Obstacles avoidance of artificial potential field method with memory function in complex environment

Robots have more and more applications in various fields. The path planning and the path recognition, as important factors in robot intelligence, have important value in theory and practice. The advantages of obstacle avoidance algorithm based on traditional artificial potential field are low computational complexity, good real-time characteristics and smooth path of obstacle avoidance. Yet, the disadvantages are existing trap area, moving back and forward side obstacles and can't reach target near obstacles. To improve those shortcomings, simulated annealing algorithm had been investigated to skip local minimum points, besides, the distance between the robot and obstacles is considered and new potential field functions are proposed and so on. Those methods mostly based on improving single shortcoming of traditional artificial potential field method, so the result is not promising in complex environment. Especially, when the target point is surrounded by obstacles, robot can't reach target and those methods will let the robot move back and forward all the time or rotate around the target. In this paper, a kind of edge followed method with memory function is proposed to resolve the shortcomings of artificial potential field method presented above. This method stepped along the edge of obstacles to skip the local minimum points of artificial potential method. Through record and analyzing the local minimum points the robot pass through to estimate whether the target is surrounded by obstacles in order to avoid the robot move back and forward all the time or rotate around the target point. The key point of this method is the edge behavior activation and exit condition, the record of local minimum points and the estimation of target been surrounded by obstacles. Performance of the proposed algorithm is evaluated through experiments and the result shows that the proposed algorithm can solve the robot obstacle avoidance in complex environment.