Parallel Optimization of Motion Controllers via Policy Iteration
Jefferson A. Coelho, Ramesh K. Sitaraman, Roderic A. Grupen · 1995
This paper describes a policy iteration algorithm for optimizing the performance of a harmonic function-based controller with respect to a user-defined index. Value functions are represented as potential distributions over the problem domain, being control policies represented as gradient fields over the same domain. All intermediate policies are intrinsically safe, i.e. collisions are not promoted during the adaptation process. The algorithm has efficient implementation in parallel SIMD architectures. One potential application -- travel distance minimization -- illustrates its usefulness. 1 INTRODUCTION Harmonic functions have been proposed as a uniform framework for the solution of several versions of the motion planning problem. Connolly and Grupen [Connolly and Grupen, 1993] have demonstrated how harmonic functions can be used to construct smooth, complete artificial potentials with no local minima. In addition, these potentials meet the criteria established in [Rimon and...