Probabilistic model of whole-body motion imitation from partial observations

Dongheui Lee, Yoshihiko Nakamura

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, a new mimesis scheme is proposed. This scheme enables for a humanoid to imitate human's motion even though the humanoid cannot see human's whole-body motion and the humanoid has not seen the exactly same motion so far. Mimesis framework is based on continues Hidden Markov Model. Viterbi algorithm is applied in order to generate more various motion patterns than the number of existing Hidden Markov Models. In order to imitate other's motion in a smooth way, a smoothing technique in generation problem is realized. The feasibility of this method is demonstrated by simulation on a 20 degrees of freedom humanoid robot configuration.

Original languageEnglish
Title of host publication2005 International Conference on Advanced Robotics, ICAR '05, Proceedings
Pages337-343
Number of pages7
DOIs
StatePublished - 2005
Externally publishedYes
Event12th International Conference on Advanced Robotics, 2005. ICAR '05 - Seattle, WA, United States
Duration: 18 Jul 200520 Jul 2005

Publication series

Name2005 International Conference on Advanced Robotics, ICAR '05, Proceedings
Volume2005

Conference

Conference12th International Conference on Advanced Robotics, 2005. ICAR '05
Country/TerritoryUnited States
CitySeattle, WA
Period18/07/0520/07/05

Keywords

  • Hidden Markov Models
  • Imitation
  • Learning

Fingerprint

Dive into the research topics of 'Probabilistic model of whole-body motion imitation from partial observations'. Together they form a unique fingerprint.

Cite this