CN-121994249-A - Navigation path determining method, device and program product

CN121994249ACN 121994249 ACN121994249 ACN 121994249ACN-121994249-A

Abstract

The application relates to a navigation path determining method, a navigation path determining device and a navigation path determining program product. Determining at least two candidate navigation paths from a grid map of an area where the robot is located according to the navigation start-stop position of the robot, selecting an initial navigation path from the candidate navigation paths according to joint size information of the robot, action time sequence sequences to be executed by the robot in the running process and passable area information of each candidate navigation path, and optimizing the initial navigation path according to the action time sequence and passable area information of the initial navigation path to obtain a target navigation path corresponding to the navigation start-stop position, wherein the action time sequence comprises actions of the robot at different running moments in the running process. By adopting the method, the accuracy of the determination of the navigation path of the robot can be improved.

Inventors

Shi Youning
ZHANG CAO
LI YANG

Assignees

重庆凤凰技术有限公司

Dates

Publication Date: 20260508
Application Date: 20260318

Claims (10)

1. A navigation path determination method, the method comprising: determining at least two candidate navigation paths from a grid map of an area where the robot is located according to the navigation start-stop positions of the robot; Selecting an initial navigation path from the candidate navigation paths according to joint size information of the robot, action time sequence to be executed by the robot in the driving process and passable area information of each candidate navigation path, wherein the action time sequence comprises actions of the robot at different driving moments in the driving process; and optimizing the initial navigation path according to the action time sequence and the passable area information of the initial navigation path to obtain a target navigation path corresponding to the navigation start-stop position.
2. The method of claim 1, wherein the sequence of motion sequences comprises a sequence of upper limb motion sequences, wherein the selecting an initial navigation path from the candidate navigation paths based on joint size information of the robot, the sequence of motion sequences to be performed by the robot during travel, and passable area information of each candidate navigation path comprises: Constructing an upper limb action convex hull of the robot at each driving moment according to the joint size information of the robot and an upper limb action time sequence to be executed by the robot in the driving process; For each candidate navigation path, determining a collision risk value of the robot running on the candidate navigation path according to the upper limb action convex hulls of the robot at different running moments and the passable area information of the candidate navigation path; and selecting an initial navigation path from the candidate navigation paths according to collision risk values corresponding to the candidate navigation paths.
3. The method according to claim 2, wherein the determining the collision risk value of the robot traveling on the candidate navigation path according to the upper limb motion convex hull of the robot at different traveling moments and the passable area information of the candidate navigation path comprises: According to the upper limb action convex hulls of the robot at different driving moments and the passable area information of the candidate navigation paths, determining the number of collisions and the collision distance of the robot driving on the candidate navigation paths; And determining a collision risk value of the robot driving on the candidate navigation path according to the collision times and the collision distance.
4. A method according to claim 3, wherein the determining the number of collisions and the collision distance of the robot traveling on the candidate navigation path according to the upper limb motion convex hull of the robot at different traveling moments and the passable area information of the candidate navigation path comprises: determining grid positions of the robot on the candidate navigation paths at each driving moment according to the speed information of the robot; Determining collision risk values of the robot at each grid position according to the upper limb action convex hulls and grid positions of the robot at different driving moments and the passable area information of the candidate navigation paths; And determining the collision times and the collision distance of the robot on the candidate navigation path according to the collision risk values of the robot at different grid positions.
5. The method according to any one of claims 1-4, wherein the action sequence includes an upper limb action sequence, and the optimizing the initial navigation path according to the action sequence and passable area information of the initial navigation path to obtain a target navigation path corresponding to the navigation start-stop position includes: Determining a collision grid in the initial navigation path according to the passable area information of the initial navigation path and an upper limb action convex hull of the robot at each driving moment, wherein the upper limb action convex hull at each driving moment is constructed according to the joint size information of the robot and the upper limb action time sequence; determining path optimization information corresponding to each collision grid according to the grid position of the collision grid and the upper limb action convex hulls of the robot at each grid position in the initial navigation path, wherein the upper limb action convex hull of each grid position is an upper limb action convex hull of the robot at the running time from the running of the robot to the grid position; And optimizing the initial navigation path according to path optimization information corresponding to each collision grid to obtain a target navigation path corresponding to the navigation start-stop position.
6. The method according to claim 5, wherein the determining path optimization information corresponding to the collision grid according to the grid position of the collision grid and the upper limb motion convex hull of each grid position of the robot in the initial navigation path includes: determining the minimum distance between the collision grid and the upper limb action convex hull according to the grid position of the collision grid and the upper limb action convex hull of the robot at the grid position of the collision grid; determining a path optimization direction corresponding to the collision grid according to the distance endpoint corresponding to the minimum distance; And determining path optimization information corresponding to the collision grid according to the minimum distance and the path optimization direction.
7. The method according to claim 5, wherein optimizing the initial navigation path according to the path optimization information corresponding to each collision grid to obtain the target navigation path corresponding to the navigation start-stop position comprises: for each collision grid, determining a reference grid corresponding to the collision grid in the initial navigation path according to path optimization information corresponding to the collision grid, wherein the reference grid is a non-collision grid surrounding the collision grid; Determining, for each reference grid, a grid evaluation value of the reference grid according to a grid position of the reference grid and speed information of the robot; and optimizing the initial navigation path according to the grid evaluation value of each reference grid to obtain a target navigation path corresponding to the navigation start-stop position.
8. The method of claim 7, wherein the determining the grid evaluation value of the reference grid based on the grid position of the reference grid and the speed information of the robot comprises: Determining the safe cost value of the reference grid according to the path optimization information of the reference grid, wherein the path optimization information of the reference grid is determined according to the grid position of the reference grid and the upper limb action convex hull of the robot at the grid position of the reference grid; Determining a path smoothing value of the reference grid according to the path position information of the initial navigation path and the grid position of the reference grid; Determining a running limit value of the robot running to the reference grid according to the speed information of the robot; and determining a grid evaluation value of the reference grid according to the safety cost value, the path smoothing value and the running limit value.
9. A navigation path determining apparatus, the apparatus comprising: The path generation module is used for determining at least two candidate navigation paths from the grid map of the area where the robot is located according to the navigation start-stop positions of the robot; The path selection module is used for selecting an initial navigation path from the candidate navigation paths according to the joint size information of the robot, the action time sequence to be executed by the robot in the driving process and the passable area information of each candidate navigation path, wherein the action time sequence comprises actions of the robot at different driving moments in the driving process; and the path optimization module is used for optimizing the initial navigation path according to the action time sequence and the passable area information of the initial navigation path to obtain a target navigation path corresponding to the navigation start-stop position.
10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method of any one of claims 1 to 8.

Description

Navigation path determining method, device and program product Technical Field The present application relates to the field of robotics, and in particular, to a navigation path determining method, apparatus, and program product. Background With the continuous development of the robot field, in order to improve the working efficiency of the robot, an automatic navigation strategy for the robot appears, that is, the robot can automatically plan an accessible navigation path according to the position to be reached. However, in the above manner, the robot is generally regarded as a fixed geometric model, so that a navigation path which does not collide when the robot is the fixed geometric model is selected, different movements (for example, clamping goods with upper limbs) of the robot in combination with specific requirements in the running process in practical application are ignored, and the pose difference between the robot and the fixed geometric model in the moving process is large, which reduces the accuracy of determining the navigation path, thereby reducing the running safety of the robot. Disclosure of Invention In view of the above, the present application provides a navigation path determining method, apparatus and program product capable of improving the accuracy of navigation path determination. In a first aspect, the present application provides a navigation path determining method, including: Determining at least two candidate navigation paths from a grid map of an area where the robot is located according to the navigation start-stop positions of the robot; Selecting an initial navigation path from the candidate navigation paths according to joint size information of the robot, action time sequence sequences to be executed by the robot in the driving process and passable area information of each candidate navigation path, wherein the action time sequence sequences comprise actions of the robot at different driving moments in the driving process; and optimizing the initial navigation path according to the action time sequence and the passable area information of the initial navigation path to obtain a target navigation path corresponding to the navigation start-stop position. In the navigation path determining method, on one hand, the initial navigation paths with low collision degree are initially screened out from the candidate navigation paths by combining the action time sequence of the robot and the passable area information of the candidate navigation paths, so that the adaptation of the selected initial navigation paths to the action change of the robot during operation can be ensured, the task amount of the subsequent path optimizing process can be reduced, and on the other hand, the initial navigation paths are optimized by combining the action time sequence, the passable area of the target navigation paths finally obtained by optimization can be ensured, the action change of the robot during operation is met, the accuracy of the navigation path determination is improved, and the operation safety of the robot is ensured. In an alternative embodiment of the first aspect, the action time sequence includes an upper limb action time sequence, and selecting an initial navigation path from the candidate navigation paths according to joint size information of the robot, the action time sequence to be executed by the robot during traveling, and passable area information of each candidate navigation path, including: constructing an upper limb action convex hull of the robot at each running moment according to joint size information of the robot and an upper limb action time sequence to be executed by the robot in the running process; Aiming at each candidate navigation path, determining a collision risk value of the robot running on the candidate navigation path according to the upper limb action convex hulls of the robot at different running moments and the passable area information of the candidate navigation path; and selecting an initial navigation path from the candidate navigation paths according to collision risk values corresponding to the candidate navigation paths. In the above-mentioned alternative embodiment, on the one hand, the decoupling processing of the upper limb and the chassis of the robot is realized by constructing the upper limb action convex hull of the robot, on the premise of ensuring the planning independence of the upper limb task, the upper limb action and the chassis are related by time sequence matching, so that the whole body coordination is realized without increasing the calculation burden of high-dimensional joint modeling, and on the other hand, the collision risk value of each candidate navigation path is determined by combining the upper limb action convex hull, so that the collision risk value obtained by calculation is matched with the actual upper limb action time sequence of the robot, thereby improving the accuracy of the initial navigation path and l