Path planning method and device, electronic equipment and storage medium

Abstract

The invention provides a path planning method and device, electronic equipment and a storage medium, and the method comprises the steps: responding to an initial planning path, obtained through planning, of target equipment moving from a first position to a second position, and constructing a safe passage corridor for the target equipment to pass through surrounding obstacles according to the initial planning path, the initial planning path comprises a plurality of first path points; executing the following operations on each first waypoint in the plurality of first waypoints to obtain a plurality of second waypoints: obtaining geometric adjustment parameters corresponding to the first waypoints; according to the geometric adjustment parameter, updating the position of the first path point to obtain a second path point; wherein the geometric adjustment parameters are parameters for carrying out geometric adjustment on a geometric model of the target equipment in the construction process of the safe passage corridor; and performing path planning according to the plurality of second path points to obtain a target planning path of the target equipment moving from the first position to the second position. The reliability of path planning can be improved.

Description

Technical Field

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

[0002] With the rapid development of autonomous driving technology, vehicles can now achieve autonomous navigation and decision-making in multiple scenarios. Path planning, as a core component of autonomous driving, directly determines driving safety and efficiency. Taking automatic parking as an example, vehicles complete multiple turns and displacements at low speeds in narrow spaces, requiring extremely high precision in the parking path; even slight deviations can lead to collisions or interruptions. How to improve the reliability of path planning has become an urgent problem to be solved. Summary of the Invention

[0003] The main objective of this application is to provide a path planning method, apparatus, electronic device, and storage medium to improve the reliability of path planning.

[0004] This application provides a path planning method, including: responding to an initial planned path for a target device to move from a first position to a second position; constructing a safe passage corridor for the target device to traverse surrounding obstacles based on the initial planned path, wherein the initial planned path includes a plurality of first path points; performing the following operations on each of the plurality of first path points to obtain a plurality of second path points: obtaining geometric adjustment parameters corresponding to the first path points; updating the position of the first path points according to the geometric adjustment parameters to obtain the second path points; wherein the geometric adjustment parameters are parameters used to geometrically adjust the geometric model of the target device during the construction of the safe passage corridor; and performing path planning based on the plurality of second path points to obtain a target planned path for the target device to move from the first position to the second position.

[0005] In one embodiment, the geometric model is a polygon; the geometric adjustment parameters include the position adjustment direction and magnitude of the target edge in the geometric model; updating the position of the first path point according to the geometric adjustment parameters to obtain the second path point includes: determining the target weight corresponding to the target edge according to the path attribute information corresponding to the initial planned path and the first path point; updating the position of the first path point according to the position adjustment direction and magnitude of the target edge and the target weight to obtain the second path point.

[0006] In one embodiment, determining the target weight corresponding to the target edge based on the path attribute information corresponding to the initial planned path and the first path point includes: determining the target weight as a first preset weight in response to the path attribute information being first path attribute information; and determining the target weight based on the orientation information corresponding to the target edge and the target device in response to the path attribute information being second path attribute information.

[0007] In one embodiment, the first path attribute information includes at least one of the following: the curvature change amplitude of the initial planned path corresponding to the first path point is less than or equal to a preset amplitude, and the initial planned path does not change direction at the first path point; the second path attribute information includes: the initial planned path changes direction at the first path point, and the curvature change amplitude is greater than the preset amplitude.

[0008] In one embodiment, determining the target weight based on the azimuth information corresponding to the target edge and the target device includes: in response to the azimuth information indicating that the target edge is perpendicular to the heading angle indication direction of the target device, determining the target weight based on the curvature change amplitude corresponding to the initial planned path and the first path point; and in response to the azimuth information indicating that the target edge is parallel to the heading angle indication direction of the target device, determining the target weight as a second preset weight.

[0009] In one embodiment, the geometric model includes a first side and a second side perpendicular to the heading angle indication direction; in the heading angle indication direction, the first side is located before the second side; determining the target weight based on the curvature change amplitude corresponding to the initial planned path and the first path point includes at least one of the following: in response to the target side being the first side, determining the target weight corresponding to the first side based on the curvature change amplitude and a first correspondence; in the first correspondence, the target weight is positively correlated with the curvature change amplitude, and the minimum target weight is greater than the first preset weight; in response to the target side being the second side, determining the target weight corresponding to the second side based on the curvature change amplitude and a second correspondence; in the second correspondence, the target weight is negatively correlated with the curvature change amplitude, and the minimum target weight is less than the first preset weight.

[0010] In one embodiment, the step of performing path planning based on the plurality of second path points to obtain the target planned path for the target device to move from the first position to the second position includes: constructing a discrete path-time related polynomial for the target device based on the positions of the plurality of second path points; constructing a nonlinear optimization problem using the coefficients and time of the polynomial as optimization variables, minimizing the total time corresponding to the discrete path, and jerk as optimization objectives, combined with target constraints; determining the target planned path based on the solution of the nonlinear optimization problem; wherein the target constraints include at least one of the following: pose constraints of the target device at the first position and the second position, path smoothness constraints, kinematic feasibility constraints, and obstacle avoidance constraints.

[0011] In one embodiment, the solution to the nonlinear optimization problem includes the values ​​of the coefficients of the polynomial; determining the target planning path based on the solution to the nonlinear optimization problem includes: determining the positions of multiple time-related target path points based on the values ​​of the coefficients of the polynomial; for each of the multiple target path points, using the kinematic model of the target device, determining the kinematic parameters of the target device at the target path point based on the position of the target path point; and determining the target planning path based on the positions of the multiple target path points and the kinematic parameters of the target device at the multiple target path points.

[0012] In one embodiment, determining the kinematic parameters of the target device at the target path point based on the position of the target path point using the kinematic model of the target device includes: establishing a differential flat model with the position of the target path point as the flat output based on the kinematic model of the target device; and solving for the kinematic parameters of the target device at the target path point based on the differential flat model.

[0013] This application embodiment also provides a path planning device, the device including a corridor construction module, a position update module, and a path planning module; the corridor construction module is used to construct a safe passage corridor for the target device to pass through surrounding obstacles in response to an initial planned path obtained from the planning of a target device moving from a first position to a second position, wherein the initial planned path includes a plurality of first path points; the position update module is used to perform the following operations for each of the plurality of first path points to obtain a plurality of second path points: obtaining geometric adjustment parameters corresponding to the first path points; updating the position of the first path points according to the geometric adjustment parameters to obtain the second path points; wherein the geometric adjustment parameters are: parameters for geometric adjustment of the geometric model of the target device during the construction of the safe passage corridor; the path planning module is used to perform path planning based on the plurality of second path points to obtain a target planned path for the target device to move from the first position to the second position.

[0014] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described path planning method.

[0015] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described path planning method.

[0016] This application provides a path planning method, apparatus, electronic device, and storage medium. By updating the positions of the first path points in the initial planned path for a target device to move from a first position to a second position using parameters obtained from the geometric adjustment of the target device's geometric model during the construction of a safe passage corridor, a second path point is obtained. Furthermore, path planning is performed based on multiple second path points to obtain the target planned path for the target device to move from the first position to the second position, thereby improving the reliability of path planning. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the path planning method provided in the embodiments of this application.

[0018] Figure 2 This is a schematic diagram illustrating an application scenario of the path planning method provided in the embodiments of this application.

[0019] Figure 3 This is a schematic diagram of the path planning device provided in the embodiments of this application.

[0020] Figure 4This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0021] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0022] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the digit " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0023] The path planning method provided in this application can be applied to electronic devices or their software. The electronic device can be a vehicle, ship, aircraft, or other device with a movement path, or it can be a terminal or server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers. The software can be an application implementing the path planning method, but is not limited to the above forms.

[0024] The path planning method provided in this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0025] Please see Figure 1 The path planning method provided in this application embodiment may include: Step S101: In response to the initial planned path obtained from the planning of the target device moving from the first position to the second position, a safe passage corridor for the target device to pass through surrounding obstacles is constructed for the initial planned path, wherein the initial planned path includes multiple first path points; Optionally, the target device can be a vehicle, ship, aircraft, or other device with a movement path. In actual implementation, given the starting point (first position) and ending point (second position) of the path planning, the initial planned path for the target device to move from the first position to the second position can be planned based on the target device's state information (such as the target device's speed, acceleration, heading angle, etc.) and the state information of surrounding obstacles (such as the shape, type, and distribution of surrounding obstacles, etc.). Path planning algorithms such as interpolation curves, A* search, and random sampling can be used.

[0026] Next, the initial planned path can be discretized into multiple path points according to the direction of movement of the target device; the multiple first path points can be all the path points of the initial planned path, or they can be some of the path points of the initial planned path.

[0027] Then, for each first path point, the first path point can be used as the reference point of the target device to construct the geometric model of the target device; then, the geometric model of the target device can be adjusted based on the positional relationship between the geometric model of the target device and the geometric model of the obstacle. For specific implementation, please refer to the relevant description below, which will not be described here; then, the safe passage corridor of the target device can be constructed based on the final geometric model of the target device at each first path point.

[0028] Step S102: Perform the following operations on each of the multiple first path points to obtain multiple second path points: obtain the geometric adjustment parameters corresponding to the first path points; update the position of the first path points according to the geometric adjustment parameters to obtain the second path points; wherein, the geometric adjustment parameters are: parameters for geometric adjustment of the geometric model of the target device during the construction of the safe passage corridor; Optionally, the geometric model of the target device can be a polygonal geometric model (such as a rectangular geometric model, a pentagonal geometric model, etc.), an elliptical geometric model, or any other geometric model that includes the actual dimensions of the target device. For polygonal geometric models, the aforementioned geometric adjustment parameters can include the direction and magnitude of position adjustment for the target edges in the geometric model; in actual implementation, each edge in the polygonal geometric model can be determined as a target edge, or only the edges whose positions are adjusted in the polygonal geometric model can be determined as target edges. For elliptical geometric models, the aforementioned geometric adjustment parameters can include major axis and minor axis parameters.

[0029] Taking a polygonal geometric model as an example, during the construction of a safe passage corridor, for each target edge in the geometric model of the target device, in response to the intersection of the target edge with the geometric model of an obstacle, the target edge can be moved along the direction pointing towards the geometric model of the target device until the minimum distance between the target edge and the geometric model of the obstacle is within a preset distance range; in response to the non-intersection of the target edge with the geometric model of the obstacle, the target edge can be moved along the direction away from the geometric model of the obstacle until the minimum distance between the target edge and the geometric model of the obstacle is within a preset distance range, or the movement distance of the target edge reaches a distance threshold. The intersection of the target edge with the geometric model of the obstacle indicates a collision risk between the target device and the obstacle, while the non-intersection indicates no collision risk between the target device and the obstacle.

[0030] In practice, the position of the first path point can be updated directly based on the geometric adjustment parameters corresponding to the first path point to obtain the second path point; taking a rectangular geometric model as an example, the second path point can be determined using formulas (1) and (2): (1) (2) in, Indicates the first path point Location; Indicates the second path point Location; , , , These represent the position adjustment ranges of the four target edges (front, back, left, and right) of the rectangular geometric model corresponding to the target device and the first path point. Their positive and negative values ​​can be determined based on the position adjustment direction of the target edges.

[0031] In practice, one can first determine the target weight corresponding to the target edge based on the path attribute information corresponding to the initial planned path and the first path point. Then, based on the geometric adjustment parameters corresponding to the first path point and the target weight corresponding to the target edge, the position of the first path point is updated to obtain the second path point. For details, please refer to the relevant description below, which will not be described here.

[0032] Step S103: Perform path planning based on multiple second path points to obtain the target planned path for the target device to move from the first position to the second position.

[0033] In practice, multiple second path points can be used to directly fit the path using path fitting algorithms such as Bézier curves and spline interpolation to generate the target planning path for the target device to move from the first position to the second position. Alternatively, multiple second path points can be used as a reference, and constraints can be further superimposed to optimize the path, thereby obtaining the target planned path for the target device to move from the first position to the second position. For specific implementation details, please refer to the relevant descriptions below, which will not be described here.

[0034] It is worth mentioning that, compared to directly obtaining the target planned path based on the position of the first path point in the initial planned path, obtaining the target planned path based on the updated positions of multiple second path points can reduce the time for path optimization using constraints, thereby improving the efficiency of path planning.

[0035] This application embodiment updates the positions of the first path points in the initial planned path for the target device to move from the first position to the second position using parameters obtained from the geometric adjustment of the target device's geometric model during the construction of the safe passage corridor, thereby obtaining second path points; and performs path planning based on multiple second path points to obtain the target planned path for the target device to move from the first position to the second position, which can improve the reliability of path planning.

[0036] Optionally, the geometric model is a polygon; the geometric adjustment parameters include the direction and magnitude of position adjustment for the target edge in the geometric model. In one embodiment, the step S102 above, which updates the position of the first path point according to the geometric adjustment parameters to obtain the second path point, includes: Based on the path attribute information corresponding to the initial planned path and the first path point, determine the target weight corresponding to the target edge; The position of the first path point is updated by adjusting the direction and magnitude of the target edge and the target weight, thus obtaining the second path point.

[0037] Optionally, the path attribute information corresponding to the initial planned path and the first path point can be used to characterize the degree of abrupt change of the initial planned path at the first path point, and may include the following information: whether the curvature change of the initial planned path corresponding to the first path point is greater than a preset range, and whether the initial planned path changes direction at the first path point. Optionally, if the directional deviation of the path before and after the first path point is greater than a preset deviation, it can be determined that the initial planned path has changed direction at the first path point; if the directional deviation of the path before and after the first path point is less than or equal to the preset deviation, it can be determined that the initial planned path has not changed direction at the first path point.

[0038] Optionally, the curvature change amplitude corresponding to the initial planned path and the first path point can be a quantitative index of the difference in curvature values ​​between the preceding and following segments of the initial planned path, with the first path point as the core reference point. This index is used to characterize the drastic change in the curvature of the initial planned path at the first path point. Optionally, the reversal of the initial planned path at the first path point can be used to characterize that the target device changes its direction of movement after moving along the initial planned path to the first path point.

[0039] In actual implementation, the target edge can be assigned a corresponding preset weight based on the path attribute information corresponding to the initial planned path and the first path point. Alternatively, the target weight can be determined by combining the target edge with the orientation information corresponding to the target device. For specific implementation details, please refer to the relevant descriptions below, which will not be described here.

[0040] Taking a rectangular geometric model as an example, the second path point can be determined using formulas (3) and (4): (3) (4) in, , , and The target weights are the front, back, left, and right target edges of the rectangular geometric model.

[0041] This application embodiment determines the target weight corresponding to the target edge based on the path attribute information corresponding to the initial planned path and the first path point, and updates the position of the first path point based on the position of the target edge, the adjustment of direction and magnitude, and the target weight, to obtain the second path point. This realizes the optimization of the initial planned path by further utilizing the path attribute information of the initial planned path based on the initial planned path, which can improve the reliability of path planning.

[0042] In one embodiment, determining the target weight corresponding to the target edge based on the path attribute information corresponding to the initial planned path and the first path point includes: In response to the path attribute information being the first path attribute information, the target weight is determined to be the first preset weight; In response to the path attribute information being the second path attribute information, the target weight is determined based on the orientation information corresponding to the target edge and the target device.

[0043] Optionally, the first path attribute information can be used to characterize that the initial planned path does not undergo abrupt changes or the degree of change is small at the first path point; the second path attribute information can be used to characterize that the initial planned path undergoes abrupt changes at the first path point and the degree of change is large.

[0044] In actual implementation, under the first path attribute information, by using the first preset weight assigned to the target edge, the position of the first path point is updated, which can make the updated second path point move away from the obstacle, thereby improving the safety of the planned path; Optionally, for different target edges, the first preset weights corresponding to each target edge can be completely the same, partially the same, or completely different.

[0045] Under the second path attribute information, by differentiating the target weight based on the orientation information corresponding to the target edge and the target device, it can not only guide the position of the first path point to be updated in the direction away from the obstacle, but also guide the position of the first path point to be updated in the direction that makes the planned path smoother, thereby improving the safety and smoothness of the planned path. For specific implementation, please refer to the relevant description below, which will not be described here.

[0046] This application embodiment improves the security of the planned path determined based on the target weight by determining the target weight as a first preset weight in response to the path attribute information being the first path attribute information. In addition, by determining the target weight based on the orientation information corresponding to the target edge and the target device in response to the path attribute information being the second path attribute information, the security and smoothness of the planned path determined based on the target weight can be improved, thereby improving the reliability of path planning.

[0047] In one embodiment, the first path attribute information includes at least one of the following: the curvature change of the initial planned path and the first path point is less than or equal to a preset range; the initial planned path does not change direction at the first path point. The aforementioned second path attribute information includes: the initially planned path changes direction at the first path point, and the curvature change is greater than the preset range.

[0048] Optionally, the preset amplitude can be obtained through calibration. If the curvature change amplitude of the initial planned path and the first path point is greater than the preset amplitude, it can indicate that the curvature values ​​of the initial planned path before and after the first path point are significantly different.

[0049] In this embodiment, when the curvature change amplitude of the initial planned path corresponding to the first path point is less than or equal to a preset amplitude, and / or when the initial planned path does not change direction at the first path point, the target weight is determined as the first preset weight, which can improve the safety of the planned path determined based on the target weight. When the initial planned path changes direction at the first path point and the curvature change amplitude is greater than the preset amplitude, the target weight is determined according to the orientation information corresponding to the target edge and the target device, which can improve the safety and smoothness of the planned path determined based on the target weight, thereby improving the reliability of path planning.

[0050] In one embodiment, determining the target weight based on the orientation information corresponding to the target edge and the target device includes: In response to the orientation information indicating that the target edge is perpendicular to the heading angle of the target equipment, the target weight is determined based on the curvature change amplitude corresponding to the initial planned path and the first path point; In response to the orientation information indicating that the target edge is parallel to the heading angle of the target equipment, the target weight is determined to be the second preset weight.

[0051] Optionally, the heading angle can be used to characterize the orientation of the target device in the horizontal plane.

[0052] In practical implementation, for a target edge perpendicular to the heading direction of the target device, the target weight can be obtained by querying a preset table of correspondence between curvature change magnitude and target weight, using the curvature change magnitude corresponding to the initial planned path and the first path point. Alternatively, the curvature change magnitude corresponding to the initial planned path and the first path point can be input into a model that has learned the relationship between curvature change magnitude and target weight to obtain the target weight. For a target edge parallel to the heading direction of the target device, a second preset weight can be assigned to it.

[0053] Optionally, the second preset weight can be the same as or different from the first preset weight; for different target edges, the second preset weights corresponding to each target edge can be exactly the same, partially the same, or completely different.

[0054] Thus, when the initial planned path changes direction at the first path point and the curvature change is greater than the preset range, the target weight corresponding to the target edge perpendicular to the heading angle indication direction of the target device is determined based on the curvature change range corresponding to the initial planned path and the first path point. This allows for adjustment of the curvature change range corresponding to the first path point, thereby improving the smoothness of the planned path while ensuring its safety.

[0055] Optionally, the geometric model includes a first side and a second side perpendicular to the heading angle indication direction; in the heading angle indication direction, the first side is located before the second side. In one embodiment, determining the target weight based on the curvature change magnitude corresponding to the initial planned path and the first path point includes at least one of the following: In response to the target edge being the first edge, the target weight corresponding to the first edge is determined based on the curvature change magnitude of the initial planned path and the first path point, as well as the first correspondence relationship. In the first correspondence relationship, the target weight is positively correlated with the curvature change magnitude, and the minimum target weight is greater than the first preset weight. In response to the target edge being the second edge, the target weight corresponding to the second edge is determined based on the curvature change magnitude of the initial planned path and the first path point, as well as the second correspondence. In the second correspondence, the target weight is negatively correlated with the curvature change magnitude, and the maximum target weight is less than the first preset weight.

[0056] Optionally, the aforementioned first and second correspondences can be preset. Thus, if the initial planned path reverses direction at the first path point and the curvature change corresponding to the first path point exceeds a preset range, by increasing the target weight of the first side perpendicular to the heading angle direction and / or decreasing the target weight of the second side perpendicular to the heading angle direction, the first path point can move along the tangents of its preceding and following paths, thereby reducing its corresponding curvature change to zero and making the planned path smoother.

[0057] Please see Figure 2 Taking the automatic parking scenario as an example, in the vehicle's geometric model, the first side can be the front side 1, and the second side can be the rear side 2. Based on the above formula (3), if the curvature change between the initial planned path and the first path point A is greater than the preset range, by increasing... , reduce This allows the first path point A to move to the second path point B along the tangents of its preceding and following paths, thus making the target planned path smoother than the initial planned path.

[0058] In one embodiment, step S103 above, which involves path planning based on multiple second path points to obtain a target planned path for the target device to move from the first position to the second position, includes: Based on the positions of multiple second path points, construct a discrete path-time related polynomial for the target device; Using the coefficients and time of the polynomial as optimization variables, minimizing the total time and jerk corresponding to the discrete path as optimization objectives, and combining the objective constraints, a nonlinear optimization problem is constructed. Determine the objective planning path based on the solution to the nonlinear optimization problem; The target constraints include at least one of the following: pose constraints of the target device in the first and second positions, path smoothness constraints, kinematic feasibility constraints, and obstacle avoidance constraints.

[0059] In practical implementation, the discrete path of the target device moving from the first position to the second position can be obtained based on the positions of multiple second path points. It can be assumed that the target device moves with uniform acceleration or deceleration, thus allowing estimation of the total time it takes for the target device to move from the first position to the second position along the discrete path. Next, the discrete path can be divided into n equal segments along the direction of the target device's movement, according to the path length and / or the target device's movement time. Then, for each segment, it can be further divided into... A trajectory segment.

[0060] For each trajectory segment, the trajectory segment can be parameterized as a time-dependent polynomial: (5) (6) (7) in, It is a basis for polynomials; The coefficient matrix of the polynomial; The time interval for each trajectory segment.

[0061] Furthermore, combinations are possible. The polynomial of the trajectory segment yields the th . Segment path time-dependent polynomial : (8) (9) in, , for the first The time corresponding to the segment path.

[0062] Furthermore, by combining the polynomials of the n path segments, we can obtain the polynomial of the entire discrete path in relation to time. : (10) (11) in, , where is the total time it takes for the target device to move along the discrete path; , for the first The start time of a path segment can be understood as the sum of the times the target device has traveled along each of the previous path segments; optionally, .

[0063] Next, the coefficients and time of the polynomial related to the entire discrete path can be defined as optimization variables: coefficient set: Time set: Construct a nonlinear optimization problem: (12) (13) in, This represents the total time corresponding to the discrete path; in the case of s=3, It can represent jerk; (14) (15) (16) (17) (18) in, This indicates the boundary conditions of the target device at the first and second positions; This represents the state constraints at the points where gear shifts occur between trajectory segments, which can be understood as smoothness constraints at path reversals. These represent path continuity conditions, and the two can constitute path smoothness constraints; Indicates at the state point The constraints at the location, among which, As a constraint of kinematic feasibility, Collision avoidance constraints for both static and dynamic obstacles.

[0064] In practice, the constraint terms shown in the above formulas (14)-(18) can also be converted into penalty terms and added to the cost function, so that the above nonlinear optimization problem can be converted into an unconstrained optimization problem. In this way, conventional optimization algorithms such as least squares method, gradient descent method, and Gauss-Newton method can be used to quickly solve the target planning path.

[0065] Based on obtaining multiple second path points, this application further constructs a discrete path-time related polynomial for the target device based on the positions of the multiple second path points; and constructs a nonlinear optimization problem by using the coefficients and time of the polynomial as optimization variables, minimizing the total time corresponding to the discrete path and the jerk as optimization objectives, combined with the target constraints; and determines the target planning path based on the solution of the nonlinear optimization problem, which can further improve the reliability of path planning.

[0066] Optionally, the solution to the nonlinear optimization problem includes the values ​​of the coefficients of the polynomial. In one embodiment, determining the objective planning path based on the solution to the nonlinear optimization problem includes: Based on the values ​​of the polynomial coefficients, determine the locations of multiple time-dependent target path points; For each of the multiple target path points, the kinematic parameters of the target device at the target path point are determined using the kinematic model of the target device based on the position of the target path point. The target planning path is determined based on the location of multiple target path points and the kinematic parameters of the target device at multiple target path points.

[0067] In actual implementation, the coefficients of the polynomial are obtained by solving the above formulas (12)-(18). In this case, it can be Substituting into the above formula (5), we obtain the positions of multiple target path points.

[0068] Next, based on the position coordinate difference and velocity difference between the current target path point and the previous adjacent target path point, the kinematic parameters such as the instantaneous velocity and acceleration of the target device at the current target path point can be estimated; for example, based on the distance between adjacent path points and the preset time step, the instantaneous velocity of the target device at the current target path point can be derived; and the acceleration of the target device at the current target path point can be calculated using the velocity difference between adjacent path points and the time step.

[0069] Alternatively, the differential flat model and the kinematic model of the target device can be combined to determine the kinematic parameters of the target device at the target path point based on the location of the target path point. For specific implementation details, please refer to the relevant descriptions below, which will not be described here.

[0070] Then, based on the positions of multiple target path points and the kinematic parameters corresponding to each path point, path fitting algorithms such as Bézier curves and spline interpolation can be used to fit adjacent target path points to obtain the target planned path.

[0071] This application embodiment determines the positions of multiple time-related target path points based on the values ​​of the coefficients of a polynomial; and for each of the multiple target path points, it uses the kinematic model of the target device to determine the kinematic parameters of the target device at the target path point based on the position of the target path point; and determines the target planning path based on the positions of the multiple target path points and the kinematic parameters of the target device at the multiple target path points, thereby obtaining a target planning path with high reliability.

[0072] In one embodiment, the above-mentioned method of determining the kinematic parameters of the target device at the target path point based on the position of the target path point using the kinematic model of the target device includes: Based on the kinematic model of the target device, a differential flat model is established with the position of the target path point as the flat output. Based on the differential flat model, the kinematic parameters of the target device at the target path point are solved.

[0073] In practical implementation, a kinematic model adapted to the target device (such as a bicycle model, a dual-track model, etc.) can be selected, and the position of the target path point can be used as the flat output. Then, the kinematic parameters of the target device at any path point can be expressed by the derivative of the position of that path point using the kinematic model of the target device to obtain the differential flat model. Then, the position of the target path point can be input into the differential flat model to obtain the kinematic parameters of the target device at the target path point.

[0074] Taking a vehicle as an example, the process of solving for kinematic parameters based on the differential flat model is explained below: First, the kinematic model of the vehicle can be simplified to a bicycle model, and its state vector can be represented as: (19) in, This refers to the position of the center of the vehicle's rear axle. The vehicle's heading angle; The longitudinal velocity in the vehicle body coordinate system; This refers to the vehicle's longitudinal acceleration; This refers to the vehicle's lateral acceleration. The steering angle of the vehicle's front wheels; The instantaneous curvature of the path; Then, a differential flat model can be established using the flat output characteristic of the vehicle, and the position of the rear axle center of the vehicle can be selected as the flat output. ,Right now Establish a differential flat model: (20) (twenty one) (twenty two) (twenty three) (twenty four) (25) in: The direction of the vehicle's movement. 1 indicates backward movement, and 1 indicates forward movement; , They represent The first and second derivatives; , They represent The first and second derivatives.

[0075] Finally, the location of the target path point ( Substitute the specific values ​​of the target device into the above formulas (20)-(25) to solve for the kinematic parameters of the target device at the target path point.

[0076] This application embodiment establishes a differential flat model with the position of the target path point as the flat output based on the kinematic model of the target device; and solves the kinematic parameters of the target device at the target path point based on the differential flat model, which can improve the accuracy of determining the kinematic parameters of the target device at the target path point, thereby improving the reliability of the final target planning path.

[0077] Please see Figure 3 This application also provides a path planning device 300, which can implement the above-mentioned path planning method. The device 300 may include a corridor construction module 301, a location update module 302, and a path planning module 303.

[0078] The corridor construction module 301 is used to construct a safe passage corridor for the target device to pass through surrounding obstacles in response to the initial planned path obtained from the planning of the target device moving from the first position to the second position. The initial planned path includes multiple first path points. The location update module 302 is used to perform the following operations for each of the multiple first path points to obtain multiple second path points: obtain the geometric adjustment parameters corresponding to the first path points; update the position of the first path points according to the geometric adjustment parameters to obtain the second path points; wherein, the geometric adjustment parameters are: parameters for geometric adjustment of the geometric model of the target device during the construction of the safe passage corridor; The path planning module 303 is used to perform path planning based on multiple second path points to obtain the target planned path for the target device to move from the first position to the second position.

[0079] The path planning device provided in this application embodiment can implement all the steps of the above-described path planning method embodiment and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0080] This application also provides an electronic device, including a processor and a memory. The memory stores a program or instructions that can run on the processor. When the program or instructions are executed by the processor, they implement the various steps of the above-described path planning method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0081] Figure 4 To illustrate the hardware structure of the electronic device according to the embodiments of this application, the electronic device includes: The processor 401 can be implemented using a general-purpose central processing unit (CPU), microprocessor, application specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 402 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 402 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 402 and is called and executed by the processor 401 using the path planning method of the embodiments of this application. Input / output interface 403 is used to implement information input and output; The communication interface 404 is used to enable communication and interaction between this electronic device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 405 transmits information between various components of an electronic device (e.g., processor 401, memory 402, input / output interface 403, and communication interface 404); The processor 401, memory 402, input / output interface 403 and communication interface 404 are connected to each other within the electronic device via bus 405.

[0082] The electronic device provided in this application embodiment can implement all the steps of the above path planning method embodiment and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0083] This application also provides a computer-readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various steps of the above-described path planning method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0084] The processor is the processor in the electronic device described in the above embodiments. The computer-readable storage medium includes computer-readable storage media such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0085] This application also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various steps of the above-described path planning method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0086] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0087] This application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various steps of the path planning method embodiment described above, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0088] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not delete other identical elements present in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0089] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0090] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A path planning method characterized by, The method comprises: in response to planning an initial planning path for a target device to move from a first position to a second position, constructing a safe passing corridor for the target device to pass through surrounding obstacles for the initial planning path, wherein the initial planning path comprises a plurality of first path points; for each of the plurality of first path points, performing the following operations to obtain a plurality of second path points: obtaining a geometric adjustment parameter corresponding to the first path point; updating the position of the first path point according to the geometric adjustment parameter to obtain a second path point; wherein the geometric adjustment parameter is a parameter for geometric adjustment of a geometric model of the target device in the safe passing corridor construction process; performing path planning according to the plurality of second path points to obtain a target planning path for the target device to move from the first position to the second position.

2. The path planning method of claim 1, wherein, The geometric model is a polygon; and the geometric adjustment parameter comprises a position adjustment direction and a magnitude of a target edge in the geometric model. The updating of the position of the first path point according to the geometric adjustment parameter to obtain a second path point comprises: determining a target weight corresponding to the target edge according to path attribute information corresponding to the initial planning path and the first path point; updating the position of the first path point according to the position adjustment direction and the magnitude of the target edge and the target weight to obtain the second path point.

3. The path planning method of claim 2, wherein, The determination of the target weight corresponding to the target edge according to the path attribute information comprises: in response to the path attribute information being first path attribute information, determining the target weight to be a first preset weight; in response to the path attribute information being second path attribute information, determining the target weight according to bearing information corresponding to the target edge and the target device.

4. The path planning method of claim 3, wherein, The first path attribute information comprises at least one of the following: a curvature change magnitude corresponding to the initial planning path and the first path point being less than or equal to a preset magnitude, and the initial planning path not changing direction at the first path point. The second path attribute information comprises: the initial planning path changing direction at the first path point, and the curvature change magnitude being greater than the preset magnitude.

5. The path planning method of claim 3, wherein, The determination of the target weight according to the bearing information corresponding to the target edge and the target device comprises: in response to the bearing information indicating that the target edge is perpendicular to a heading angle indication direction of the target device, determining the target weight according to a curvature change magnitude corresponding to the initial planning path and the first path point; in response to the bearing information indicating that the target edge is parallel to the heading angle indication direction of the target device, determining the target weight to be a second preset weight.

6. The path planning method of claim 5, wherein, The geometric model comprises a first edge and a second edge that are perpendicular to the heading angle indication direction; and in the heading angle indication direction, the first edge is located before the second edge. The determination of the target weight according to the curvature change magnitude corresponding to the initial planning path and the first path point comprises at least one of the following: in response to the target edge being the first edge, determining a target weight corresponding to the first edge according to the curvature variation amplitude and a first correspondence relationship, in which the target weight is positively correlated with the curvature variation amplitude, and a maximum target weight is greater than the first preset weight; in response to the target edge being the second edge, determining a target weight corresponding to the second edge according to the curvature variation amplitude and a second correspondence relationship, in which the target weight is negatively correlated with the curvature variation amplitude, and a minimum target weight is less than the first preset weight.

7. The path planning method of claim 1, wherein, The path planning according to the plurality of second path points to obtain the target planning path of the target device moving from the first position to the second position includes: constructing a time-dependent polynomial of the discrete path of the target device according to the positions of the plurality of second path points; constructing a nonlinear optimization problem by taking the coefficients of the polynomial and time as optimization variables, taking the total time corresponding to the discrete path and the jerk as optimization objectives, and combining target constraint conditions; determining the target planning path according to the solution of the nonlinear optimization problem; The target constraint conditions include at least one of the following: a pose constraint of the target device at the first position and the second position, a path smoothness constraint, a kinematic feasibility constraint, and an obstacle avoidance constraint.

8. The path planning method of claim 7, wherein, The solution of the nonlinear optimization problem includes the values of the coefficients of the polynomial; The determination of the target planning path according to the solution of the nonlinear optimization problem includes: determining the positions of a plurality of target path points related to time according to the values of the coefficients of the polynomial; for each target path point in the plurality of target path points, determining kinematic parameters of the target device at the target path point according to the position of the target path point by using a kinematic model of the target device; determining the target planning path according to the positions of the plurality of target path points and the kinematic parameters of the target device at the plurality of target path points.

9. The path planning method of claim 8, wherein, The determination of the kinematic parameters of the target device at the target path point according to the position of the target path point by using the kinematic model of the target device includes: establishing a differential flat model with the position of the target path point as a flat output based on the kinematic model of the target device; solving the kinematic parameters of the target device at the target path point based on the differential flat model.

10. A path planning device characterized by comprising: The device includes a corridor construction module, a position updating module, and a path planning module; The corridor construction module is configured to, in response to planning an initial planning path of a target device moving from a first position to a second position, construct a safe passing corridor of the target device through surrounding obstacles for the initial planning path, wherein the initial planning path includes a plurality of first path points. The position updating module is configured to perform the following operations on each of the first path points in the plurality of first path points to obtain a plurality of second path points: obtaining a geometric adjustment parameter corresponding to the first path point; and updating a position of the first path point according to the geometric adjustment parameter to obtain a second path point; wherein the geometric adjustment parameter is a parameter for geometric adjustment of a geometric model of the target device in the process of constructing the safe passage corridor. The path planning module is configured to perform path planning according to the plurality of second path points to obtain a target planning path for the target device to move from the first position to the second position.

11. An electronic device, comprising: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the path planning method according to any one of claims 1 to 9 when executing the computer program.

12. A computer-readable storage medium, the computer-readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor to implement the path planning method according to any one of claims 1 to 9.

Images