A potential function and artificial neural network for path planning in dynamic environments based on self-reconfigurable mobile robot system

A dynamic environment is defined that either the obstacles or the goal or both are in motion. There are many methods to deal with the problems of the path planning of the robot in dynamic environment. In the case of the dynamic environment, one method for path planning is to take the velocity of the goal and obstacles into account. In this paper, we propose a method for path planning in dynamic environments that uses a potential function which indicates the probability that a robot will collide with an obstacle. The traditional potential function method has many shortcomings that are not suitable for the robot in the dynamic environment. So a modified method of potential function is proposed, and artificial neural network (ANN) is also used in order to get the information of velocity and positions of the obstacles and goal. This paper will discuss how to define the attractive force and repulsive force, and how to predict the velocity of the obstacle and the distance between obstacle and the robot.