Learning arm motion strategies for balance recovery of humanoid robots

Masaki Nakada*, Brian Allen, Shigeo Morishima, Demetri Terzopoulos

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Humans are able to robustly maintain balance in the presence of disturbances by combining a variety of control strategies using posture adjustments and limb motions. Such responses can be applied to balance control in two-armed bipedal robots. We present an upper-body control strategy for improving balance in a humanoid robot. Our method improves on lowerbody balance techniques by introducing an arm rotation strategy (ARS). The ARS uses Q-learning to map sensed state to the appropriate arm control torques. We demonstrate successful balance in a physically-simulated humanoid robot, in response to perturbations that overwhelm lower-body balance strategies alone.

Original languageEnglish
Title of host publicationProceedings - EST 2010 - 2010 International Conference on Emerging Security Technologies, ROBOSEC 2010 - Robots and Security, LAB-RS 2010 - Learning and Adaptive Behavior in Robotic Systems
Pages165-170
Number of pages6
DOIs
Publication statusPublished - 2010 Dec 1
Event2010 International Conference on Emerging Security Technologies, EST 2010, Robots and Security, ROBOSEC 2010, Learning and Adaptive Behavior in Robotic Systems, LAB-RS 2010 - Canterbury, United Kingdom
Duration: 2010 Sept 62010 Sept 8

Publication series

NameProceedings - EST 2010 - 2010 International Conference on Emerging Security Technologies, ROBOSEC 2010 - Robots and Security, LAB-RS 2010 - Learning and Adaptive Behavior in Robotic Systems

Conference

Conference2010 International Conference on Emerging Security Technologies, EST 2010, Robots and Security, ROBOSEC 2010, Learning and Adaptive Behavior in Robotic Systems, LAB-RS 2010
Country/TerritoryUnited Kingdom
CityCanterbury
Period10/9/610/9/8

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'Learning arm motion strategies for balance recovery of humanoid robots'. Together they form a unique fingerprint.

Cite this