Robot obstacle avoidance method and device

Abstract

The invention discloses a robot obstacle avoidance method and device and relates to the technical field of computers. One specific embodiment of the method comprises steps of sampling multiple groupsof speeds in a speed space according to a motion limiting condition of a robot to simulate a motion track of the robot at the multiple groups of speeds to obtain a simulated track set; wherein the multiple sets of speeds comprise the speeds of the robot at multiple moments; performing expansion processing on obstacles in the environment map, and filtering movement tracks passing through the obstacles or expansion areas from the simulated track set to obtain an optimized track set; and respectively evaluating the motion trails of the optimized trajectory set by adopting an evaluation function so as to determine a target trajectory from the optimized trajectory set according to an evaluation result, and driving the robot to move by using the speed corresponding to the target trajectory. According to the method, after the obstacle is expanded, the motion trail passing through the obstacle or the expansion area in the simulation trail set is filtered, the target trail is determined in combination with the evaluation function, and the robot is prevented from colliding with the obstacle.

Description

technical field [0001] The invention relates to the field of computers, in particular to a robot obstacle avoidance method and device. Background technique [0002] The basic requirement for autonomous navigation of mobile robots is obstacle avoidance. Obstacle avoidance means that the mobile robot uses the obstacle avoidance algorithm to effectively avoid obstacles when it senses static objects and dynamic objects that hinder its passage through sensors during walking based on the state information of the collected obstacles, and finally reaches the target position. In the prior art, commonly used obstacle avoidance algorithms include a visual map method, an artificial potential field method, a Vector Field Histogram (Vector Field Histogram, VFH) method, and the like. [0003] In the course of realizing the present invention, the inventor finds that there are at least the following problems in the prior art: [0004] The existing obstacle avoidance algorithm treats the mo...

AI Technical Summary

Problems solved by technology

[0004] The existing obstacle avoidance algorithm treats the mobile robot as a particle, regardless of the overall outline and shape of the mobile robot. The path obtained by using the obstacle avoidance algorithm for local path planning may be very close to obstacles in the real world, and the robot moves along this path will cause the mobile robot to collide with obstacles and be impassable

Images