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

Biped Walk Learning On Nao Through Playback and Real-time Corrective Demonstration

Çetin Meriçli and Manuela Veloso. Biped Walk Learning On Nao Through Playback and Real-time Corrective Demonstration. In Workshop on Agents Learning Interactively from Human Teachers, 9th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2010), 2010.

Download

[PDF] 

Abstract

We contribute a two-phase biped walk learning approach which is developed on the Aldebaran Nao humanoid robot. In the first phase, we identify and save a complete walk cycle from the motions of the robot while it is executing a given walk algorithm as a black box. We show how the robot can then play back such a recorded cycle in a loop to obtain a good open-loop walking behavior. In the second phase, we introduce an algorithm to directly modify the recorded walk cycle using real time corrective feedback provided by a human. The algorithm learns joint movement corrections to the open-loop walk based on the corrective feedback as well as the robot's sensory readings while walking autonomously. Compared to the open-loop algorithm and hand-tuned closed-loop walking algorithms, our two-phase method provides an improvement in walking stability, as demonstrated by our experimental results.

BibTeX

@InProceedings{MericliAAMAS2010b,
  author    = {Çetin Meriçli and Manuela Veloso},
  title     = {Biped Walk Learning On Nao Through Playback and Real-time Corrective Demonstration},
  booktitle = {Workshop on Agents Learning Interactively from Human Teachers, 9th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2010)},
  abstract  = {We contribute a two-phase biped walk learning approach which is developed on the Aldebaran Nao humanoid robot. In the first phase, we identify and save a complete walk cycle from the motions of the robot while it is executing a given walk algorithm as a black box. We show how the robot can then play back such a recorded cycle in a loop to obtain a good open-loop walking behavior. In the second phase, we introduce an algorithm to directly modify the recorded walk cycle using real time corrective feedback provided by a human. The algorithm learns joint movement corrections to the open-loop walk based on the corrective feedback as well as the robot's sensory readings while walking autonomously. Compared to the open-loop algorithm and hand-tuned closed-loop walking algorithms, our two-phase method provides an improvement in walking stability, as demonstrated by our experimental results.}
  year      = {2010},
  bib2html_pubtype = {Refereed Workshop},
  bib2html_rescat = {Learning from Demonstration},
  bib2html_dl_pdf = {../files/cmericliAAMAS2010WalkLearningShort.pdf},
}

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