A path planning method, apparatus, storage medium, and electronic device

Abstract

This application discloses a path planning method, apparatus, storage medium, and electronic device. The method includes: obtaining a first original reference route based on the vehicle's current first driving parameter information, the vehicle's global path planning route, and a preset high-precision map, covering the distance range between the vehicle's front and rear targets; smoothing the first original reference route using a preset optimization algorithm to obtain a first smoothed route, thus obtaining the path planning result for the vehicle's first operating segment; when the vehicle is traveling in a second operating segment, if a smoothed route for the second operating segment cannot be calculated, or if the curvature value of the second smoothed route obtained through smoothing exceeds a preset threshold, controlling the vehicle to stop and using the first smoothed route as the path planning result for the second operating segment. The method in this application can control the vehicle to stop and rationally plan a driving path to continue driving when the vehicle encounters obstacles or when the vehicle's turning curvature is too large.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a path planning method, apparatus, storage medium, and electronic device. Background Technology

[0002] In recent years, the field of autonomous driving has developed rapidly. To ensure the safety of autonomous vehicles during operation, research into autonomous driving technology is of particular significance. An autonomous driving system mainly consists of three technical modules: environmental perception, decision-making and planning, and motion control. Among these, decision-making and planning involves formulating reasonable driving strategies based on the current driving environment of the autonomous vehicle and planning a safe driving route.

[0003] U-turns are a typical scenario for autonomous vehicles. Making a U-turn takes longer and is more difficult than turning left, right, or going straight. While the autonomous driving system can plan a path during a U-turn, when the path curvature is large or the steering angle is significant, even if a U-turn path is successfully planned, the control module's tracking performance deteriorates due to the continuous large steering angles. This results in significant lateral and directional deviations during vehicle movement, leading to repeated braking or even complete stopping, thus causing path planning failure. Therefore, path planning methods in U-turn scenarios are crucial for the realization of autonomous driving. Summary of the Invention

[0004] In view of this, the present invention provides a path planning method, apparatus, storage medium, and electronic device, the main purpose of which is to solve the problem of path planning failure caused by lateral position deviation and heading deviation during vehicle U-turns.

[0005] To address the above problems, this application provides a path planning method, comprising:

[0006] Based on the vehicle's current first driving parameter information, the vehicle's global path planning route, and a preset high-precision map, the target distance range in front of and behind the vehicle is obtained, so as to obtain a first original reference route based on the target distance range.

[0007] The first original reference route is smoothed using a preset optimization algorithm to obtain a first smoothed route, thereby obtaining the path planning result for the first running segment of the vehicle.

[0008] When the vehicle is traveling in the second operating segment, if it is impossible to calculate a smooth route for the second operating segment based on the vehicle's driving parameter information, or if the curvature value of the second smooth route corresponding to the second operating segment obtained through smoothing exceeds a preset threshold, the vehicle will be stopped and the first smooth route will be used as the path planning result for the second operating segment.

[0009] Optionally, the step of obtaining the target distance ranges before and after the vehicle based on the vehicle's current first driving parameter information, the vehicle's global path planning route, and a preset high-precision map, and obtaining the first original reference route based on the target distance range, specifically includes:

[0010] Using a preset positioning system and a preset carrier differential phase calculation method, the first driving parameter information of the vehicle entering the first running stage is obtained. The first driving parameter information includes one or more of the following: three-dimensional geodetic coordinates, timestamp, roll angle, pitch angle, yaw angle, heading, linear velocity, angular velocity, linear acceleration, gear, driving mode, and steering percentage.

[0011] Obtain the vehicle's global path planning route;

[0012] The vehicle's first driving parameter information is continuously updated on the preset high-precision map to determine that the vehicle is on a drivable target road of the global path planning route.

[0013] Obtain the distance range of targets in front of and behind the vehicle;

[0014] Acquire a number of first reference points corresponding to the target distance range, wherein the target distance range includes: a first preset distance in the forward direction of travel and a second preset distance in the backward direction of travel;

[0015] The first original reference route is determined based on each of the first reference points.

[0016] Optionally, the first original reference route is smoothed using a preset optimization algorithm to obtain a first smoothed route, specifically including:

[0017] Anchor points are collected at preset intervals along the original reference route to obtain several first anchor points and first initial coordinate values ​​corresponding to each first anchor point.

[0018] At least based on each of the initial coordinate values ​​and the target cost function with preset constraints, a smoothing calculation is performed to obtain the first smoothed coordinate values ​​corresponding to each of the first initial coordinate values.

[0019] Based on each of the first smoothed coordinate values, a first smoothed route is determined, and the path planning result for the first running segment of the vehicle is obtained.

[0020] Optionally, the smoothing calculation process, based at least on each of the initial coordinate values ​​and a preset target cost function with preset constraints, to obtain a first smoothed coordinate value corresponding to each of the first initial coordinate values, specifically includes:

[0021] Set the parameter information corresponding to each anchor point, and the parameter information includes at least: lateral margin parameter value, longitudinal margin parameter value, and whether it is a strong constraint;

[0022] Based on the lateral margin parameter value and the preset lateral margin coefficient value, the lateral margin contraction value is calculated.

[0023] Based on the lateral margin shrinkage value, the maximum and minimum lateral margin values ​​corresponding to each anchor point are calculated.

[0024] Based on each of the first initial coordinate values, the maximum lateral margin, the minimum lateral margin, the maximum preset longitudinal margin, and the minimum preset longitudinal margin, the preset constraint conditions are constructed.

[0025] Based on each of the first initial coordinate values, the target cost function with the preset constraints is smoothed to obtain the first smoothed coordinate values ​​corresponding to each of the first initial coordinate values.

[0026] Optionally, when the vehicle is traveling in the second operating segment, if a smooth route for the second operating segment cannot be calculated based on the vehicle's driving parameter information, or if the curvature value of the smoothed route corresponding to the second operating segment obtained through smoothing exceeds a preset threshold, the system controls the vehicle to stop and uses the first smoothed route as the path planning result for the second operating segment. Specifically, this includes:

[0027] Obtain the current second driving parameter information of the vehicle after it leaves the first driving segment;

[0028] Acquire several second reference points corresponding to the target distance range in front of and behind the vehicle, and determine the second original reference route based on each second reference point;

[0029] Anchor points are collected at preset intervals along the second original reference route to obtain several second anchor points and second initial coordinate values ​​corresponding to each second anchor point.

[0030] At least based on each of the second initial coordinate values ​​and the target cost function with preset constraints, a smoothing calculation is performed to obtain the second smoothed coordinate values ​​corresponding to each of the second initial coordinate values.

[0031] The second smoothing route for the second runtime segment is determined based on each of the second smoothing coordinate values;

[0032] When the vehicle encounters an obstacle or the curvature of the second smooth route exceeds a preset threshold, the vehicle is stopped and the first smooth route is used as the path planning result for the second running segment.

[0033] Optionally, after smoothing the first original reference route using a preset optimization algorithm to obtain a first smoothed route, the method further includes:

[0034] Store the first smooth route in a preset storage area;

[0035] When the second smooth route meets the preset conditions, the first smooth route in the preset storage area is updated based on the second smooth route to obtain the path planning result of the second runtime segment.

[0036] Optionally, before performing smoothing calculation on the target cost function with the preset constraints based on each of the first initial coordinate values ​​to obtain the first smoothed coordinate values ​​corresponding to each of the first initial coordinate values, the method further includes: constructing the target cost function, specifically including:

[0037] Construct a smoothness cost function, a length cost function, and a deviation cost function relative to the original reference point;

[0038] The target cost function is constructed based on the smoothness cost function, the length cost function, and the deviation cost function.

[0039] To address the above problems, this application provides a path planning device, comprising:

[0040] Acquisition module: used to acquire the target distance range in front of and behind the vehicle based on the vehicle's current first driving parameter information, the vehicle's global path planning route and a preset high-precision map, so as to obtain the first original reference route based on the target distance range;

[0041] First path planning module: used to smooth the first original reference route using a preset optimization algorithm to obtain a first smooth route, so as to obtain the path planning result of the vehicle's first running segment;

[0042] The second path planning module is used to control the vehicle to stop and use the first smooth route as the path planning result for the second running segment when the vehicle is traveling in the second running segment and cannot calculate a smooth route for the second running segment based on the vehicle driving parameter information, or when the curvature value of the second smooth route corresponding to the second running segment obtained through smoothing exceeds a preset threshold.

[0043] To address the aforementioned problems, this application provides a storage medium storing a computer program that, when executed by a processor, implements the steps of the path planning method described above.

[0044] To address the aforementioned problems, this application provides an electronic device, comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program in the memory, implements the steps of the path planning method described above.

[0045] This application obtains the target distance ranges before and after the vehicle based on the vehicle's current first driving parameter information, the vehicle's global path planning route, and a preset high-precision map, and obtains a first original reference route based on the target distance range. A preset optimization algorithm is then used to smooth the first original reference route to obtain a first smoothed route, thus obtaining the path planning result for the vehicle's first operating segment. When the vehicle is traveling in a second operating segment, if a smoothed route for the second operating segment cannot be calculated based on the vehicle's driving parameter information, or if the curvature value of the second smoothed route obtained through smoothing exceeds a preset threshold, the vehicle is controlled to stop, and the first smoothed route is used as the path planning result for the second operating segment. The path planning method in this application can reasonably plan a driving path when the vehicle encounters obstacles or when the vehicle's turning curvature is too large, enabling the autonomous vehicle to smoothly complete a U-turn and continue driving.

[0046] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0047] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0048] Figure 1 A flowchart illustrating a path planning method provided in an embodiment of this application is shown.

[0049] Figure 2 A flowchart illustrating another path planning method provided in an embodiment of this application is shown;

[0050] Figure 3 A schematic diagram of the first original reference route obtained according to an embodiment of this application is shown;

[0051] Figure 4 A schematic diagram of the first smooth route obtained according to an embodiment of this application is shown;

[0052] Figure 5A structural block diagram of a path planning device provided in an embodiment of this application is shown. Detailed Implementation

[0053] Various embodiments and features of this application are described herein with reference to the accompanying drawings.

[0054] It should be understood that various modifications can be made to the embodiments described herein. Therefore, the above description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope and spirit of this application will be apparent to those skilled in the art.

[0055] The accompanying drawings, which are included in and form part of this specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0056] These and other features of this application will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.

[0057] It should also be understood that although this application has been described with reference to some specific examples, those skilled in the art can certainly implement many other equivalent forms of this application.

[0058] The above and other aspects, features and advantages of this application will become more apparent when taken in conjunction with the accompanying drawings and in view of the following detailed description.

[0059] Specific embodiments of this application are described thereafter with reference to the accompanying drawings; however, it should be understood that the claimed embodiments are merely examples of this application, which can be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that could obscure the application. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but merely serve as the basis and representative basis for the claims to teach those skilled in the art to use this application in a variety of substantially any suitable detailed structures.

[0060] This specification may use the phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in other embodiments,” all of which may refer to one or more of the same or different embodiments according to this application.

[0061] This application provides a path planning method, such as... Figure 1 As shown, it includes:

[0062] Step S101: Based on the vehicle's current first driving parameter information, the vehicle's global path planning route, and the preset high-precision map, obtain the target distance range in front of and behind the vehicle, and obtain the first original reference route based on the target distance range;

[0063] In this step, a positioning module and a CAN bus module can be used to obtain the vehicle's current first driving parameter information. This first driving parameter information includes: the vehicle's three-dimensional geodetic coordinates, timestamp, roll angle, pitch angle, yaw angle, heading, linear velocity, angular velocity, linear acceleration, gear position, driving mode, steering percentage, etc. The positioning module in this application can be the vehicle's positioning system, such as a Global Positioning System (GPS), a combined inertial navigation system, or a high-precision map, used to determine the vehicle's location and its drivable area. A routing module is used to obtain the vehicle's global path planning route, which provides a reference for the local path planning in this application. The first driving parameter information of the vehicle is continuously updated on the preset high-precision map to determine if the vehicle is on a drivable target road; the vehicle status is updated in the high-precision map, and it is determined whether the vehicle is on a drivable road in the high-precision map; if the vehicle is not on a drivable road, the vehicle status is updated until the vehicle is on a drivable road. Obtain the target distance range in front of and behind the vehicle; obtain several first reference points corresponding to the target distance range, the target distance range including: a first preset distance in the forward direction and a second preset distance in the backward direction; determine the first original reference route based on each of the first reference points. Specifically, connect each of the first reference points with a straight line to obtain the first original reference route.

[0064] Step S102: The first original reference route is smoothed using a preset optimization algorithm to obtain a first smoothed route, so as to obtain the path planning result of the vehicle's first running segment.

[0065] In this step, anchor points are collected at preset intervals along the original reference route to obtain several first anchor points and corresponding first initial coordinate values. Specifically, anchor points are collected at preset intervals along the first original reference route. Each anchor point contains parameters such as lateral margin parameter value, longitudinal margin parameter value, and whether it is a strong constraint. Among the first anchor points, the first and last two anchor points are strong constraints, and the lateral margin and longitudinal margin values ​​corresponding to the first and last anchor points are both 0m. Smoothing calculation is performed based at least on each of the initial coordinate values ​​and the target cost function with preset constraints to obtain first smoothed coordinate values ​​corresponding to each of the first initial coordinate values. Specifically, the parameter information corresponding to each of the first anchor points is first read, and the lateral margin contraction value is calculated based on the lateral margin and the preset lateral margin coefficient value. Each of the first initial coordinate values ​​and the lateral margin contraction value are input into a preset smoothing solver, and the target cost function with preset constraints is smoothed to obtain first smoothed coordinate values ​​corresponding to each of the first initial coordinate values. Based on each of the first smoothed coordinate values, a first smoothed route is determined, and the path planning result for the first running segment of the vehicle is obtained.

[0066] Step S103: When the vehicle is traveling in the second operating segment, if it is impossible to calculate a smooth route for the second operating segment based on the vehicle driving parameter information, or if the curvature value of the second smooth route corresponding to the second operating segment obtained through smoothing exceeds a preset threshold, the vehicle is stopped and the first smooth route is used as the path planning result for the second operating segment.

[0067] In the specific implementation process of this step, the methods in steps S101 and S102 are used to obtain the second smooth route when the vehicle leaves the first running segment, that is, when it runs into the second running segment. When the vehicle encounters an obstacle in the second running segment and cannot obtain a smooth route, or when the curvature value of the second smooth route obtained by calculation exceeds a preset threshold, the vehicle is controlled to stop and the first smooth route is used as the path planning result of the second running segment.

[0068] This application obtains the target distance ranges before and after the vehicle based on the vehicle's current first driving parameter information, the vehicle's global path planning route, and a preset high-precision map, and obtains a first original reference route based on the target distance range. A preset optimization algorithm is then used to smooth the first original reference route to obtain a first smoothed route, thus obtaining the path planning result for the vehicle's first operating segment. When the vehicle is traveling in a second operating segment, if a smoothed route for the second operating segment cannot be calculated based on the vehicle's driving parameter information, or if the curvature value of the second smoothed route obtained through smoothing exceeds a preset threshold, the vehicle is controlled to stop, and the first smoothed route is used as the path planning result for the second operating segment. The path planning method in this application can reasonably plan a driving path when the vehicle encounters obstacles or when the vehicle's turning curvature is too large, enabling the autonomous vehicle to smoothly complete a U-turn and continue driving.

[0069] Another embodiment of this application provides another path planning method, such as Figure 2 As shown, it includes:

[0070] Step S201: Based on the vehicle's current first driving parameter information, the vehicle's global path planning route, and the preset high-precision map, obtain several first reference points within the target distance range in front of and behind the vehicle;

[0071] In this step, a preset positioning system and a preset carrier differential phase calculation method are used to obtain the first driving parameter information of the vehicle entering the first operating phase. The first driving parameter information includes one or more of the following: three-dimensional geodetic coordinates, timestamp, roll angle, pitch angle, yaw angle, heading, linear velocity, angular velocity, linear acceleration, gear position, driving mode, and steering percentage. The current first driving parameter information of the vehicle can be obtained using a positioning module and a CAN bus module. The positioning module in this application can be the vehicle's positioning system, such as a global positioning system, a combined inertial navigation system, or a high-precision map, used to determine the vehicle's location and its drivable area. The vehicle's global path planning route is obtained; this global path planning route provides a reference for the local path planning in this application. The global path planning route is as follows: Figure 3As shown, the thin white line 1 represents the global path planning route. The vehicle's first driving parameter information is continuously updated on the preset high-precision map to determine if the vehicle is on a drivable target road; the vehicle status is updated in the high-precision map, and it is determined whether the vehicle is on a drivable road in the high-precision map; if the vehicle is not on a drivable road, the vehicle status is updated until the vehicle is on a drivable road. The target distance ranges before and after the vehicle are obtained; several first reference points corresponding to the target distance ranges are obtained, the target distance ranges including: a first preset distance in the forward direction and a second preset distance in the backward direction; for example: several first reference points on the road reference line within the range of the first preset distance Lf = 150m in the forward direction and the second preset distance Lr = 50m in the backward direction are obtained from the high-precision map.

[0072] Step S202: Determine the first original reference route based on each of the first reference points;

[0073] In this step, the first reference points are connected by straight lines to obtain the first original reference route. The first original reference route obtained in this step is as follows: Figure 3 As shown, the thick black line 2 represents the first original reference route. The length of the thick black line in front of the vehicle is 150m, and the length of the thick black line behind the vehicle is 50m. In the actual implementation process, the first preset distance and the second preset distance can be adjusted according to actual needs. It can be seen that the shape of the first original reference route before smoothing is jagged, which does not meet the requirements for vehicle driving. This lays the foundation for the subsequent collection of anchor points on the first original reference route.

[0074] Step S203: On the first original reference route, anchor points are collected at preset intervals to obtain a number of first anchor points and the first initial coordinate values ​​corresponding to each first anchor point;

[0075] In this step, anchor points are collected at preset intervals along the original reference route. For example, anchor points are collected every 1 meter. When the first preset distance Lf = 150 meters and the second preset distance Lr = 50 meters in the direction of travel, the length of the first original reference route is 200 meters. Anchor points are collected every 1 meter, resulting in 200 first anchor points. The first initial coordinate values ​​corresponding to these 200 first anchor points are then obtained.

[0076] Step S204: Set the parameter information corresponding to each of the first anchor points. The parameter information includes at least the lateral margin parameter value, the longitudinal margin parameter value, and whether it is a strong constraint.

[0077] In this step, the first and last anchor points are set as strong constraints with 0m in both lateral and longitudinal margins. The lateral margin parameter values ​​and longitudinal margin parameter values ​​of the remaining anchor points are the same, set according to actual needs.

[0078] Step S205: Calculate the lateral margin contraction value based on the lateral margin parameter value and the preset lateral margin coefficient value;

[0079] In this step, the lateral margin coefficient value k can be 0.8, and the value of the lateral margin coefficient can be set according to actual needs. Setting the lateral margin coefficient value can make the path planning results more accurate.

[0080] Step S206: Based on the lateral margin shrinkage value, set the maximum and minimum lateral margin values ​​corresponding to each anchor point;

[0081] In the specific implementation of this step, the smaller the minimum lateral margin, the better. It can be set to 0.05m, 0.1m, etc. The minimum lateral margin can be set according to actual needs. The maximum lateral margin is less than or equal to half the vehicle width and less than the difference between half the road width and half the vehicle width.

[0082] Step S207: Based on each of the first initial coordinate values, the maximum value of the lateral margin, the minimum value of the lateral margin, the maximum value of the preset longitudinal margin, and the minimum value of the preset longitudinal margin, the preset constraint conditions are constructed.

[0083] In the specific implementation process of this step, the preset constraints are as shown in the following formula (1):

[0084]

[0085] Wherein, each of the first initial coordinates is (x i_ref y i_ref ), x max For maximum lateral margin, x min For minimum lateral margin, y max For maximum longitudinal margin, y min This represents the minimum longitudinal margin. For example, setting the maximum lateral margin relative to the road centerline in the smoother to x. max =0.4m, minimum lateral margin value is x min =0.1m; the maximum longitudinal margin is y max =1.2m, minimum longitudinal margin value is y min =0.5m. The resulting constraint conditions are shown in Formula 5 below:

[0086]

[0087] Where, x max x min y max y min The specific values ​​can be set according to actual needs based on the actual vehicle width and road width parameters.

[0088] Step S208: Construct the target cost function;

[0089] In the specific implementation process of this step, a smoothness cost function, a length cost function, and a deviation cost function relative to the first initial coordinate value are constructed; specifically, the smoothness cost function is as shown in the following formula (2):

[0090]

[0091] The length cost function is shown in the following formula (3):

[0092]

[0093] The deviation cost function relative to the first initial coordinate value is shown in the following formula (4):

[0094]

[0095] In formulas (2) to (4), the value n represents the number of anchor points, where (x i y i ) represents the smoothed coordinate value after smoothing. The target cost function is constructed based on the smoothness cost function, the length cost function, and the deviation cost function. The formula for the target cost function is shown in formula (5) below:

[0096] cost = cost1 + cost2 + cost3

[0097] Step S209: Perform smoothing calculation on the target cost function with the preset constraints based on each of the first initial coordinate values ​​to obtain the first smoothed coordinate values ​​corresponding to each of the first initial coordinate values;

[0098] In this step, each of the first initial coordinate values ​​is substituted into the objective function shown in formula (5) above, which has the constraints described in formula (1) above. After smoothing optimization, the first smoothed coordinate values ​​corresponding to each of the first initial coordinate values ​​are obtained. The preset optimization algorithm used in this application can be a smoothing optimization algorithm such as the interior point method, the active set method, or Newton's method.

[0099] Step S210: Determine the first smoothing route based on each of the first smoothing coordinate values;

[0100] In this step, the points corresponding to each of the first smoothed coordinate values ​​are connected to obtain the first smoothed route. For example... Figure 4 As shown, the thick black line 3 represents the first smooth path.

[0101] Step S211: Store the first smooth route in a preset storage area;

[0102] In the specific implementation process of this step, the first smoothed route is stored. If the smoothing result of the smoothed route can be successfully solved in each subsequent runtime segment, the smoothing result of the latest smoothed route is stored in the preset storage area.

[0103] Step S212: When the vehicle is traveling in the second running segment, if it is impossible to calculate a smooth route for the second running segment based on the vehicle driving parameter information, or if the curvature value of the second smooth route corresponding to the second running segment obtained through smoothing exceeds a preset threshold, control the vehicle to stop and use the first smooth route as the path planning result for the second running segment.

[0104] In the specific implementation process, this step obtains the current second driving parameter information of the vehicle after it leaves the first driving segment;

[0105] The system acquires several second reference points corresponding to the target distance ranges in front of and behind the vehicle, and determines a second original reference route based on each second reference point. Anchor points are collected at preset intervals along the second original reference route to obtain several second anchor points and corresponding second initial coordinate values. Smoothing calculations are performed based at least on each of the second initial coordinate values ​​and a target cost function with preset constraints to obtain second smoothed coordinate values ​​corresponding to each of the second initial coordinate values. A second smoothed route for the second running segment is determined based on each of the second smoothed coordinate values. When the vehicle encounters an obstacle or the curvature of the second smoothed route exceeds a preset threshold, the system stops and uses the first smoothed route as the path planning result for the second running segment. This application can use sensors such as lidar, cameras, millimeter-wave radar, and ultrasonic radar to detect obstacles around the vehicle. If the driving reference path is not smooth due to the presence of obstacles, excessive curvature during U-turns, or excessive curvature of the smoothed reference line, failing to meet the dynamic requirements of vehicle driving, and the vehicle cannot drive on the path, then the smoothed reference route successfully smoothed in the previous time period is used as the local path planning result for the second running segment.

[0106] Step S213: When the vehicle reaches the second running segment, and the second smoothed route obtained through smoothing meets the preset conditions, the first smoothed route in the preset storage area is updated based on the second smoothed route to obtain the path planning result of the second running segment.

[0107] In this step, the following steps are implemented: First, the current second driving parameter information of the vehicle after it leaves the first running segment is obtained. Second, several second reference points corresponding to the target distance ranges before and after the vehicle are obtained, and a second original reference route is determined based on each second reference point. Anchor points are collected on the second original reference route at preset intervals to obtain several second anchor points and corresponding second initial coordinate values. Smoothing calculations are performed based at least on each of the second initial coordinate values ​​and a target cost function with preset constraints to obtain second smoothed coordinate values ​​corresponding to each of the second initial coordinate values. A second smoothed route for the second running segment is determined based on each of the second smoothed coordinate values. When the second smoothed route is less than or equal to a preset threshold, a first smoothed route in a preset storage area is updated based on the second smoothed route to obtain the path planning result for the second running segment.

[0108] This application obtains the target distance range before and after the vehicle based on the vehicle's current first driving parameter information, the vehicle's global path planning route, and a preset high-precision map. A first original reference route is obtained based on several first reference points within the target distance range. Anchor points are collected at preset intervals along the first original reference route, and constraints and an objective function for a smoothing optimization algorithm are constructed. The objective function with constraints is solved using the coordinate values ​​corresponding to each first anchor point to obtain smoothed coordinate values ​​corresponding to each anchor point. This yields a first smooth curve corresponding to the first running segment. When the second smooth curve obtained in the second running segment meets preset conditions, the first smooth curve stored in a preset storage area is updated with the second smooth curve to obtain the path planning result for the second time segment. If the curvature of the second smooth curve does not meet preset conditions, or if the second smooth curve cannot be obtained due to obstacles in the second running segment, the vehicle is stopped, and the first smooth curve in the preset storage area is used as the path planning result for the second running segment for path planning. The path planning method in this application can reasonably plan a driving path when the vehicle encounters obstacles or when the turning radius is too large, enabling the autonomous vehicle to smoothly complete a U-turn and continue driving.

[0109] This application provides a path planning device, such as... Figure 5 As shown, it includes:

[0110] Acquisition Module 1: Used to acquire the target distance range in front of and behind the vehicle based on the vehicle's current first driving parameter information, the vehicle's global path planning route and a preset high-precision map, so as to obtain a first original reference route based on the target distance range;

[0111] First path planning module 2: used to smooth the first original reference route using a preset optimization algorithm to obtain a first smooth route, so as to obtain the path planning result of the vehicle's first running segment;

[0112] The second path planning module 3 is used to control the vehicle to stop and use the first smooth route as the path planning result for the second running segment when the vehicle is traveling in the second running segment and cannot calculate a smooth route for the second running segment based on the vehicle driving parameter information, or when the curvature value of the second smooth route corresponding to the second running segment obtained through smoothing exceeds a preset threshold.

[0113] In specific implementation, the acquisition module 1 is specifically used to: obtain first driving parameter information of the vehicle entering the first running segment using a preset positioning system and a preset carrier differential phase calculation method. The first driving parameter information includes one or more of the following: three-dimensional geodetic coordinates, timestamp, roll angle, pitch angle, yaw angle, heading, linear velocity, angular velocity, linear acceleration, gear, driving mode, and steering percentage; obtain the vehicle's global path planning route; continuously update the vehicle's first driving parameter information on the preset high-precision map to determine that the vehicle is on a drivable target road of the global path planning route; obtain the target distance range before and after the vehicle; obtain several first reference points corresponding to the target distance range, the target distance range including: a first preset distance in the forward direction and a second preset distance in the backward direction; and determine the first original reference route based on each of the first reference points.

[0114] In the specific implementation process, the first path planning module 2 is specifically used to: collect anchor points at preset intervals on the original reference route to obtain a number of first anchor points and first initial coordinate values ​​corresponding to each first anchor point; perform smoothing calculation processing based at least on each of the initial coordinate values ​​and a target cost function with preset constraints to obtain first smoothed coordinate values ​​corresponding to each of the first initial coordinate values; determine a first smoothed route based on each of the first smoothed coordinate values ​​to obtain the path planning result for the first running segment of the vehicle.

[0115] In the specific implementation process, the first path planning module 2 is further configured to: set parameter information corresponding to each anchor point, wherein the parameter information includes at least: lateral margin parameter value, longitudinal margin parameter value, and whether it is a strong constraint; calculate the lateral margin contraction value based on the lateral margin parameter value and the preset lateral margin coefficient value; calculate the maximum and minimum lateral margin values ​​corresponding to each anchor point based on the lateral margin contraction value; construct the preset constraint conditions based on each first initial coordinate value, the maximum lateral margin value, the minimum lateral margin value, the preset maximum longitudinal margin value, and the preset minimum longitudinal margin value; and perform smoothing calculation on the target cost function with the preset constraint conditions based on each first initial coordinate value to obtain the first smoothed coordinate value corresponding to each first initial coordinate value.

[0116] In specific implementation, the second path planning module 3 is specifically used for: acquiring the current second driving parameter information of the vehicle after leaving the first running segment; acquiring several second reference points corresponding to the target distance range in front of and behind the vehicle, and determining the second original reference route based on each second reference point; collecting anchor points on the second original reference route at preset intervals to obtain several second anchor points and second initial coordinate values ​​corresponding to each second anchor point; performing smoothing calculation processing based at least on each second initial coordinate value and a target cost function with preset constraints to obtain second smooth coordinate values ​​corresponding to each second initial coordinate value; determining the second smooth route of the second running segment based on each second smooth coordinate value; and controlling the vehicle to stop and using the first smooth route as the path planning result of the second running segment when the vehicle encounters an obstacle or the curvature of the second smooth route exceeds a preset threshold.

[0117] In the specific implementation process, the second path planning module 3 is also used to: store the first smooth route in a preset storage area; when the second smooth route meets the preset conditions, update the first smooth route in the preset storage area based on the second smooth route to obtain the path planning result of the second runtime.

[0118] In specific implementation, the path planning device further includes a target cost function construction module, which is specifically used to: construct a smoothness cost function, a length cost function, and a deviation cost function relative to the original reference point; and construct the target cost function based on the smoothness cost function, the length cost function, and the deviation cost function.

[0119] This application obtains the target distance ranges before and after the vehicle based on the vehicle's current first driving parameter information, the vehicle's global path planning route, and a preset high-precision map, and obtains a first original reference route based on the target distance range. A preset optimization algorithm is then used to smooth the first original reference route to obtain a first smoothed route, thus obtaining the path planning result for the vehicle's first operating segment. When the vehicle is traveling in a second operating segment, if a smoothed route for the second operating segment cannot be calculated based on the vehicle's driving parameter information, or if the curvature value of the second smoothed route obtained through smoothing exceeds a preset threshold, the vehicle is controlled to stop, and the first smoothed route is used as the path planning result for the second operating segment. The path planning method in this application can reasonably plan a driving path when the vehicle encounters obstacles or when the vehicle's turning curvature is too large, enabling the autonomous vehicle to smoothly complete a U-turn and continue driving.

[0120] Another embodiment of this application provides a storage medium storing a computer program, which, when executed by a processor, implements the following method steps:

[0121] Step 1: Based on the vehicle's current first driving parameter information, the vehicle's global path planning route, and the preset high-precision map, obtain the target distance range in front of and behind the vehicle, and obtain the first original reference route based on the target distance range;

[0122] Step 2: Use a preset optimization algorithm to smooth the first original reference route to obtain the first smoothed route, so as to obtain the path planning result of the vehicle's first running segment.

[0123] Step 3: When the vehicle is traveling in the second operating segment, if it is impossible to calculate a smooth route for the second operating segment based on the vehicle driving parameter information, or if the curvature value of the second smooth route corresponding to the second operating segment obtained through smoothing exceeds a preset threshold, the vehicle is controlled to stop and the first smooth route is used as the path planning result for the second operating segment.

[0124] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0125] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0126] The specific implementation process of the above method steps can be found in the embodiments of the above arbitrary path planning method, which will not be repeated here.

[0127] This application obtains the target distance ranges before and after the vehicle based on the vehicle's current first driving parameter information, the vehicle's global path planning route, and a preset high-precision map, and obtains a first original reference route based on the target distance range. A preset optimization algorithm is then used to smooth the first original reference route to obtain a first smoothed route, thus obtaining the path planning result for the vehicle's first operating segment. When the vehicle is traveling in a second operating segment, if a smoothed route for the second operating segment cannot be calculated based on the vehicle's driving parameter information, or if the curvature value of the second smoothed route obtained through smoothing exceeds a preset threshold, the vehicle is controlled to stop, and the first smoothed route is used as the path planning result for the second operating segment. The path planning method in this application can reasonably plan a driving path when the vehicle encounters obstacles or when the vehicle's turning curvature is too large, enabling the autonomous vehicle to smoothly complete a U-turn and continue driving.

[0128] Another embodiment of this application provides an electronic device, which can be a server. The electronic device includes a processor, a memory, a network interface, and a database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external clients via a network connection. When the program is executed by the processor, it implements the functions or steps of a path planning method on the server side.

[0129] In one embodiment, an electronic device is provided, which can be a client. The electronic device includes a processor, memory, a network interface, a display screen, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with an external server via a network connection. When the program of the electronic device is executed by the processor, it implements the functions or steps of a path planning method on the client side.

[0130] Another embodiment of this application provides an electronic device, including at least a memory and a processor. The memory stores a computer program, and the processor, when executing the computer program in the memory, performs the following method steps:

[0131] Step 1: Based on the vehicle's current first driving parameter information, the vehicle's global path planning route, and the preset high-precision map, obtain the target distance range in front of and behind the vehicle, and obtain the first original reference route based on the target distance range;

[0132] Step 2: Use a preset optimization algorithm to smooth the first original reference route to obtain the first smoothed route, so as to obtain the path planning result of the vehicle's first running segment.

[0133] Step 3: When the vehicle is traveling in the second operating segment, if it is impossible to calculate a smooth route for the second operating segment based on the vehicle driving parameter information, or if the curvature value of the second smooth route corresponding to the second operating segment obtained through smoothing exceeds a preset threshold, the vehicle is controlled to stop and the first smooth route is used as the path planning result for the second operating segment.

[0134] The specific implementation process of the above method steps can be found in the embodiments of the above arbitrary path planning method, which will not be repeated here.

[0135] This application obtains the target distance ranges before and after the vehicle based on the vehicle's current first driving parameter information, the vehicle's global path planning route, and a preset high-precision map, and obtains a first original reference route based on the target distance range. A preset optimization algorithm is then used to smooth the first original reference route to obtain a first smoothed route, thus obtaining the path planning result for the vehicle's first operating segment. When the vehicle is traveling in a second operating segment, if a smoothed route for the second operating segment cannot be calculated based on the vehicle's driving parameter information, or if the curvature value of the second smoothed route obtained through smoothing exceeds a preset threshold, the vehicle is controlled to stop, and the first smoothed route is used as the path planning result for the second operating segment. The path planning method in this application can reasonably plan a driving path when the vehicle encounters obstacles or when the vehicle's turning curvature is too large, enabling the autonomous vehicle to smoothly complete a U-turn and continue driving.

[0136] The above embodiments are merely exemplary embodiments of this application and are not intended to limit this application. The scope of protection of this application is defined by the claims. Those skilled in the art can make various modifications or equivalent substitutions to this application within its substance and scope of protection, and such modifications or equivalent substitutions should also be considered to fall within the scope of protection of this application.

Claims

1. A path planning method, characterized in that, include: Based on the vehicle's current first driving parameter information, the vehicle's global path planning route, and a preset high-precision map, the target distance range in front of and behind the vehicle is obtained, so as to obtain a first original reference route based on the target distance range. The first original reference route is smoothed using a preset optimization algorithm to obtain a first smoothed route, thereby obtaining the path planning result for the first running segment of the vehicle. When the vehicle is traveling in the second operating segment, if it is impossible to calculate a smooth route for the second operating segment based on the vehicle driving parameter information, or if the curvature value of the second smooth route corresponding to the second operating segment obtained through smoothing exceeds a preset threshold, the vehicle is controlled to stop and the first smooth route is used as the path planning result for the second operating segment. The step of smoothing the first original reference route using a preset optimization algorithm to obtain a first smoothed route specifically includes: Anchor points are collected at preset intervals along the original reference route to obtain several first anchor points and first initial coordinate values ​​corresponding to each first anchor point. At least based on each of the initial coordinate values ​​and the target cost function with preset constraints, a smoothing calculation is performed to obtain the first smoothed coordinate values ​​corresponding to each of the first initial coordinate values. Based on each of the first smoothed coordinate values, a first smoothed route is determined, and the path planning result for the first running segment of the vehicle is obtained. The target cost function includes a smoothness cost function, a length cost function, and a deviation cost function relative to the original reference point; The smoothing calculation process, based at least on each of the initial coordinate values ​​and a preset target cost function with preset constraints, to obtain first smoothed coordinate values ​​corresponding to each of the first initial coordinate values, specifically includes: Set the parameter information corresponding to each anchor point, and the parameter information includes at least: lateral margin parameter value, longitudinal margin parameter value, and whether it is a strong constraint; Based on the lateral margin parameter value and the preset lateral margin coefficient value, the lateral margin contraction value is calculated. Based on the lateral margin shrinkage value, the maximum and minimum lateral margin values ​​corresponding to each anchor point are calculated. Based on each of the first initial coordinate values, the maximum lateral margin, the minimum lateral margin, the maximum preset longitudinal margin, and the minimum preset longitudinal margin, the preset constraint conditions are constructed. Based on each of the first initial coordinate values, the target cost function with the preset constraints is smoothed to obtain the first smoothed coordinate values ​​corresponding to each of the first initial coordinate values.

2. The method as described in claim 1, characterized in that, The step of obtaining the target distance ranges in front of and behind the vehicle based on the vehicle's current first driving parameter information, the vehicle's global path planning route, and a preset high-precision map, and then obtaining the first original reference route based on the target distance range, specifically includes: Using a preset positioning system and a preset carrier differential phase calculation method, the first driving parameter information of the vehicle entering the first running stage is obtained. The first driving parameter information includes one or more of the following: three-dimensional geodetic coordinates, timestamp, roll angle, pitch angle, yaw angle, heading, linear velocity, angular velocity, linear acceleration, gear, driving mode, and steering percentage. Obtain the vehicle's global path planning route; The vehicle's first driving parameter information is continuously updated on the preset high-precision map to determine that the vehicle is on a drivable target road of the global path planning route. Obtain the distance range of targets in front of and behind the vehicle; Acquire a number of first reference points corresponding to the target distance range, wherein the target distance range includes: a first preset distance in the forward direction of travel and a second preset distance in the backward direction of travel; The first original reference route is determined based on each of the first reference points.

3. The method as described in claim 1, characterized in that, When the vehicle is traveling in the second operating segment, and a smooth route for the second operating segment cannot be calculated based on the vehicle's driving parameter information, or the curvature value of the smooth route corresponding to the second operating segment obtained through smoothing exceeds a preset threshold, the system controls the vehicle to stop and uses the first smooth route as the path planning result for the second operating segment. Specifically, this includes: Obtain the current second driving parameter information of the vehicle after it leaves the first driving segment; Acquire several second reference points corresponding to the distance range of the targets in front of and behind the vehicle, and determine the second original reference route based on each of the second reference points; Anchor points are collected at preset intervals along the second original reference route to obtain several second anchor points and second initial coordinate values ​​corresponding to each second anchor point. At least based on each of the second initial coordinate values ​​and the target cost function with preset constraints, a smoothing calculation is performed to obtain the second smoothed coordinate values ​​corresponding to each of the second initial coordinate values. The second smoothing route for the second runtime segment is determined based on each of the second smoothing coordinate values; When the vehicle encounters an obstacle or the curvature of the second smooth route exceeds a preset threshold, the vehicle is stopped and the first smooth route is used as the path planning result for the second running segment.

4. The method as described in claim 1, characterized in that, After smoothing the first original reference route using a preset optimization algorithm to obtain a first smoothed route, the method further includes: Store the first smooth route in a preset storage area; When the second smooth route meets the preset conditions, the first smooth route in the preset storage area is updated based on the second smooth route to obtain the path planning result of the second runtime segment.

5. The method as described in claim 1, characterized in that, Before performing smoothing calculation on the target cost function with the preset constraints based on each of the first initial coordinate values ​​to obtain the first smoothed coordinate values ​​corresponding to each of the first initial coordinate values, the method further includes: constructing the target cost function, specifically including: Construct a smoothness cost function, a length cost function, and a deviation cost function relative to the original reference point; The target cost function is constructed based on the smoothness cost function, the length cost function, and the deviation cost function.

6. A path planning device, characterized in that, include: Acquisition module: used to acquire the target distance range in front of and behind the vehicle based on the vehicle's current first driving parameter information, the vehicle's global path planning route and a preset high-precision map, so as to obtain the first original reference route based on the target distance range; First path planning module: used to smooth the first original reference route using a preset optimization algorithm to obtain a first smooth route, so as to obtain the path planning result of the first running segment of the vehicle; specifically used to: collect anchor points on the original reference route at preset intervals to obtain a number of first anchor points and the first initial coordinate values ​​corresponding to each first anchor point; The process involves smoothing calculations based on at least the initial coordinate values ​​and a target cost function with preset constraints to obtain first smoothed coordinate values ​​corresponding to each of the first initial coordinate values. Specifically, this includes: setting parameter information for each anchor point, the parameter information including at least: lateral margin parameter values, longitudinal margin parameter values, and whether it is a strong constraint; calculating a lateral margin contraction value based on the lateral margin parameter values ​​and a preset lateral margin coefficient value; calculating the maximum and minimum lateral margin values ​​corresponding to each anchor point based on the lateral margin contraction values; constructing the preset constraints based on each of the first initial coordinate values, the maximum and minimum lateral margin values, the preset maximum and minimum longitudinal margin values; performing smoothing calculations on the target cost function with the preset constraints based on each of the first initial coordinate values ​​to obtain first smoothed coordinate values ​​corresponding to each of the first initial coordinate values; determining a first smoothed route based on each of the first smoothed coordinate values ​​to obtain the path planning result for the first running segment of the vehicle; the target cost function includes a smoothness cost function, a length cost function, and a deviation cost function relative to the original reference point. The second path planning module is used to control the vehicle to stop and use the first smooth route as the path planning result for the second running segment when the vehicle is traveling in the second running segment and cannot calculate a smooth route for the second running segment based on the vehicle driving parameter information, or when the curvature value of the second smooth route corresponding to the second running segment obtained through smoothing exceeds a preset threshold.

7. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the path planning method according to any one of claims 1-5.

8. An electronic device, characterized in that, It includes at least a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program in the memory, implements the steps of the path planning method according to any one of claims 1-5.

Images