Research on obstacle avoidance method of robot manipulator based on binocular vision

Abstract

Aiming at static obstacles in indoor environment, the six-axis robot manipulator can avoid obstacles successfully through binocular stereo vision system. According to the principle of camera imaging, the camera calibration is completed by using the camera calibration toolbox of MATLAB, and then the three-dimensional coordinates of the feature points of obstacles are obtained by using the Structure from Motion (SFM) algorithm, so as to determine the location of obstacles. In the aspect of path planning, combining the characteristics of binocular visual obstacle recognition, the artificial potential field (APF) method is used to realize the obstacle avoidance. Finally, the simulation and data analysis under the Matlab development environment verify the feasibility of the algorithm in the binocular vision obstacle avoidance system.