Improved RRT path planning method based on pathfinder algorithm

Abstract

The invention discloses an improved RRT path planning method based on a pathfinder algorithm. According to the method, a guide path is introduced on the basis of a traditional RRT path planning algorithm, an optimal guide path is generated by using a pathfinder optimization algorithm, and the generation of a new node Xnew of the RRT is guided by using the optimal guide path, so that not only is the randomness of the RRT algorithm utilized, but also the characteristic that the new node is expanded towards a target point direction by using the guide path is utilized, and the path planning accuracy is improved. Therefore, the target performance of path planning is improved, the randomness and search time of path search are reduced, the efficiency, real-time performance and success rate of path planning are improved, and the obstacle avoidance capability is enhanced. According to the method, the generation of the random points is determined by introducing a path point adjacent area sampling method, so that each path point can be sampled in a specific area, the randomness of sampling points is avoided, the target guidance quality during RRT algorithm sampling is improved, and collision with obstacles is avoided.

Description

technical field [0001] The invention relates to the technical field of intelligent control, in particular to an improved RRT path planning method based on a pathfinder algorithm. Background technique [0002] In recent years, the study of path planning problem has emerged in the field of robotics and has become a research hotspot. The path planning problem is crucial for most robots, and its goal is to find a collision-free path in the workspace from an initial point to a goal point, satisfying certain optimization criteria. Path planning is further divided into global path planning and local path planning. Global path planning can generate a complete path from the starting point to the end point in a known working environment, and local path planning can use sensor information to avoid obstacles in real time. [0003] Path planning algorithms mainly include sampling-based methods, artificial potential field methods, visual graph methods, biological intelligence algorithms,...

AI Technical Summary

Problems solved by technology

In the literature "Song Yu, Wang Zhiming. Improved path planning algorithm for RRT mobile robots [J]. Journal of Changchun University of Technology, 2018, 39(6): 546-550." In this paper, the artificial potential field method and the RRT algorithm are combined, and the resultant force direction The expansion of the guided search tree can reduce the number of sampling points and the length of the search path, but the search time increases significantly

[0005] In order to further enhance the rapidity of the RRT algorithm, the derivative algorithm RRT-Connect of RRT is proposed. This algorithm generates a random tree at the starting point and the end point until the two trees meet. However, both the RRT algorithm and RRT-Connect have limitations. Because their leaves are randomly generated and lack of targetness, the generated paths are often not optimal, resulting in poor real-time performance and low efficiency, and these characteristics are particularly important for practical applications.

Images