

[0018] predicting traffic conditions at a lane change point based on the lane-level traffic data;

[0019] The lane change timing weight factor is generated using the lane change timing strategy according to the feasibility of the lane change and the traffic conditions at the lane change point.

[0020] Optionally, the preset lane-level path planning strategy includes an intersection lane alignment strategy, the multi-dimensional path planning weight factor includes an intersection lane alignment weight factor, and generating the multi-dimensional path planning weight factor using the preset lane-level path planning strategy based on the real-time status data of the autonomous driving vehicle and lane-level traffic data includes:

[0021] Analyzing the traffic layout of the intersection based on the lane-level traffic data to determine the lane distribution and turning requirements of each intersection;

[0022] According to the lane distribution and turning requirements of each intersection, the intersection lane alignment strategy is used to set the intersection lane alignment weight factor.

[0023] Optionally, the preset lane-level path planning strategy includes a special operation lane selection strategy, the multi-dimensional path planning weight factor includes a special operation lane selection weight factor, and generating the multi-dimensional path planning weight factor using the preset lane-level path planning strategy based on the real-time status data of the autonomous driving vehicle and lane-level traffic data includes:

[0024] Performing a turn analysis based on the lane-level traffic data to obtain a turn analysis result;

[0025] The special operation lane selection weight factor is set using the special operation lane selection strategy according to the turning analysis result.

[0026] Optionally, after performing path planning using a preset path planning algorithm based on the basic path planning result and the multi-dimensional path planning weight factors to obtain an optimized path planning result for the autonomous driving vehicle, the path planning method further includes:

[0027] Comparing and evaluating a basic path planning result and an optimized path planning result of the autonomous driving vehicle to obtain a comparative evaluation result;

[0028] The preset lane-level path planning strategy is optimized based on the comparative evaluation.

[0029] In a second aspect, an embodiment of the present application further provides a path planning device, the path planning device comprising:

[0030] An acquisition unit, used to obtain basic path planning results of the autonomous driving vehicle, as well as real-time status data of the autonomous driving vehicle and lane-level traffic data;

[0031] a generating unit, configured to generate a multi-dimensional path planning weight factor using a preset lane-level path planning strategy based on the real-time state data of the autonomous driving vehicle and the lane-level traffic data;

[0032] A path planning unit is used to perform path planning using a preset path planning algorithm based on the basic path planning result and the multi-dimensional path planning weight factors to obtain an optimized path planning result for the autonomous driving vehicle.

[0033] In a third aspect, an embodiment of the present application further provides a device, including:

[0034] A processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform any of the aforementioned path planning methods.

[0035] In a fourth aspect, an embodiment of the present application further provides a computer program product, comprising a computer program / instruction, which implements any of the aforementioned path planning methods when executed by a processor.

[0036] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the path planning method in the embodiments of the present application first obtains the basic path planning results of the autonomous driving vehicle as well as the real-time status data and lane-level traffic data of the autonomous driving vehicle; then, based on the real-time status data and lane-level traffic data of the autonomous driving vehicle, a preset lane-level path planning strategy is used to generate a multi-dimensional path planning weight factor; finally, based on the basic path planning results and the multi-dimensional path planning weight factor, a preset path planning algorithm is used to perform path planning to obtain an optimized path planning result for the autonomous driving vehicle. The path planning method in the embodiments of the present application, on the basis of considering the path planning time and distance, further adjusts and optimizes the basic route planning results by introducing a multi-dimensional lane-level path planning weight factor, thereby optimizing the driving experience and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0038] Figure 1 A schematic diagram of a path planning method according to an embodiment of the present application;

[0039] Figure 2 This is a schematic structural diagram of a path planning device in an embodiment of the present application;

[0040] Figure 3 This is a structural diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0041] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0042] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0043] The present application embodiment provides a path planning method, such as Figure 1As shown, a flow chart of a path planning method in an embodiment of the present application is provided, and the path planning method includes at least the following steps S110 to S130:

[0044] Step S110, obtaining the basic path planning results of the autonomous driving vehicle as well as the real-time status data and lane-level traffic data of the autonomous driving vehicle.

[0045] The basic path planning results for autonomous vehicles can be generated by traditional path planning algorithms, such as the Dijkstra algorithm and the A* algorithm. These algorithms use the road topology information in high-precision maps, take the starting point and end point as input parameters, and calculate the shortest or optimal path between nodes in the map to obtain the approximate route of the autonomous vehicle from the starting point to the end point.

[0046] Real-time status data for autonomous vehicles covers multiple aspects, and this data can be obtained through various sensors and devices installed on the vehicle. For example, the Global Positioning System (GPS) sensor can obtain the vehicle's latitude and longitude coordinates in the world coordinate system in real time. In combination with sensors such as the Inertial Measurement Unit (IMU), the accuracy of this location information can be further improved. Wheel speed sensors or radar speedometers can accurately measure the vehicle's speed. The IMU can measure the vehicle's acceleration in three axes: longitudinal, lateral, and vertical. This helps understand the vehicle's acceleration, deceleration, and cornering, and is crucial for adjusting path planning strategies in real time to adapt to the vehicle's dynamic changes. Sensors such as the gyroscope can be used to obtain the vehicle's heading angle—the angle between the vehicle's forward direction and the geographic North Pole. This heading angle information can be used to determine the vehicle's direction of travel, perform lane keeping maneuvers, and perform lane changing operations.

[0047] Lane-level traffic data can more accurately reflect actual road traffic conditions and provide more detailed information support for route planning. For example, traffic lights, roadside units (RSUs), and other devices on the road can collect and transmit lane-level traffic information such as lane occupancy, traffic flow, and average speed. Autonomous vehicles communicate with these devices to obtain real-time lane-level traffic data. Sensors such as cameras and lidar installed on autonomous vehicles can perceive the vehicle's surrounding environment in real time. By processing and analyzing sensor data, the position and shape of lane lines, the trajectories and speeds of surrounding vehicles, and other information can be obtained, thereby determining lane-level traffic conditions.

[0048] Step S120: Generate a multi-dimensional path planning weight factor using a preset lane-level path planning strategy based on the real-time status data of the autonomous driving vehicle and the lane-level traffic data.

[0049] Preset lane-level path planning strategies are a set of rules and algorithms developed based on a comprehensive consideration of various key factors in the autonomous driving process. These strategies are designed to assign corresponding weights to different lane-level path planning dimensions based on the vehicle's real-time state and lane-level traffic conditions, thereby generating multi-dimensional path planning weighting factors. Preset lane-level path planning strategies in embodiments of the present application may include, for example, lane selection strategies, lane change timing strategies, and lane selection strategies after special maneuvers.

[0050] Based on the preset lane-level path planning strategy, combined with the autonomous vehicle's real-time status data and lane-level traffic data, a specific algorithm and calculation method are used to generate multi-dimensional path planning weighting factors. These weighting factors cover multiple path planning-related dimensions, providing a more comprehensive and accurate basis for lane-level decision-making in subsequent path planning, ensuring that the path planning results are more aligned with actual driving needs.

[0051] Step S130: Perform path planning using a preset path planning algorithm based on the basic path planning result and the multi-dimensional path planning weight factor to obtain an optimized path planning result for the autonomous driving vehicle.

[0052] The preset path planning algorithm is used to combine the basic path planning results and the multi-dimensional path planning weight factors to generate an optimized path planning result. For example, based on the traditional A* algorithm, a multi-dimensional path planning weight factor is introduced. When calculating the path cost between nodes, not only traditional factors such as distance or time are considered, but also the lane-level multi-dimensional path planning weight factor is included in the calculation as an influencing factor of path planning. For example, in the A* algorithm, the heuristic function can be adjusted according to the multi-dimensional weight factor to guide the search direction to be more inclined to the optimized path that comprehensively considers various factors, and finally obtains the optimized path planning result of the autonomous driving vehicle. This result not only takes into account the shortest time and distance, but also comprehensively considers multiple key factors such as lane selection, lane change timing, special operations, etc., providing a more reasonable, safe and comfortable driving route for autonomous driving vehicles.

[0053] For example, the optimized path planning results may adjust the vehicle's lane selection on certain road sections to avoid frequent lane changes and unnecessary detours; when approaching an intersection, the appropriate lane is planned in advance to ensure smooth turning or straight-ahead maneuvers; when special maneuvers such as turning are required, the optimal time and location are selected to minimize the impact on other vehicles and improve overall traffic efficiency. In this way, the autonomous vehicle path planning method of the embodiment of the present application can significantly improve the driving experience and safety, meeting the needs of autonomous driving technology in practical applications.

[0054] The path planning method of the embodiment of the present application further adjusts and optimizes the basic route planning results by introducing multi-dimensional lane-level path planning weight factors based on consideration of path time and distance, thereby optimizing driving experience and safety.

[0055] In some embodiments of the present application, obtaining the basic path planning results of the autonomous driving vehicle includes: obtaining basic path planning data, the basic path planning data including the starting and ending point positions and high-precision map data of the autonomous driving vehicle; based on the basic path planning data, using a preset path planning algorithm to perform path planning to obtain the basic path planning results of the autonomous driving vehicle.

[0056] In an autonomous driving system, the starting and ending point locations can be obtained in a variety of ways. One way is user interactive input. For example, on the in-vehicle navigation interface or a mobile device application connected to it, the user can select the starting and ending points by touching the screen, and the system converts the geographical location information selected by the user into precise latitude and longitude coordinates. The vehicle's current location can also be used as the starting point, which can be achieved by using the global positioning system (GPS) sensor equipped on the vehicle. The GPS sensor can receive satellite signals in real time, calculate the vehicle's precise position in the earth's coordinate system, and transmit this position information to the path planning module of the autonomous driving system. As for the end point location, in addition to user input, it can also be automatically determined based on preset mission objectives, such as going to a designated charging station, parking lot, etc. Of course, the specific method for obtaining the starting and ending point location information of the path planning can be flexibly determined by those skilled in the art based on the actual application scenario, and is not specifically limited here.

[0057] High-precision map data is an important foundation for route planning. It contains rich road information, including not only high-precision coordinates but also accurate road shapes. The slope, curvature, heading, elevation, and roll data of each lane are also included. In addition, the type of markings on each lane, the color of the lane lines, the road median strips, and the arrows and text on the road signs are all presented in the high-precision map.

[0058] There are a variety of pre-defined path planning algorithms in the autonomous driving field, such as the Dijkstra algorithm and the A* algorithm. Different algorithms have different characteristics and applicable scenarios. Those skilled in the art can flexibly select an appropriate path planning algorithm based on actual needs. For example, they can use the A* algorithm to perform path planning based on the starting and ending points of the autonomous vehicle and high-precision map data to obtain the basic path planning results for the autonomous vehicle.

[0059] This embodiment of the application obtains the starting and ending points of the autonomous vehicle and comprehensive high-precision map data, and uses an appropriate preset path planning algorithm to quickly generate basic path planning results. This provides a reliable foundation for further optimizing path planning and comprehensively considering multiple factors such as lane selection and lane change timing. It helps improve the accuracy and rationality of autonomous vehicle path planning and ensures the safety and efficiency of autonomous driving.

[0060] In some embodiments of the present application, the preset lane-level path planning strategy includes a lane selection strategy, the multi-dimensional path planning weight factor includes a lane selection weight factor, and generating the multi-dimensional path planning weight factor based on the real-time status data of the autonomous driving vehicle and the lane-level traffic data using the preset lane-level path planning strategy includes: generating a lane selection rule based on the lane-level traffic data using the lane selection strategy; and generating a lane selection weight factor based on the lane selection rule.

[0061] The preset lane-level path planning strategy in the embodiment of the present application may include a lane selection strategy, and the corresponding multi-dimensional path planning weight factor may include a lane selection weight factor.

[0062] Lane-level traffic data can be collected through sensors installed on the road (such as cameras and geomagnetic sensors). For example, a geomagnetic sensor can be installed in each lane of a city's main road to monitor the number of vehicles passing through the lane in real time. The lane utilization rate is calculated based on the lane's designed capacity (for example, a lane can pass 1,000 vehicles per hour under ideal conditions). At the same time, traffic rule information for the lane is obtained from the traffic sign recognition system, such as whether trucks are allowed to pass or whether it is a bus lane. Vehicle performance parameters, such as vehicle height and weight, can be obtained through the vehicle's own sensors or data provided by the vehicle manufacturer.

[0063] Lane selection rules are developed based on the collected data. For example, a lane utilization threshold is set at 80%. When a lane's utilization falls below 80%, that lane is prioritized. If multiple lanes have similar utilization rates, lanes without special restrictions (such as no height or weight restrictions) are prioritized. These rules are converted into lane selection weighting factors in the A* algorithm. Lanes with low utilization and no special restrictions have smaller selection weighting factors (lower cost) and are more likely to be selected during path planning.

[0064] During route planning, when the vehicle reaches a road section with multiple lane options, the lane selection on the baseline route is adjusted based on the established lane selection rules and the weighted calculations of the A* algorithm. For example, if the baseline route originally selected the center lane, but the lane selection strategy finds that the right lane is less used and has no special restrictions, the lane selection is adjusted to the right lane, and the driver is prompted to change lanes in the navigation system.

[0065] The embodiment of the present application collects lane-level traffic data (such as utilization rate and traffic rules) in real time. Combined with preset lane selection rules, the system can dynamically evaluate the traffic conditions of each lane. The rules not only take into account lane utilization rate, but also integrate vehicle performance parameters (such as height and weight) and traffic rules (such as dedicated lane restrictions), adapting to traffic changes in real time and optimizing driving experience and comfort.

[0066] In some embodiments of the present application, the preset lane-level path planning strategy includes a lane change timing strategy, the multi-dimensional path planning weight factor includes a lane change timing weight factor, and generating the multi-dimensional path planning weight factor using the preset lane-level path planning strategy based on the real-time status data of the autonomous driving vehicle and the lane-level traffic data includes: determining the feasibility of lane changing based on the real-time status data of the autonomous driving vehicle; predicting the traffic conditions at the lane changing point based on the lane-level traffic data; and generating the lane changing timing weight factor using the lane changing timing strategy based on the feasibility of the lane changing and the traffic conditions at the lane changing point.

[0067] The preset lane-level path planning strategy in the embodiment of the present application may include a lane change timing strategy, and the corresponding multi-dimensional path planning weight factor may include a lane change timing weight factor.

[0068] Based on real-time traffic flow data, the system analyzes the utilization rate of the target lane and its surrounding lanes. For example, by interacting with surrounding vehicles, it obtains real-time position and speed information for each lane and calculates lane utilization. If the utilization rate of lanes surrounding the target lane is low (e.g., below 60%) and there is no vehicle blocking the target lane for a certain distance (e.g., 50 meters) ahead, the lane is considered suitable for lane change.

[0069] The vehicle's speed and acceleration are monitored using its own sensors (such as speed sensors and accelerometers). For example, when the vehicle's speed is stable at 60 km / h and the acceleration is close to 0, it indicates that the vehicle is in a stable driving state and meets the basic conditions for lane change. If the vehicle is accelerating or decelerating, the feasibility of lane change is determined based on the magnitude and direction of the acceleration. If the acceleration is too high, lane change is not recommended.

[0070] The optimal lane change timing is determined by combining traffic flow analysis and vehicle status monitoring results. For example, if traffic flow analysis shows low lane usage around the target lane and no obstructions ahead, and vehicle status monitoring indicates a stable driving state, the navigation system will prompt the driver to change lanes. This lane change decision will be used as a weighting factor in the A* algorithm's lane change timing, influencing subsequent path planning.

[0071] This embodiment of the application quantitatively assesses the feasibility of lane changes to avoid collision risks or traffic disruptions caused by blind lane changes. By monitoring vehicle acceleration and traffic flow changes in real time, the lane change timing weights are dynamically adjusted to adapt planning results to complex conditions such as acceleration, deceleration, and congestion, improving decision robustness. Incorporating lane change timing weights into the path planning algorithm guides path search to prioritize low-risk lane change nodes, reducing invalid path expansion and shortening planning calculation time.

[0072] In some embodiments of the present application, the preset lane-level path planning strategy includes an intersection lane alignment strategy, the multi-dimensional path planning weight factor includes an intersection lane alignment weight factor, and the generation of the multi-dimensional path planning weight factor based on the real-time status data of the autonomous driving vehicle and the lane-level traffic data using the preset lane-level path planning strategy includes: analyzing the traffic layout of the intersection based on the lane-level traffic data to determine the lane distribution and turning requirements of each intersection; and setting the intersection lane alignment weight factor based on the lane distribution and turning requirements of each intersection using the intersection lane alignment strategy.

[0073] The preset lane-level path planning strategy of the embodiment of the present application may also include an intersection lane alignment strategy, and the corresponding multi-dimensional path planning weight factor may include an intersection lane alignment weight factor.

[0074] High-precision maps are used to obtain intersection traffic layout information, including lane distribution and turning requirements at each intersection. For example, at an intersection, there are three turns: left, straight, and right. Each turn corresponds to a different lane, such as the first lane on the left for a left turn, the middle two lanes for a straight turn, and the first lane on the right for a right turn. This information is stored in the database as lane distribution information and can be queried during route planning. Turn requirements, such as whether a left or right turn is required, are used to enter the corresponding dedicated lane in advance, which serves as a weighting factor for the intersection lane alignment in the A* algorithm.

[0075] When the vehicle approaches an intersection, it plans lane changes based on the navigation system's turn prompts (e.g., a 500-meter-ahead left turn prompt) and the intersection's lane distribution information. For example, if a left turn is required, the system plans to change lanes from the current lane to the first lane on the left, and displays a lane change prompt in the navigation system, such as "500 meters ahead, left turn, please change lanes to the left."

[0076] The navigation system's user interface provides clear, graphical lane guidance. For example, the screen displays the vehicle's current location and a lane map of the upcoming intersection. The lane the vehicle needs to enter is marked with different colors, and the guidance information is updated in real time as the vehicle approaches the intersection, helping the driver make the correct lane selection in advance.

[0077] This embodiment of the application uses lane distribution and steering requirements analysis based on high-precision maps to ensure vehicles enter the correct lane in advance, avoiding violations such as crossing the line or driving against traffic due to impromptu lane changes. Lane alignment weights are integrated into global path planning to align vehicle steering at intersections with upstream lane selection, minimizing path interruptions and repeated adjustments.

[0078] In some embodiments of the present application, the preset lane-level path planning strategy includes a special operation lane selection strategy, the multi-dimensional path planning weight factor includes a special operation lane selection weight factor, and the generation of the multi-dimensional path planning weight factor based on the real-time status data of the autonomous driving vehicle and the lane-level traffic data using the preset lane-level path planning strategy includes: performing a turning analysis based on the lane-level traffic data to obtain a turning analysis result; and setting the special operation lane selection weight factor based on the turning analysis result using the special operation lane selection strategy.

[0079] The preset lane-level path planning strategy of the embodiment of the present application may also include a special operation lane selection strategy, and the corresponding multi-dimensional path planning weight factor may include a special operation lane selection weight factor.

[0080] High-precision maps are used to obtain information about traffic rules and lane distribution at turning points. For example, a certain turning point requires vehicles to enter a left-turn waiting area before turning, and the left-turn waiting area is located in the second lane on the left. Traffic signal rules at this turning point are also known, such as the duration of the left-turn signal. This information is used as a weight for the A* algorithm's lane selection for special operations, prioritizing lanes that meet turning requirements.

[0081] The navigation system will prompt the driver to change lanes a certain distance (e.g., 300 meters) in advance, based on the location of the turning point and the vehicle's speed. For example, when the vehicle is 300 meters from the turning point, the navigation system will prompt "Turn left in 300 meters. Please change lanes to the second lane on the left," giving the driver ample time to make the lane change.

[0082] Near turning points, the navigation system provides clear lane instructions through voice prompts and on-screen displays. For example, when the vehicle approaches a turning point, a voice prompt appears, "Please stay in the second lane on the left and prepare to turn left." At the same time, the correct lane is indicated on the screen with arrows and text, ensuring the driver can complete the turn safely and accurately.

[0083] This embodiment of the application, based on rules such as waiting areas and dedicated lanes on high-precision maps, forces vehicles to enter compliant lanes in advance, avoiding violations caused by crossing the line, driving in the wrong direction, or missing the waiting time to turn. By analyzing the linkage between traffic light rules (such as left turn signal timing) and lane distribution, lanes that can smoothly pass the turning point are prioritized, reducing the risk of being stranded at the intersection.

[0084] In some embodiments of the present application, after performing path planning using a preset path planning algorithm based on the basic path planning result and the multi-dimensional path planning weight factor to obtain the optimized path planning result of the autonomous driving vehicle, the path planning method further includes: performing comparative evaluation on the basic path planning result and the optimized path planning result of the autonomous driving vehicle to obtain a comparative evaluation result; and optimizing the preset lane-level path planning strategy based on the comparative evaluation.

[0085] After obtaining the optimized path planning results, the route after applying the new strategy can be compared with the baseline route to evaluate the effectiveness of the new strategy based on multiple metrics, such as route length, travel time, number of lane changes, and user satisfaction. For example, if the travel time of the two routes is 10% shorter than the baseline route, the new strategy has improved time efficiency. Similarly, if the number of lane changes is reduced by 20%, the new strategy has improved lane change rationality.

[0086] For evaluation indicators such as route length, driving time, and number of lane changes, actual driving data, including driving time, number of lane changes, and fuel consumption, can be collected through data collection devices on the vehicle (such as OBD interfaces and dashcams). For example, after each drive, the collected data can be uploaded to a cloud server for storage and analysis.

[0087] Regarding user satisfaction, a feedback portal is provided through the navigation system's user interface, allowing users to submit feedback on route planning at any time. For example, after navigation is complete, a feedback window will pop up, asking users for their opinions on route accuracy, the timeliness of navigation prompts, and other aspects. Users can provide feedback by selecting a rating or entering text.

[0088] Collected user feedback is categorized and analyzed. For example, feedback can be categorized into issues such as route accuracy, navigation prompts, and driving comfort, and the number and proportion of feedback in each category can be counted. By analyzing the feedback, problems and deficiencies in route planning can be identified. For example, if multiple users report that navigation prompts on a particular route section are untimely, this indicates a problem with the prompt strategy for that route section.

[0089] Furthermore, route risk assessments can be performed, leveraging high-precision maps and real-time traffic data to identify potential risk points along the route. For example, by analyzing historical accident data, accident-prone sections of road can be identified and displayed in the navigation system with special warnings, such as "Accident-prone section ahead, please drive with caution." Construction information can also be incorporated to mark construction areas and provide detour suggestions.

[0090] Based on the above evaluation results, the strategy is adjusted and optimized. For example, if the new strategy is found to increase travel time on certain sections of road, analysis may indicate that the lane selection strategy is unreasonable for that section. In this case, the lane selection rules are adjusted, such as increasing the weight threshold for lane utilization, and the path planning and strategy evaluation are re-performed until the optimal strategy is found. If the lane selection rules on a certain section of road are found to result in excessive lane changes, affecting driving comfort, it is recommended to adjust the lane selection rules, such as increasing the buffer distance for lane changes. If the lane alignment strategy at a certain intersection causes vehicles to wait too long at the intersection, it is recommended to optimize lane planning and prompt drivers to change lanes earlier. If user feedback indicates that navigation prompts are not timely, the prompt strategy is adjusted to provide advance distance prompts or increase the frequency of prompts. The optimized strategy is reapplied to path planning and verified and further optimized through a new round of user feedback loops to provide a better user experience.

[0091] The present application also provides a path planning device 200, such as Figure 2 As shown, a schematic diagram of the structure of a path planning device in an embodiment of the present application is provided. The path planning device 200 includes: an acquisition unit 210, a generation unit 220 and a path planning unit 230, wherein:

[0092] An acquisition unit 210 is configured to acquire basic path planning results of the autonomous driving vehicle, as well as real-time status data of the autonomous driving vehicle and lane-level traffic data;

[0093] A generating unit 220 is configured to generate a multi-dimensional path planning weight factor using a preset lane-level path planning strategy based on the real-time state data of the autonomous driving vehicle and the lane-level traffic data;

[0094] The path planning unit 230 is used to perform path planning using a preset path planning algorithm based on the basic path planning result and the multi-dimensional path planning weight factor to obtain an optimized path planning result for the autonomous driving vehicle.

[0095] In some embodiments of the present application, the acquisition unit 210 is specifically used to: obtain basic path planning data, the basic path planning data including the starting and ending point positions of the autonomous driving vehicle and high-precision map data; based on the basic path planning data, use a preset path planning algorithm to perform path planning to obtain a basic path planning result for the autonomous driving vehicle.

[0096] In some embodiments of the present application, the preset lane-level path planning strategy includes a lane selection strategy, the multi-dimensional path planning weight factor includes a lane selection weight factor, and the generation unit 220 is specifically used to: generate a lane selection rule using the lane selection strategy based on the lane-level traffic data; and generate a lane selection weight factor based on the lane selection rule.

[0097] In some embodiments of the present application, the preset lane-level path planning strategy includes a lane change timing strategy, the multi-dimensional path planning weight factor includes a lane change timing weight factor, and the generation unit 220 is specifically used to: determine the feasibility of lane changing based on the real-time status data of the autonomous driving vehicle; predict the traffic conditions at the lane changing point based on the lane-level traffic data; and generate the lane change timing weight factor using the lane change timing strategy based on the feasibility of the lane change and the traffic conditions at the lane changing point.

[0098] In some embodiments of the present application, the preset lane-level path planning strategy includes an intersection lane alignment strategy, the multi-dimensional path planning weight factor includes an intersection lane alignment weight factor, and the generation unit 220 is specifically used to: analyze the traffic layout of the intersection based on the lane-level traffic data, and determine the lane distribution and turning requirements of each intersection; according to the lane distribution and turning requirements of each intersection, use the intersection lane alignment strategy to set the intersection lane alignment weight factor.

[0099] In some embodiments of the present application, the preset lane-level path planning strategy includes a special operation lane selection strategy, the multi-dimensional path planning weight factor includes a special operation lane selection weight factor, and the generation unit 220 is specifically used to: perform a turning analysis based on the lane-level traffic data to obtain a turning analysis result; and according to the turning analysis result, use the special operation lane selection strategy to set the special operation lane selection weight factor.

[0100] In some embodiments of the present application, the path planning device 200 also includes: an evaluation unit, which is used to perform path planning using a preset path planning algorithm based on the basic path planning result and the multi-dimensional path planning weight factor, and after obtaining the optimized path planning result of the autonomous driving vehicle, perform comparative evaluation on the basic path planning result and the optimized path planning result of the autonomous driving vehicle to obtain a comparative evaluation result; and an optimization unit, which is used to optimize the preset lane-level path planning strategy based on the comparative evaluation.

[0101] It can be understood that the above-mentioned path planning device can implement each step of the path planning method provided in the above-mentioned embodiment. The relevant explanations about the path planning method are applicable to the path planning device and will not be repeated here.

[0102] Figure 3 This is a schematic diagram of the structure of a device in the embodiment of the present application. Figure 3 As shown, the device includes one or more processors (or processing units), may further include one or more memories coupled to the processors, and may further include a communication module coupled to the processors.

[0103] The communication module can be used to communicate with other devices or apparatuses, such as sending or receiving data and / or signals. The communication module can include at least one communication module for communication. The communication module can include any interface necessary for communicating with other devices. Exemplarily, the communication module can be a transceiver, circuit, bus, module, or other type of communication module.

[0104] The processor may include, but is not limited to, at least one of the following: a general-purpose computer, a special-purpose computer, a microcontroller, a digital signal processor (DSP), or one or more of a controller-based multi-core controller architecture. A device may have multiple processors, such as application-specific integrated circuit chips, which are time-slave to a clock synchronized with a main processor.

[0105] The memory may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, at least one of the following: read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, hard disk, compact disc (CD), digital video disc (DVD), or other magnetic storage and / or optical storage. Examples of volatile memories include, but are not limited to, at least one of the following: random access memory (RAM), or other volatile memories that do not persist during a power outage.

[0106] A computer program includes computer-executable instructions that are executed by an associated processor. The program may be stored in ROM. The processor may perform any suitable actions and processes by loading the program into RAM.

[0107] The possible implementation of the present application can be realized by means of a program, so that the communication device can perform any process discussed in the above embodiments. The possible implementation of the present application can also be realized by hardware or by a combination of software and hardware.

[0108] In some embodiments, the program may be tangibly contained in a computer-readable storage medium that may be included in the device (such as in a memory) or other storage device accessible by the device. The program may be loaded from the computer-readable storage medium into RAM for execution. The computer-readable storage medium may include any type of tangible non-volatile memory, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc.

[0109] The present application also provides a computer-readable storage medium having computer instructions or program codes stored thereon, which, when executed by a processor, causes the processor to perform the methods and functions described in any of the above embodiments. A computer-readable medium may be any tangible medium containing or storing a program for or related to an instruction execution system, apparatus, or device. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. Computer-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination thereof. The computer-readable storage medium may be any available medium that a computer can access, or a data storage device such as a server or data center that includes one or more available media integrated therein. More detailed examples of computer-readable storage media include electrical connections with one or more wires, magnetic media (e.g., magnetic disks, floppy disks, hard disks, tapes, magnetic storage devices), optical media (e.g., optical storage devices, DVDs), semiconductor media (e.g., solid-state drives), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), or any suitable combination thereof.

[0110] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The embodiments of the present application also provide at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes one or more computer-executable instructions, such as instructions included in a program module, which are executed in a device on a real or virtual processor of the target to perform the processes, methods and functions involved in any of the above embodiments. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) method.

[0111] The present application also provides a computer program product, including a computer program or instructions, which, when run on a computer, causes the computer to perform the processes, methods, and functions in the above-described embodiments. Typically, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functions of the program modules can be combined or divided between program modules as needed. The machine executable instructions for the program modules can be executed in local or distributed devices. In distributed devices, the program modules can be located in local and remote storage media.

[0112] In general, various embodiments of the present application can be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects can be implemented in hardware, while other aspects can be implemented in firmware or software, which can be executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of the present disclosure are shown and described as block diagrams, flow charts, or using some other graphical representation, it should be understood that the blocks, devices, systems, techniques, or methods described herein can be implemented as, by way of non-limiting example, hardware, software, firmware, dedicated circuits or logic, general-purpose hardware or a controller or other computing device, or some combination thereof.

[0113] It should be noted that although the embodiments of the present application are described above in conjunction with the accompanying drawings, the above embodiments are not independent of each other, and they can also be combined to obtain other embodiments. The methods, situations, categories, and divisions of the embodiments in the embodiments of the present application are only for the convenience of description and should not constitute special limitations. The features of the various methods, categories, situations, and embodiments can be combined with each other when they are logical. The various embodiments of the present application can be combined arbitrarily to achieve different technical effects. The embodiments of the present application no longer list various combinations.

[0114] In addition, although the operations of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that these operations must be performed in this particular order, or that all the operations shown must be performed to achieve the desired result. On the contrary, the steps depicted in the flowchart can change the order of execution. Additionally or alternatively, certain steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps. It should also be noted that the features and functions of two or more devices according to the present disclosure can be embodied in one device. Conversely, the features and functions of a device described above can be further divided into being embodied by multiple devices.

[0115] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0116] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A path planning method, characterized in that: The path planning method comprises: Obtain basic path planning results for autonomous vehicles, as well as real-time status data and lane-level traffic data for autonomous vehicles; Generating a multi-dimensional path planning weight factor using a preset lane-level path planning strategy based on the real-time status data of the autonomous driving vehicle and lane-level traffic data; According to the basic path planning result and the multi-dimensional path planning weight factors, a preset path planning algorithm is used to perform path planning to obtain an optimized path planning result for the autonomous driving vehicle.

2. The path planning method according to claim 1, characterized in that: Obtaining the basic path planning results of the autonomous driving vehicle includes: Obtaining basic path planning data, including the starting and ending points of the autonomous driving vehicle and high-precision map data; Based on the path planning basic data, a preset path planning algorithm is used to perform path planning to obtain a basic path planning result for the autonomous driving vehicle.

3. The path planning method according to claim 1, characterized in that: The preset lane-level path planning strategy includes a lane selection strategy, the multi-dimensional path planning weight factor includes a lane selection weight factor, and generating the multi-dimensional path planning weight factor using the preset lane-level path planning strategy based on the real-time status data of the autonomous driving vehicle and lane-level traffic data includes: generating a lane selection rule using the lane selection strategy based on the lane-level traffic data; A lane selection weighting factor is generated according to the lane selection rule.

4. The path planning method according to claim 1, characterized in that: The preset lane-level path planning strategy includes a lane change timing strategy, the multi-dimensional path planning weight factor includes a lane change timing weight factor, and generating the multi-dimensional path planning weight factor using the preset lane-level path planning strategy based on the real-time status data of the autonomous driving vehicle and lane-level traffic data includes: determining the feasibility of lane changing based on real-time status data of the autonomous vehicle; predicting traffic conditions at a lane change point based on the lane-level traffic data; The lane change timing weight factor is generated using the lane change timing strategy according to the feasibility of the lane change and the traffic conditions at the lane change point.

5. The path planning method according to claim 1, characterized in that: The preset lane-level path planning strategy includes an intersection lane alignment strategy, the multi-dimensional path planning weight factor includes an intersection lane alignment weight factor, and generating the multi-dimensional path planning weight factor using the preset lane-level path planning strategy based on the real-time status data of the autonomous driving vehicle and lane-level traffic data includes: Analyzing the traffic layout of the intersection based on the lane-level traffic data to determine the lane distribution and turning requirements of each intersection; According to the lane distribution and turning requirements of each intersection, the intersection lane alignment strategy is used to set the intersection lane alignment weight factor.

6. The path planning method according to claim 1, characterized in that: The preset lane-level path planning strategy includes a special operation lane selection strategy, the multi-dimensional path planning weight factor includes a special operation lane selection weight factor, and generating the multi-dimensional path planning weight factor using the preset lane-level path planning strategy based on the real-time status data of the autonomous driving vehicle and lane-level traffic data includes: Performing a turn analysis based on the lane-level traffic data to obtain a turn analysis result; The special operation lane selection weight factor is set using the special operation lane selection strategy according to the turning analysis result.

7. The path planning method according to any one of claims 1 to 6, characterized in that: After performing path planning using a preset path planning algorithm based on the basic path planning result and the multi-dimensional path planning weight factors to obtain an optimized path planning result for the autonomous driving vehicle, the path planning method further includes: Comparing and evaluating a basic path planning result and an optimized path planning result of the autonomous driving vehicle to obtain a comparative evaluation result; The preset lane-level path planning strategy is optimized based on the comparative evaluation.

8. A path planning device, characterized in that: The path planning device comprises: An acquisition unit, used to obtain basic path planning results of the autonomous driving vehicle, as well as real-time status data of the autonomous driving vehicle and lane-level traffic data; a generating unit, configured to generate a multi-dimensional path planning weight factor using a preset lane-level path planning strategy based on the real-time state data of the autonomous driving vehicle and the lane-level traffic data; A path planning unit is used to perform path planning using a preset path planning algorithm based on the basic path planning result and the multi-dimensional path planning weight factors to obtain an optimized path planning result for the autonomous driving vehicle.

9. A device comprising: processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the path planning method according to any one of claims 1 to 7.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the path planning method according to any one of claims 1 to 7 is implemented.

Images