Robot action planning via explanation-based learning

Abstract

Domain-specific searching heuristics is greatly influential upon the searching efficiency of robot action planning (RAP), but its computer-realized recognition and acquisition, i.e., learning, is difficult. This paper makes an exploration into this challenge. First, a problem formulation of RAP is made. Then, by applying explanation-based learning, which is currently the only approach to acquiring domain-specific searching heuristics, a new learning based method is developed for RAP, named robot action planning via explanation-based learning (RAPEL). Finally, an example study demonstrates the effectiveness of RAPEL.