Path planning method and device, domain controller, storage medium and vehicle

Abstract

The application provides a path planning method and device, a domain controller, a storage medium and a vehicle. The method comprises the following steps: the vehicle acquires a target path planning result at a historical moment and vehicle state information at a current moment, the time interval between the historical moment and the current moment is within a preset time range; path optimization is performed on the target path planning result based on the vehicle state information, and a path optimization result at the current moment is determined; and if the path optimization result meets a preset condition, the target path planning result is determined as a path planning result at the current moment. In the embodiment of the application, the target path planning result is reused, path jump under abnormal conditions such as no solution of path optimization can be avoided, the safety and reliability of vehicle driving can be improved, the calculation amount can be reduced, the calculation time consumption can be shortened, and the real-time performance of path planning can be improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a path planning method, apparatus, domain controller, storage medium, and vehicle. Background Technology

[0002] With the continuous development of artificial intelligence technology, autonomous driving technology is becoming increasingly mature.

[0003] In related technologies, vehicles typically have multiple possible paths during operation. Intelligent modules within the vehicle, such as optimizers, usually perform secondary optimization on these multiple paths to obtain numerical solutions for each path.

[0004] This path planning method, due to inconsistent optimization parameter settings, may result in situations where there is no solution for vehicle path optimization, leading to abrupt changes in the planned path and low vehicle safety. At the same time, the computational load during the path optimization process is large and time-consuming, resulting in low real-time performance of path planning. Summary of the Invention

[0005] This application provides a path planning method, apparatus, domain controller, storage medium, and vehicle, which can avoid abrupt changes in the planned path, improve vehicle safety, reduce the computational load of path optimization, shorten computation time, and improve the real-time performance of path planning.

[0006] In a first aspect, embodiments of this application provide a path planning method, including:

[0007] Obtain the target path planning results at a historical moment and the vehicle status information at the current moment, wherein the time interval between the historical moment and the current moment is within a preset time range;

[0008] Based on the vehicle status information, the target path planning result is optimized to determine the path optimization result at the current moment;

[0009] If the path optimization result meets the preset conditions, then the target path planning result is determined as the path planning result at the current moment.

[0010] In one possible implementation, after optimizing the target path planning result based on the vehicle state information and determining the path optimization result at the current moment, the method further includes:

[0011] If the current path optimization result indicates the existence of alternative path planning results, determine the deviation between the alternative path planning results and the target path planning results;

[0012] If the deviation is greater than a preset threshold, then the path optimization result at the current moment is determined to meet the preset conditions.

[0013] In one possible implementation, the method further includes:

[0014] The timeliness parameters of the target path planning results are determined based on the time interval between the historical time and the initial time.

[0015] Determine the number of times the target path planning results can be reused;

[0016] The confidence level of the target path planning result is determined based on the timeliness parameter and the number of reuses.

[0017] Within the preset time range, if the number of target path planning results is at least two, then the historical time and the target path planning result corresponding to the historical time are determined based on the confidence level.

[0018] In one possible implementation, the method further includes:

[0019] If the time interval between the current time and the initial time reaches a preset time threshold, and / or the vehicle position coordinates at the current time are greater than the endpoint position coordinates of the target path planning result, multiple alternative paths are re-acquired.

[0020] The multiple alternative paths are optimized to determine and output new path planning results.

[0021] In one possible implementation, after optimizing the target path planning result based on the vehicle state information and determining the path optimization result at the current moment, the method further includes:

[0022] If the path optimization result at the current moment is unsolvable, then the path optimization result at the current moment is determined to meet the preset conditions.

[0023] In one possible implementation, the deviation includes at least one of lateral distance deviation, heading angle deviation, steering wheel angle deviation, and lateral acceleration deviation.

[0024] Secondly, embodiments of this application provide a path planning device, comprising:

[0025] The acquisition module is used to acquire the target path planning results at a historical time and the vehicle status information at the current time, wherein the time interval between the historical time and the current time is within a preset time range;

[0026] The first determining module is used to optimize the target path planning result based on the vehicle status information and determine the path optimization result at the current moment;

[0027] The second determining module is used to determine the target path planning result as the path planning result at the current moment if the path optimization result meets the preset conditions.

[0028] In one possible implementation, the device is further used for:

[0029] If the current path optimization result indicates the existence of alternative path planning results, determine the deviation between the alternative path planning results and the target path planning results;

[0030] If the deviation is greater than a preset threshold, then the path optimization result at the current moment is determined to meet the preset conditions.

[0031] In one possible implementation, the device is further used for:

[0032] The timeliness parameters of the target path planning results are determined based on the time interval between the historical time and the initial time.

[0033] Determine the number of times the target path planning results can be reused;

[0034] The confidence level of the target path planning result is determined based on the timeliness parameter and the number of reuses.

[0035] Within the preset time range, if the number of target path planning results is at least two, then the historical time and the target path planning result corresponding to the historical time are determined based on the confidence level.

[0036] In one possible implementation, the device is further used for:

[0037] If the time interval between the current time and the initial time reaches a preset time threshold, and / or the vehicle position coordinates at the current time are greater than the endpoint position coordinates of the target path planning result, multiple alternative paths are re-acquired.

[0038] The multiple alternative paths are optimized to determine and output new path planning results.

[0039] In one possible implementation, the device is further used for:

[0040] If the path optimization result at the current moment is unsolvable, then the path optimization result at the current moment is determined to meet the preset conditions.

[0041] In one possible implementation, the deviation includes at least one of lateral distance deviation, heading angle deviation, steering wheel angle deviation, and lateral acceleration deviation.

[0042] Thirdly, embodiments of this application provide a domain controller, including: a processor and a memory;

[0043] The memory stores computer-executed instructions;

[0044] The processor executes computer execution instructions stored in the memory to implement the path planning method as described in any of the first aspects.

[0045] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed, are used to implement the path planning method described in any of the first aspects.

[0046] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed, implements the path planning method described in any of the first aspects.

[0047] Sixthly, embodiments of this application provide a vehicle including the domain controller described in the third aspect.

[0048] The path planning method, apparatus, domain controller, storage medium, and vehicle provided in this application embodiment allow the vehicle to acquire the target path planning result from a historical time and the vehicle status information at the current time, with the time interval between the historical time and the current time within a preset time range. Based on the vehicle status information, the target path planning result is optimized to determine the optimized path result at the current time. If the optimized path result meets preset conditions, the target path planning result is then determined as the path planning result at the current time. In this application embodiment, when the optimized path result at the current time meets preset conditions, the vehicle directly uses the target path planning result from a historical time as the path planning result at the current time. This reuse of the target path planning result avoids path jumps in abnormal situations such as unsolvable path optimization, improving the safety and reliability of vehicle operation. Furthermore, when optimizing the path at the current time, the vehicle can perform optimization calculations only on the target path planning result determined at a historical time, reducing computational load, shortening computation time, and improving the real-time performance of path planning. Attached Figure Description

[0049] Figure 1 This is a flowchart illustrating a path planning process in a related technology.

[0050] Figure 2 A flowchart illustrating a path planning method provided in an embodiment of this application;

[0051] Figure 3 A flowchart illustrating another path planning method provided in an embodiment of this application;

[0052] Figure 4 A schematic diagram illustrating a passageway scenario provided in an embodiment of this application;

[0053] Figure 5 A logical schematic diagram of a path planning method provided in an embodiment of this application;

[0054] Figure 6 This is a schematic diagram of the structure of a path planning device provided in an embodiment of this application;

[0055] Figure 7 This is a schematic diagram of the structure of a domain controller provided in an embodiment of this application. Detailed Implementation

[0056] To enable those skilled in the art to better understand the technical solutions of this application, the application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments and drawings described herein are merely for explaining this application and are not intended to limit this application. The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0057] With the continuous development of technologies such as the Internet and artificial intelligence, autonomous driving technology is becoming increasingly mature. Autonomous vehicles can automatically perceive environmental information around the vehicle and plan a reasonable driving path based on this information.

[0058] During operation, autonomous vehicles may determine multiple paths based on environmental information. The intelligent modules of these vehicles can optimize each path individually to obtain a path planning result. For example, Figure 1 This is a flowchart illustrating a path planning process in a related technology. For example... Figure 1 As shown, when an autonomous vehicle performs path planning, it first determines multiple paths based on the acquired vehicle information, that is, determines the path boundaries corresponding to each path; then, the autonomous vehicle can optimize the multiple paths separately to determine the numerical solutions corresponding to each path; then, the autonomous vehicle can make path decisions to determine the optimal path planning result; finally, it can output the optimal path planning result and drive based on the optimal path planning result.

[0059] In related technologies, path optimization typically employs a secondary optimization approach to obtain an approximate numerical solution for the path. However, this approach has several drawbacks. First, because autonomous vehicles optimize multiple paths with numerous optimization objectives and inconsistent parameter settings, situations where no solution exists within certain scenarios or configuration spaces can arise, such as exceeding the maximum number of iterations or the initial solution being infeasible. This leads to unstable and inconsistent path generation, causing the autonomous vehicle to sway and become unstable, thus compromising driving safety. Second, the secondary optimization of each path consumes significant computational resources and is inefficient, increasing latency in the intelligent module, weakening the real-time performance of path planning, and causing weak correlation between optimization processes at different times, potentially leading to computational redundancy or duplication and consuming substantial computational resources.

[0060] In this embodiment, the autonomous vehicle acquires the target path planning results from historical moments and the vehicle status information at the current moment, with the time interval between the historical moment and the current moment within a preset time range. Based on the vehicle status information, the target path planning results are optimized to determine the optimized path result at the current moment. If the optimized path result meets preset conditions, the target path planning result is determined as the current path planning result. In this embodiment, when the optimized path result at the current moment meets preset conditions, the vehicle directly uses the target path planning results from historical moments as the current path planning result. By reusing the target path planning results, path jumps can be avoided in abnormal situations such as unsolvable path optimization, improving the safety and reliability of vehicle operation. Furthermore, when optimizing the path at the current moment, the vehicle can only perform optimization calculations on the target path planning results determined from historical moments, reducing computational load, shortening computation time, and improving the real-time performance of path planning.

[0061] The following detailed description of the solution presented in this application is provided through specific embodiments. It should be noted that the following embodiments may exist independently or in combination with each other; identical or similar content will not be repeated in different embodiments.

[0062] Figure 2 This is a flowchart illustrating a path planning method provided in an embodiment of this application. Please refer to [link / reference]. Figure 2 The path planning method may include:

[0063] S201. Obtain the target path planning results at historical moments and the vehicle status information at the current moment. The time interval between the historical moment and the current moment is within a preset time range.

[0064] The execution subject of this application embodiment can be an autonomous vehicle, or it can refer to an on-board computer, domain controller, automotive-grade chip, processor, etc. installed in an autonomous vehicle. Of course, it can also include remote servers such as cloud servers. This application embodiment does not limit this. In the following description, the execution subject is a vehicle (i.e., an autonomous vehicle).

[0065] In this embodiment of the application, the historical moment can refer to a moment before the current moment. The time interval between the historical moment and the current moment can be within a preset time range. The preset time range can refer to a pre-set time interval, specifically 50 milliseconds (ms), 100 milliseconds, 200 milliseconds, etc. This embodiment of the application does not limit this.

[0066] The target path planning result can refer to the path planning result determined at a historical moment. The path planning result can refer to a path composed of multiple waypoints. The specific information of each waypoint can include vehicle position, vehicle lateral speed, vehicle heading angle, etc. Vehicle status information can refer to relevant information at the current moment, such as vehicle current position, road boundaries, speed parameters, and information about obstacles around the vehicle.

[0067] In this step, the vehicle can obtain its own vehicle status information based on the positioning device, inertial measurement unit (IMU), radar, camera and other sensing devices at the current moment. At the same time, it can obtain the target path planning results determined at the previous time. Subsequently, it can determine whether to reuse the target path planning results based on the path optimization results at the current moment.

[0068] S202. Optimize the target path planning results based on vehicle status information and determine the path optimization result at the current moment.

[0069] In this embodiment of the application, the path optimization result at the current moment may refer to the result obtained after path optimization at the current moment. The path optimization result may be unsolvable or solvable.

[0070] In this step, after obtaining the vehicle's current status information and the target path planning results from previous times, the vehicle can perform secondary optimization on the target path planning results to determine the optimized path result for the current time. Thus, in multi-path scenarios, the vehicle only needs to optimize the target path planning result, reducing the computational load on the vehicle's intelligent modules, improving computational efficiency, and consequently shortening computation time and improving the real-time performance of path planning.

[0071] S203. If the path optimization result meets the preset conditions, the target path planning result shall be determined as the path planning result at the current moment.

[0072] In this embodiment of the application, the preset condition may refer to the condition for reusing the path planning result in advance. The preset condition may be that the path optimization result at the current time has no solution, or the path optimization result at the current time has a solution, but the deviation between this solution and the target path planning result determined at the historical time is large.

[0073] In this step, if the path optimization result at the current moment meets the preset conditions, the vehicle's path optimization process at this moment will either have no solution or have a solution but with a large deviation. This will cause the vehicle's path to change abruptly, leading to vehicle shaking and instability. At this time, the vehicle can use the target path planning result corresponding to the historical moment as the path planning result at the current moment. That is, the vehicle can reuse the target path planning result corresponding to the historical moment, which can ensure the continuity and stability of the vehicle's path planning and improve vehicle safety.

[0074] The path planning method provided in this application involves an autonomous vehicle acquiring the target path planning results from historical moments and the vehicle's current state information, with the time interval between the historical moments and the current moment within a preset time range. Based on the vehicle state information, the target path planning results are optimized to determine the optimized path result for the current moment. If the optimized path result meets preset conditions, the target path planning result is then determined as the current path planning result. In this application embodiment, when the optimized path result for the current moment meets preset conditions, the vehicle directly uses the target path planning results from historical moments as the current path planning result. This reuse of the target path planning results avoids path jumps in abnormal situations such as unsolvable path optimization, improving the safety and reliability of vehicle operation. Furthermore, when optimizing the path at the current moment, the vehicle can perform optimization calculations only on the target path planning results determined from historical moments, reducing computational load, shortening computation time, and improving the real-time performance of path planning.

[0075] Based on the above embodiments, Figure 3 This is a flowchart illustrating another path planning method provided in an embodiment of this application. Please refer to... Figure 3 The method may include:

[0076] S301. Obtain the target path planning results at historical moments and the vehicle status information at the current moment. The time interval between the historical moment and the current moment is within a preset time range.

[0077] S302. Optimize the target path planning results based on vehicle status information and determine the path optimization result at the current moment.

[0078] The specific implementation process of steps S301 and S302 can be referred to the aforementioned steps S201 and S202, and will not be repeated in this embodiment.

[0079] S303. If the path optimization result meets the preset conditions, the target path planning result shall be determined as the path planning result at the current moment.

[0080] In one possible implementation, prior to step S303, the path planning method may further include the following steps:

[0081] If the path optimization result at the current moment indicates that there is an alternative path planning result, determine the deviation between the alternative path planning result and the target path planning result; if the deviation is greater than a preset threshold, determine that the path optimization result at the current moment meets the preset conditions.

[0082] In this embodiment, the alternative path planning result can refer to the path optimization result obtained after path optimization at the current moment. Deviation can refer to the difference between the alternative path planning result and the target path planning result. The preset threshold can refer to a pre-set deviation threshold; since the path planning result includes multiple parameters, this preset threshold can refer to the threshold corresponding to each of the multiple parameters.

[0083] In this step, after the vehicle performs secondary optimization on the target path planning result based on the vehicle's state information at the current moment, if a solution exists, a candidate path planning result is obtained. The vehicle can compare this candidate path planning result with the target path planning result to determine the deviation between the two. If the deviation of at least one parameter between the candidate path planning result and the target path planning result is greater than a preset threshold, the vehicle can determine that the deviation between the candidate path planning result and the target path planning result is large, and the current path optimization result meets the preset conditions. If the vehicle directly follows the candidate path planning result, it will lead to vehicle instability and poor safety.

[0084] In one possible implementation, the deviation includes at least one of lateral distance deviation, heading angle deviation, steering wheel angle deviation, and lateral acceleration deviation.

[0085] In this embodiment, lateral distance deviation refers to the deviation between the candidate path planning result and the target path planning result in terms of the vehicle's lateral distance. This lateral distance can be the distance between the vehicle and parallel vehicles, the vehicle and oncoming vehicles, or the vehicle and a reference line. Heading angle deviation refers to the deviation between the candidate path planning result and the target path planning result in terms of the vehicle's heading angle. This heading angle can be the angle between the vehicle's center of gravity velocity and the lateral axis in a ground coordinate system. Steering wheel angle deviation refers to the deviation between the candidate path planning result and the target path planning result in terms of the steering wheel angle. This steering wheel angle can be the rotation angle of the vehicle's steering wheel. Lateral acceleration deviation refers to the deviation between the candidate path planning result and the target path planning result in terms of lateral acceleration. This lateral acceleration (vehicle lateral jerk value) can be the acceleration perpendicular to the vehicle's direction of travel, specifically the acceleration caused by centrifugal force generated when the vehicle is turning.

[0086] Of course, the deviation between the alternative path planning result and the target path planning result may also include other parameters, which can be flexibly set based on actual needs. This application embodiment does not limit this.

[0087] In one possible implementation, after step S302, the path planning method may further include the following steps:

[0088] If the path optimization result at the current moment is unsolvable, then the path optimization result at the current moment is determined to meet the preset conditions.

[0089] In this embodiment, when the vehicle performs secondary optimization of the target path planning result based on the vehicle's state information at the current moment, due to limitations such as optimization parameters, there may be a situation where the path optimization result is unsolvable. In this case, the vehicle's intelligent module has no numerical solution to output, resulting in path jumps, causing vehicle instability and low safety. When the vehicle's path optimization result at the current moment is unsolvable, it can be determined that the path optimization result at the current moment meets preset conditions.

[0090] In this embodiment of the application, if the path optimization result of the vehicle at the current moment is unsolvable, or if the path optimization result at the current moment is solvable but the alternative path planning result deviates significantly from the target path planning result, it can be determined that the path optimization result at the current moment meets the preset conditions. At this time, the vehicle can reuse the target path planning result from the previous moment, which can avoid path jumps, thereby avoiding vehicle instability or shaking and improving the safety of vehicle driving.

[0091] In practical applications, within a preset time range, autonomous vehicles can store data from one or more historical moments. Correspondingly, the number of target path planning results corresponding to each historical moment can also be one or more. At this point, the autonomous vehicle needs to determine the target path planning result that needs to be reused from at least one target path planning result. Based on this, to further improve path decision-making efficiency, in this embodiment, the autonomous vehicle can determine the final selected historical moment and the corresponding path planning result based on the confidence level of the target path planning results at each historical moment. Specifically, the path planning method may further include the following steps:

[0092] S304. Determine the timeliness parameters of the target path planning results based on the time interval between the historical time and the initial time.

[0093] In this embodiment, the initial time can refer to the starting time corresponding to the vehicle's movement according to the target path planning result. It should be noted that the time in this embodiment can correspond to a frame; the initial time can correspond to the initial frame, the historical time can correspond to a historical frame, and the current time can correspond to the current frame. The timeliness parameter can be used to characterize the timeliness of the target path planning result. Generally speaking, the larger the time interval between the historical time and the initial time, the closer the historical time is to the current time, and the higher the timeliness parameter of the target path planning result corresponding to the historical time. This embodiment does not limit the specific calculation method of the timeliness parameter.

[0094] S305. Determine the number of times the target path planning results can be reused.

[0095] In this embodiment, the reuse count can refer to the frequency with which the target route planning result is reused. After reusing the target route planning result, the vehicle can increment the reuse count of the target route planning result by one, thus enabling real-time updates to the reuse count of the target route planning result.

[0096] S306. Determine the confidence level of the target path planning results based on the timeliness parameters and the number of reuses.

[0097] In this embodiment, confidence level refers to the degree of credibility of the target route planning result. This confidence level can also be represented by other names, such as cost. After determining the timeliness parameter and the number of reuses, the vehicle can determine the confidence level of the target route planning result based on these two parameters. Generally, the higher the timeliness parameter (better timeliness) and the higher the number of reuses, the higher the confidence level of the target route planning result. The vehicle can use a weighted summation method to calculate the confidence level, that is, assigning different weights to the timeliness parameter and the number of reuses and then calculating the weighted sum of the two as the confidence level of the target route planning result. Of course, the vehicle can also use other methods to calculate the confidence level, and this embodiment does not limit this method.

[0098] S307. Within a preset time range, if the number of target path planning results is at least two, then the historical time and the target path planning result corresponding to the historical time are determined based on the confidence level.

[0099] In this embodiment of the application, if there are at least two target path planning results corresponding to historical moments within a preset time range, the vehicle can obtain the target path planning result with the highest confidence based on the confidence of the target path planning result, and at the same time, it can also determine the historical moment corresponding to the target path planning result with the highest confidence.

[0100] In this embodiment, the vehicle determines the timeliness parameter and reuse count of the target path planning result, and determines the confidence level corresponding to the target path planning result based on the timeliness parameter and reuse count. When there are two or more reusable target path planning results, the vehicle can obtain the target path planning result with the highest confidence level. This can improve the accuracy and real-time performance of the data and further improve the safety of vehicle driving.

[0101] In another possible implementation, autonomous vehicles can also determine historical moments and target path planning results in the following way:

[0102] SS1: Determine at least one historical moment and obtain the path planning results corresponding to each historical moment;

[0103] SS2: Determine the target path planning result from the path planning results of at least one historical moment.

[0104] In this embodiment, the target path planning result can refer to the path planning result determined by the autonomous vehicle for path optimization. The autonomous vehicle can acquire at least one historical moment and the corresponding target path planning result within a preset time range at the current moment. The autonomous vehicle can determine the target path planning result from the path planning results of at least one historical moment.

[0105] Specifically, in one possible embodiment, the autonomous vehicle can determine the target path planning result based on confidence level. This embodiment's method may include steps S304-S307, which will not be elaborated upon here.

[0106] In another possible embodiment, if the path planning results of the at least one historical moment meet the target preset condition, the path planning result of the historical moment with the smallest time interval to the current moment is taken as the target path planning result. Specifically, the similarity between the path planning results of the at least one historical moment can be determined, and the similarity can include the Euclidean distance between the fitted curves corresponding to the path planning results. Correspondingly, the target preset condition can include the similarity between any two pairs of the path planning results of the at least one historical moment being higher than a preset threshold. In this case, the path planning result of the historical moment closest to the current moment can be taken as the target path planning result.

[0107] Of course, in other embodiments, the autonomous vehicle can also directly use the historical moment with the smallest time interval from the current moment as the target historical moment. For example, if the autonomous vehicle has obtained the target path planning results of the previous 5 frames in the current frame, it can directly use the previous frame with the smallest time interval from the current frame as the target historical moment. Subsequently, the autonomous vehicle can optimize the target path planning results corresponding to the target historical moment based on the vehicle state information at the current moment. If the path optimization result at the current moment meets preset conditions, the autonomous vehicle can determine the target path planning result corresponding to the target historical moment as the path planning result at the current moment. This can improve the accuracy and flexibility of historical moment determination and improve vehicle stability.

[0108] S308. If the time interval between the current time and the initial time reaches a preset time threshold, and / or the vehicle position coordinates at the current time are greater than the endpoint position coordinates of the target path planning result, multiple alternative paths are re-acquired.

[0109] In this embodiment, the preset time threshold can refer to a pre-set time threshold. If the time interval between the current moment and the initial moment reaches the preset time threshold, the vehicle can determine that it has completed the current scenario (borrowing lanes, changing lanes, etc.) and needs to perform path optimization and path decision again.

[0110] Vehicle position coordinates can refer to the real-time position coordinates of the vehicle at the current moment. The destination position coordinates of the target path planning result can refer to the position coordinates corresponding to the last path point in the target path planning result. If the vehicle's current position coordinates are greater than the destination position coordinates of the target path planning result, the vehicle can be determined to have completely traveled the path represented by the target path planning result, and path optimization and decision-making need to be performed again.

[0111] In this step, in multi-path generation scenarios such as borrowing lanes, changing lanes, and parking on the side of the road, if the time interval between the current moment and the initial moment reaches a preset time threshold, and / or the vehicle's position coordinates at the current moment are greater than the target path planning result endpoint coordinates, the vehicle can determine that it has completed the current scenario, such as completing the borrowing lane process or the changing lane process. At this time, the vehicle can re-acquire multiple alternative paths and carry out subsequent path optimization and path decision-making processes.

[0112] S309. Optimize multiple alternative paths, determine and output new path planning results.

[0113] In this embodiment of the application, after the vehicle completes the current scenario, it can reacquire multiple alternative paths, optimize and decide on the multiple alternative paths, and determine a new and optimal path planning result, which can ensure the continuity and stability of the vehicle's driving.

[0114] For example, Figure 4 This is a schematic diagram illustrating a passageway scenario provided in an embodiment of this application. Figure 4 The scenario shown depicts an obstacle avoidance and lane-changing situation where the vehicle is ahead of an obstacle. The vehicle uses a path labeled "left" or "right," and there are no other obstacles in its direction of travel during the lane-changing process. In this scenario, the vehicle generates three paths based on the acquired state information: path 1 (left), path 2 (self), and path 3 (fallback). After making the lane-changing decision in frame 1 (the initial moment), the vehicle uses path 1 (the target path planning result). However, paths 2 and 3 also generate road boundary information and other relevant data, which are then sent to the vehicle's intelligent module (e.g., the optimizer).

[0115] In related technologies, for paths 1, 2, and 3, starting from the first frame, the vehicle needs to perform secondary optimization and path decision-making for these three paths in every frame (every moment). This consumes a lot of computational resources, takes a long time to compute, and is prone to situations where there is no solution, leading to vehicle instability and low safety.

[0116] In this embodiment, after the target path planning result is determined in the first frame (i.e., the vehicle determines that path 1 is the target path planning result), starting from the second frame, the vehicle only needs to perform secondary optimization on path 1. This reduces the computational load of the system and lowers the module computational latency. Simultaneously, starting from the second frame, the vehicle needs to determine whether to reuse the target path planning result from a previous time (i.e., the first frame) based on the path optimization result for path 1. When the path optimization result for path 1 is unsolvable, or when the path optimization result for path 1 is a candidate path planning result but deviates significantly from the target path planning result, the vehicle can determine that the path optimization result at the current time (the current frame) meets preset conditions, and the vehicle can reuse the target path planning result from a previous time. This ensures the stability of path usage, avoids path jumps, and improves the stability of vehicle driving. If the current frame reaches a value N (a preset positive integer), i.e., the time interval between the current time and the initial time reaches a preset time threshold, or the vehicle has completed the current lane-borrowing scenario, the vehicle can re-optimize the path and make a path decision, no longer following path 1.

[0117] Based on the above embodiments, Figure 5 This is a logical schematic diagram of a path planning method provided in an embodiment of this application. Figure 5 As shown, at a historical moment (e.g., the first frame or a certain historical frame), the vehicle acquires its own relevant state information and determines the road boundaries of multiple paths based on the relevant state information. Then, the vehicle can optimize the multiple paths separately, make path decisions, and determine the target path planning result.

[0118] At each current moment following a historical moment, the vehicle can obtain the target path planning result from the historical moment and acquire the vehicle's state information for the current moment. The vehicle can then determine the path boundaries of the target path planning result and perform secondary optimization based on the vehicle's state information to determine the optimized path result for the current moment. The vehicle can then determine whether the optimized path result for the current moment meets preset conditions. If it does, the vehicle can use the target path planning result as the current path planning result; if it does not meet the preset conditions, the vehicle can optimize other paths, re-determine the path, and output a new path planning result.

[0119] Thus, in this embodiment of the application, the vehicle can perform secondary optimization only on the target path planning result determined in the past at the current time, which can reduce the amount of computation and improve the real-time performance of path planning; at the same time, if the path optimization result at the current time has no solution or has a solution but the deviation is large, the vehicle can reuse the target path planning result from the past time, which can avoid path jumps and improve vehicle safety.

[0120] Figure 6 This is a schematic diagram of a path planning device provided in an embodiment of this application. Please refer to... Figure 6 The path planning device 60 may include:

[0121] The acquisition module 60 is used to acquire the target path planning results at historical moments and the vehicle status information at the current moment. The time interval between the historical moment and the current moment is within a preset time range.

[0122] The first determining module 61 is used to optimize the target path planning result based on vehicle status information and determine the path optimization result at the current moment.

[0123] The second determining module 62 is used to determine the target path planning result as the path planning result at the current moment if the path optimization result meets the preset conditions.

[0124] In one possible implementation, the device 60 is further used for:

[0125] If the current path optimization result indicates the existence of alternative path planning results, determine the deviation between the alternative path planning results and the target path planning results;

[0126] If the deviation is greater than the preset threshold, then the path optimization result at the current moment is determined to meet the preset conditions.

[0127] In one possible implementation, the device 60 is further configured to:

[0128] Based on the time interval between the historical moment and the initial moment, determine the timeliness parameters of the target path planning results;

[0129] Determine the number of times the target path planning results can be reused;

[0130] The confidence level of the target path planning results is determined based on the timeliness parameter and the number of reuses.

[0131] Within a preset time range, if the number of target path planning results is at least two, then the historical time and the target path planning result corresponding to the historical time are determined based on the confidence level.

[0132] In one possible implementation, the device 60 is further configured to:

[0133] If the time interval between the current time and the initial time reaches a preset time threshold, and / or the vehicle position coordinates at the current time are greater than the endpoint position coordinates of the target path planning result, multiple alternative paths are re-acquired.

[0134] Optimize multiple alternative paths, determine and output new path planning results.

[0135] In one possible implementation, the device 60 is further configured to:

[0136] If the path optimization result at the current moment is unsolvable, then the path optimization result at the current moment is determined to meet the preset conditions.

[0137] In one possible implementation, the deviation includes at least one of lateral distance deviation, heading angle deviation, steering wheel angle deviation, and lateral acceleration deviation.

[0138] The path planning device 60 provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0139] Figure 7 This is a schematic diagram of a domain controller provided in an embodiment of this application. The domain controller (DCU) is an electronic device composed of a main control chip, operating system and middleware, application algorithm software, and other hardware and software components. The main control chip is the core of the domain controller, primarily consisting of a heterogeneous SoC (System-on-a-Chip) integrating a CPU and an XPU (XPU includes GPU / FPGA / ASIC, etc.), meaning that a CPU, DSP, ISP, ASIC, GPU, FPGA, and other processors are integrated on a single chip to support hardware acceleration requirements in various scenarios. The software operating system and middleware employ a complex embedded operating system, including a system kernel, basic software, and middleware, responsible for the rational allocation of hardware resources to ensure the orderly operation of various intelligent functions. The application algorithms are software programs independently developed based on the operating system, including perception algorithms, prediction algorithms, path planning algorithms, control algorithms, etc. The methods proposed in the various embodiments of this application belong to the path planning algorithm category within application algorithms.

[0140] Please see details. Figure 7 The domain controller 70 may include a memory 71 and a processor 72. Exemplarily, the memory 71 and the processor 72 are interconnected via a bus 73.

[0141] Memory 71 is used to store program instructions;

[0142] The processor 72 is used to execute the program instructions stored in the memory to implement the path planning method shown in the above embodiments.

[0143] Figure 7 The domain controller shown in the embodiments can execute the technical solutions shown in the above method embodiments. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0144] This application provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above-described path planning method when executed by a processor.

[0145] This application embodiment may also provide a computer program product, including a computer program that, when executed by a processor, can implement the above-described path planning method.

[0146] This application embodiment may also provide a vehicle including the aforementioned domain controller.

[0147] This application provides a chip that stores a computer program. When the computer program is executed by the chip, the above-described path planning method is implemented.

[0148] It should be noted that the processor mentioned in the embodiments of this application can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0149] It should be understood that the memory mentioned in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct RAM Bus RAM (DR RAM). It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) is integrated into the processor. It should be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0150] It should be understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0151] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processing unit of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0152] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0153] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0154] Regarding the modules / units included in the various devices and products described in the above embodiments, they can be software modules / units, hardware modules / units, or a combination of both. Each device and product can be applied to or integrated into a chip, chip module, or terminal device. For example, for devices and products applied to or integrated into a chip, each included module / chip can be implemented entirely using hardware methods such as circuits, or at least some modules / units can be implemented using software programs running on a processor integrated within the chip, while the remaining modules / units can be implemented using hardware methods such as circuits.

[0155] In this application, the term "comprising" and its variations can refer to non-limiting inclusion; the term "or" and its variations can refer to "and / or". The terms "first", "second", etc., in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. In this application, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0156] The above are only some embodiments of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A path planning method, characterized in that, include: Obtain the target path planning results at a historical moment and the vehicle status information at the current moment, wherein the time interval between the historical moment and the current moment is within a preset time range; Based on the vehicle status information, the target path planning result is optimized to determine the path optimization result at the current moment; If the path optimization result meets the preset conditions, then the target path planning result is determined as the path planning result at the current moment; If the current path optimization result indicates the existence of alternative path planning results, determine the deviation between the alternative path planning results and the target path planning results; If the deviation is greater than a preset threshold, then the path optimization result at the current moment is determined to meet the preset conditions; If the path optimization result at the current moment is unsolvable, then the path optimization result at the current moment is determined to meet the preset conditions. The method further includes: The timeliness parameters of the target path planning results are determined based on the time interval between the historical time and the initial time. Determine the number of times the target path planning results can be reused; The confidence level of the target path planning result is determined based on the timeliness parameter and the number of reuses. Within the preset time range, if the number of target path planning results is at least two, then the historical time and the target path planning result corresponding to the historical time are determined based on the confidence level.

2. The method according to claim 1, characterized in that, The method further includes: If the time interval between the current time and the initial time reaches a preset time threshold, and / or the vehicle position coordinates at the current time are greater than the endpoint position coordinates of the target path planning result, multiple alternative paths are re-acquired. The multiple alternative paths are optimized to determine and output new path planning results.

3. The method according to claim 1, characterized in that, The deviation includes at least one of the following: lateral distance deviation, heading angle deviation, steering wheel angle deviation, and lateral acceleration deviation.

4. A path planning device, characterized in that, include: The acquisition module is used to acquire the target path planning results at a historical time and the vehicle status information at the current time, wherein the time interval between the historical time and the current time is within a preset time range; The first determining module is used to optimize the target path planning result based on the vehicle status information and determine the path optimization result at the current moment; The second determining module is used to determine the target path planning result as the path planning result at the current moment if the path optimization result meets the preset conditions. If the current path optimization result indicates the existence of alternative path planning results, determine the deviation between the alternative path planning results and the target path planning results; If the deviation is greater than a preset threshold, then the path optimization result at the current moment is determined to meet the preset conditions; If the path optimization result at the current moment is unsolvable, then the path optimization result at the current moment is determined to meet the preset conditions. The timeliness parameters of the target path planning results are determined based on the time interval between the historical time and the initial time. Determine the number of times the target path planning results can be reused; The confidence level of the target path planning result is determined based on the timeliness parameter and the number of reuses. Within the preset time range, if the number of target path planning results is at least two, then the historical time and the target path planning result corresponding to the historical time are determined based on the confidence level.

5. A domain controller, characterized in that, include: Processor, memory; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the path planning method as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed, are used to implement the path planning method according to any one of claims 1 to 3.

7. A vehicle, characterized in that, Includes the domain controller as described in claim 5.

Images