Abstract: In order to solve the problem of poor obstacle avoidance and low efficiency of robots in obstacle environments, a wheeled industrial robot obstacle avoidance control algorithm based on neighborhood rough sets is proposed. Firstly, the environment perception method based on 2D Laser rangefinder is used to analyze the local environment of the robot and the obstacle environment, so as to provide accurate environmental information for subsequent obstacle avoidance control; Secondly, based on the initial obstacle avoidance decision rules of robots, the knowledge reduction effect of neighborhood rough sets is utilized to reduce them to the minimum obstacle avoidance decision rules, and a feasible path set is obtained; Finally, based on the feasible path set, the ND +(Nondimensional) algorithm is used to determine the direction of the robot’s obstacle avoidance decision, thereby achieving obstacle avoidance control for wheeled industrial robots. The experimental results show that this method can achieve high accuracy and control efficiency of machine obstacle avoidance control while ensuring the stability of obstacle avoidance control. 

Key words: neighborhood rough set, wheeled industrial robots, 2D laser rangefinder, ND+algorithm, obstacle avoidance control