Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Task-Motion Planning with Reinforcement Learning for Adaptable Mobile Service Robots

Yuqian Jiang, Fangkai Yang, Shiqi Zhang, and Peter Stone. Task-Motion Planning with Reinforcement Learning for Adaptable Mobile Service Robots. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019), November 2019.

Download

[PDF]925.2kB  

Abstract

Task-motion planning (TMP) addresses the problem of efficiently generating executable and low-cost task plans in a discrete space such that the ( initially unknown) action costs are determined by motion plans in a corresponding continuous space. A task-motion plan for a mobile service robot that behaves in a highly dynamic domain can be sensitive to domain uncertainty and changes, leading to suboptimal behaviors or execution failures. In this paper, we propose a novel framework, TMP-RL, which is an integration of TMP and reinforcement learning (RL), to solve the problem of robust TMP in dynamic and uncertain domains. The robot first generates a low-cost, feasible task-motion plan by iteratively planning in the discrete space and updating relevant action costs evaluated by the motion planner in continuous space. During execution, the robot learns via model-free RL to further improve its task-motion plans. RL enables adaptability to the current domain, but can be costly with regards to experience; using TMP, which does not rely on experience, can jump-start the learning process before executing in the real world. TMP-RL is evaluated in a mobile service robot domain where the robot navigates in an office area, showing significantly improved adaptability to unseen domain dynamics over TMP and task planning (TP)-RL methods.

BibTeX Entry

@InProceedings{IROS19-jiang,
  author = {Yuqian Jiang and Fangkai Yang and Shiqi Zhang and Peter Stone},
  title = {Task-Motion Planning with Reinforcement Learning for Adaptable Mobile Service Robots},
  booktitle = {Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019)},
  location = {Macau, China},
  month = {November},
  year = {2019},
  abstract = {
  Task-motion planning (TMP) addresses the problem of efficiently generating 
  executable and low-cost task plans in a discrete space such that the (
  initially unknown) action costs are determined by motion plans in a 
  corresponding continuous space.  A task-motion plan for a mobile service  
  robot that behaves in a highly dynamic domain can be sensitive to domain 
  uncertainty and changes, leading to suboptimal behaviors or execution 
  failures. In this paper, we propose a novel framework, TMP-RL, which is an  
  integration of TMP and reinforcement learning (RL), to solve the problem of 
  robust TMP in dynamic and uncertain domains. The robot first generates a 
  low-cost, feasible task-motion plan by iteratively planning in the discrete 
  space and updating relevant action costs evaluated by the motion planner in 
  continuous space. During execution, the robot learns via model-free RL to 
  further improve its task-motion plans. RL enables adaptability to the 
  current domain, but can be costly with regards to experience; using TMP, 
  which does not rely on experience, can jump-start the learning process 
  before executing in the real world. TMP-RL is evaluated in a mobile service 
  robot domain where the robot navigates in an office area, showing 
  significantly improved adaptability to unseen domain dynamics over TMP and 
  task planning (TP)-RL methods.
  },
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Nov 25, 2020 10:07:50