Peter Stone's Selected Publications

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


APPLD: Adaptive Planner Parameter Learning from Demonstration

Xuesu Xiao, Bo Liu, Garrett Warnell, Jonathan Fink, and Peter Stone. APPLD: Adaptive Planner Parameter Learning from Demonstration. IEEE Robotics and Automation Letters, presented at International Conference on Intelligent Robots and Systems (IROS), June 2020.
5-minute Video presentation; 15-minute Video presentation.

Download

[PDF]2.2MB  [slides.pdf]21.1MB  

Abstract

Existing autonomous robot navigation systems allow robots to move from one point to another in a collision-free manner. However, when facing new environments, these systems generally require re-tuning by expert roboticists with a good understanding of the inner workings of the navigation system. In contrast, even users who are unversed in the details of robot navigation algorithms can generate desirable navigation behavior in new environments via teleoperation. In this paper, we introduce APPLD, Adaptive Planner Parameter Learning from Demonstration, that allows existing navigation systems to be successfully applied to new complex environments, given only a human-teleoperated demonstration of desirable navigation. APPLD is verified on two robots running different navigation systems in different environments. Experimental results show that APPLD can outperform navigation systems with the default and expert-tuned parameters, and even the human demonstrator themselves.

BibTeX Entry

@article{ral20-xiao,
  title={{APPLD}: Adaptive Planner Parameter Learning from Demonstration},
  author={Xuesu Xiao and Bo Liu and Garrett Warnell and Jonathan Fink and Peter Stone},
  Journal = {{IEEE} Robotics and Automation Letters, presented at International Conference on Intelligent Robots and Systems ({IROS})},
  abstract={Existing autonomous robot navigation systems allow robots to move from one point to another in a collision-free manner. However, when facing new environments, these systems generally require re-tuning by expert roboticists with a good understanding of the inner workings of the navigation system. In contrast, even users who are unversed in the details of robot navigation algorithms can generate desirable navigation behavior in new environments via teleoperation. In this paper, we introduce APPLD, Adaptive Planner Parameter Learning from Demonstration, that allows existing navigation systems to be successfully applied to new complex environments, given only a human-teleoperated demonstration of desirable navigation. APPLD is verified on two robots running different navigation systems in different environments. Experimental results show that APPLD can outperform navigation systems with the default and expert-tuned parameters, and even the human demonstrator themselves.},
  year={2020},
  month={June},
  doi="10.1109/LRA.2020.3002217",
  wwwnote={<a href="https://www.youtube.com/watch?v=umK8whn6TDs">5-minute Video presentation</a>; <a href="https://www.youtube.com/watch?v=7mHUf0S1nHc&t=1s">15-minute Video presentation</a>.}
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Nov 25, 2020 10:07:49