Sorted by DateClassified by Publication TypeSorted by First Author Last NameClassified by Topic

Complementary Humanoid Behavior Shaping using Corrective Demonstration

Çetin Meriçli, Manuela Veloso, and H. Levent Akın. Complementary Humanoid Behavior Shaping using Corrective Demonstration. In Proceedings of 2010 IEEE-RAS International Conference on Humanoid Robots, December 6-8, 2010, Nashville, TN, USA, 2010.

Download

[PDF] 

Abstract

A humanoid robot can perform a task through a policy mapping from its sensed state to the appropriate task actions. We assume that a hand-coded controller can capture such a mapping only for the core cases of the given task. As the complexity of the situation increases, the harder it is to refine the controller, and such refinements become tedious and error prone. Based on the fact that a human can detect the failures of a robot executing the hand-coded controller, we contribute a corrective learning from demonstration approach to improve the robot performance. Corrections are captured as new state action pairs, and during the autonomous humanoid robot execution, the controller is replaced by the demonstration corrections when the new state is found to be similar to the corrected state. We focus on the Aldebaran Nao humanoid robot and a concrete complex dribbling task in an environment with obstacles. We present experimental results showing an improvement in the humanoid task performance when the corrective demonstration is used in addition to the basic hand-coded controller.

BibTeX

@inproceedings{mericli2010d,
  author    = {Çetin Meriçli and Manuela Veloso and H. Levent Akın},
  title     = {Complementary Humanoid Behavior Shaping using Corrective Demonstration},
  booktitle = {Proceedings of 2010 IEEE-RAS International Conference on Humanoid Robots, December 6-8, 2010, Nashville, TN, USA},
  year      = {2010},
  abstract  = { A humanoid robot can perform a task through a policy mapping from its
    sensed state to the appropriate task actions. We assume that a
    hand-coded controller can capture such a mapping only for the core
    cases of the given task. As the complexity of the situation increases, the
    harder it is to refine the controller, and such refinements become
    tedious and error prone. Based on the fact that a human can detect the
    failures of a robot executing the hand-coded controller, we
    contribute a corrective learning from demonstration approach to
    improve the robot performance. Corrections are captured as new state
    action pairs, and during the autonomous humanoid robot execution, the
    controller is replaced by the demonstration corrections when the new
    state is found to be similar to the corrected state. We focus on the
    Aldebaran Nao humanoid robot and a concrete complex dribbling task in
    an environment with obstacles. We present experimental results showing
    an improvement in the humanoid task performance when the corrective
    demonstration is used in addition to the basic hand-coded controller.},
  bib2html_pubtype = {Refereed Conference},
  bib2html_rescat = {Learning from Demonstration},
  bib2html_dl_pdf = {../files/cmericliHumanoids2010BehaviorShaping.pdf},
}

Generated by bib2html.pl (written by Patrick Riley ) on Thu May 01, 2014 16:27:43