Peter Stone's Selected Publications

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


Deep R-Learning for Continual Area Sweeping

Rishi Shah, Yuqian Jiang, Justin Hart, and Peter Stone. Deep R-Learning for Continual Area Sweeping. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2020), October 2020.
1-minute video demonstration; 13-minute Video presentation.

Download

[PDF]374.2kB  [slides.pdf]1.1MB  

Abstract

Coverage path planning is a well-studied problem in robotics in which a robot must plan a path that passes through every point in a given area repeatedly, usually with a uniform frequency. To address the scenario in which some points need to be visited more frequently than others, this problem has been extended to non-uniform coverage planning. This paper considers the variant of non-uniform coverage in which the robot does not know the distribution of relevant events beforehand and must nevertheless learn to maximize the rate of detecting events of interest. This continual area sweeping problem has been previously formalized in a way that makes strong assumptions about the environment, and to date only a greedy approach has been proposed. We generalize the continual area sweeping formulation to include fewer environmental constraints, and propose a novel approach based on reinforcement learning in a Semi-Markov Decision Process. This approach is evaluated in an abstract simulation and in a high fidelity Gazebo simulation. These evaluations show significant improvement upon the existing approach in general settings, which is especially relevant in the growing area of service robotics. We also present a video demonstration on a real service robot.

BibTeX Entry

@InProceedings{IROS20-shah,
  author = {Rishi Shah and Yuqian Jiang and Justin Hart and Peter Stone},
  title = {Deep R-Learning for Continual Area Sweeping},
  booktitle = {Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2020)},
  location = {Las Vegas, NV, USA},
  month = {October},
  year = {2020},
  abstract = {
  Coverage path planning is a well-studied problem in robotics in which a robot must plan a path that passes through every point in a given area repeatedly, usually with a uniform frequency. To address the scenario in which some points need to be visited more frequently than others, this problem has been extended to non-uniform coverage planning. This paper considers the variant of non-uniform coverage in which the robot does not know the distribution of relevant events beforehand and must nevertheless learn to maximize the rate of detecting events of interest. This continual area sweeping problem has been previously formalized  in a way that makes strong assumptions about the environment, and to date only a greedy approach has been proposed. We generalize the continual area sweeping formulation to include fewer environmental constraints, and propose a novel approach based on reinforcement learning in a Semi-Markov Decision Process. This approach is evaluated in an abstract simulation and in a high fidelity Gazebo simulation. These evaluations show significant improvement upon the existing approach in general settings, which is especially relevant in the growing area of service robotics. We also present a video demonstration on a real service robot.
  },
  wwwnote={<a href="https://youtu.be/KqEwfs1xqdw">1-minute video demonstration</a>; <a href="https://drive.google.com/file/d/1tZBNq27rWWxeWowH608meei-shsymSyw/view">13-minute Video presentation</a>.}
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Nov 25, 2020 21:30:59