Abstract: A new behavior-based robot motion planning approach, which uses the fuzzy logic method, is proposed for collision avoidance of multi-joint robot operating in unstructured environments. The sensitive skin is used to build a description of the robot’s surroundings. This approach includes two behaviors: target reaching behavior and obstacle avoidance behavior. The robot selects appropriate one of the two behaviors according to the situation around the robot to reach the target. The computation time is reduced and the algorithm can work in real time in unknown environments. It has been tested in a variety of working scenarios, providing each time a collision-free trajectory for the robot manipulator. Effectiveness of the proposed approach is verified through simulation.

Key words: Fuzzy control, Behavior, Motion planning, Robot