An Obstacle Avoidance Method Based on Dynamic Window and Virtual Target Point

Abstract

Provided is an obstacle avoiding method based on a dynamic window and virtual target points. A robot is guided by virtual target points to advance, and a motion instruction of the robot is issued through a dynamic window, and thus, the robot can avoid an obstacle to reach a target point. First, a robot predicts the motion track of an obstacle according to the angle and distance information of theobstacle fed back by a sensor on the robot; then, multiple virtual target points are generated according to the track prediction of the obstacle, the motion state of the robot and the position of a real target point, and an optimal virtual target is screened out by considering the direction of the robot and the distance between the virtual target points and the real target point through an evaluation function; and finally, the robot generates a control instruction set of the robot for the next moment through a dynamic window approach according to the track prediction of the obstacle and the positions of the virtual target points, and screens out an optimal control instruction of the robot for the next moment by considering the direction and motion speed of the robot and the distance between the robot and the target point through an evaluation function.

Description

technical field [0001] The invention relates to an obstacle avoidance method for a robot in a dynamic unknown environment. For the obstacles detected during the movement of the robot, the obstacle avoidance algorithm designed by the invention generates a virtual target point to guide the robot forward by predicting the trajectory of the obstacle. The window issues the movement instructions of the robot, so that the robot can avoid obstacles and reach the target point. Background technique [0002] With the development of robot technology, more and more mobile robots are used in production and life, such as medical service robots, home service robots, etc. To complete the task of transporting objects, mobile robots need to have functions such as sensing the environment, path planning, and motion control. In addition, mobile robots also need to deal with obstacles that appear during the movement, perceive and avoid them, and ensure that the robot can operate safely. [0003]...

AI Technical Summary

Problems solved by technology

However, using the artificial potential field method is easy to cause the robot to generate local oscillations in areas with dense obstacles.

Farah Kamil et al. proposed an obstacle avoidance algorithm to enable the robot to work safely in an environment where the position, shape and motion state of obstacles are unknown (F.Kamil, T.S.Hong, W.Khaksar, M.Y.Moghrabiah, N.Zulkifli, S.A.Ahmad .New Robot Navigation Algorithm for Arbitrary Unknown Dynamic Environments based on FuturePrediction and Priority Behavior.Expert Systems with Applications%@0957-4174.(2017).), however, this method was only tested in the simulation environment and did not consider the kinematics of the robot characteristic

Images