Robot path planning using potential field representation

Abstract

Finding a safe, smooth, and efficient path to move an object through obstacles is necessary for object manipulation in robotics and automation. This thesis presents an approach to the two-dimensional as well as three-dimensional findpath problems that divide the problem into two steps. First, rough paths are found based only on topological information. This is accomplished by assigning to each obstacle an artificial potential similar to the electrostatic potential to prevent the moving object from colliding with the obstacles, and then locating minimum potential valleys. Second, the paths defined by the minimum potential valleys are modified to obtain an optimal collision-free path and orientations of the moving object along the path. Three algorithms are given to accomplish this second step. The first algorithm simply minimizes a weighted sum of the path length and the total potential experienced by the moving object along the path. This algorithm solves only easy problems where the free space between the obstacles is wide. The other two algorithms are developed to handle the problems in which intelligent maneuvering of the moving object among tightly packed obstacles is necessary. These three algorithms based on potential fields are nearly complete in scope, and solve a large variety of problems.