Planning in Action Language BC while Learning Action Costs for Mobile Robots

Authors

  • Piyush Khandelwal The University of Texas at Austin
  • Fangkai Yang The University of Texas at Austin
  • Matteo Leonetti The University of Texas at Austin
  • Vladimir Lifschitz The University of Texas at Austin
  • Peter Stone The University of Texas at Austin

DOI:

https://doi.org/10.1609/icaps.v24i1.13671

Keywords:

Robotics, Answer Set Programming, Robot Task Planning

Abstract

The action language BC provides an elegant way of formalizing dynamic domains which involve indirect effects of actions and recursively defined fluents. In complex robot task planning domains, it may be necessary for robots to plan with incomplete information, and reason about indirect or recursive action effects. In this paper, we demonstrate how BC can be used for robot task planning to solve these issues. Additionally, action costs are incorporated with planning to produce optimal plans, and we estimate these costs from experience making planning adaptive. This paper presents the first application of BC on a real robot in a realistic domain, which involves human-robot interaction for knowledge acquisition, optimal plan generation to minimize navigation time, and learning for adaptive planning.

Downloads

Published

2014-05-11

How to Cite

Khandelwal, P., Yang, F., Leonetti, M., Lifschitz, V., & Stone, P. (2014). Planning in Action Language BC while Learning Action Costs for Mobile Robots. Proceedings of the International Conference on Automated Planning and Scheduling, 24(1), 472-480. https://doi.org/10.1609/icaps.v24i1.13671