Path Planning Method Based on Triangle Inner Guided RRT Algorithm

Abstract

The invention relates to a path planning method based on a triangle inwardly guided RRT algorithm. In order to overcome the shortcomings of the RRT algorithm and the danger of falling into a local minimum if the target point appears in a random point with a certain probability, this method proposes a method to guide the random tree by using the innards of the triangle. By using the random point generated by the random function, the point closest to the random point in the random tree and the target point to form the three vertices of the triangle, then calculate the inner coordinates of the triangle, and use the inner coordinates as the growth direction of the random tree ; In addition, adjust the sampling method by recording the number of inner guides used and the growth of the random tree under a certain number of cycles. This not only guides the growth of the random tree, but also effectively avoids the risk of falling into a local minimum. The method of the invention improves planning efficiency, requires less time for path planning, fewer iterations and shorter paths.

Description

technical field [0001] The invention relates to the field of path planning, in particular to a path planning method based on a triangle inner-guided RRT algorithm. Background technique [0002] Path planning has always been a research hotspot in the field of mobile robots. The main task of path planning is to find a continuous collision-free path from the initial state point to the target state point in space, while satisfying the corresponding conditions and constraints. [0003] Commonly used trajectory planning algorithms include graph search algorithm, bionic intelligence algorithm, artificial potential field method, etc. Traditional path planning algorithms, such as the artificial potential field method, are based on vector synthesis and plan the motion path of the robot under the combined action of the repulsive force of the obstacle to the mobile robot and the attractive force of the target position to the mobile robot, but when the attractive force When the resulta...

AI Technical Summary

Problems solved by technology

However, because the basic RRT algorithm adopts a uniform sampling strategy and lacks guidance information, the resulting path is tortuous. Under the complex obstacle distribution, the planning time is long; in addition, for the target point to appear as a random point with a certain probability In the sampling point, although this can improve the planning efficiency, it may also lead to falling into a local minimum, and eventually no path can be found under the specified time or number of iterations

Images