Incremental on-line hierarchical clustering of whole body motion patterns

Dana Kulić, Wataru Takano, Yoshihiko Nakamura

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

30 Citations (Scopus)

Abstract

This paper describes a novel algorithm for autonomous and incremental learning of motion pattern primitives by observation of human motion. Human motion patterns are abstracted into a Hidden Markov Model representation, which can be used for both subsequent motion recognition and generation, analogous to the mirror neuron hypothesis in primates. As new motion patterns are observed, they are incrementally grouped together using hierarchical agglomerative clustering based on their relative distance in the HMM space. The clustering algorithm forms a tree structure, with specialized motions at the tree leaves, and generalized motions closer to the root. The generated tree structure will depend on the type of training data provided, so that the most specialized motions will be those for which the most training has been received. Tests with motion capture data for a variety of motion primitives demonstrate the efficacy of the algorithm.

Original languageEnglish
Title of host publication16th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1016-1021
Number of pages6
ISBN (Print)1424416345, 9781424416349
DOIs
Publication statusPublished - 1 Dec 2007
Externally publishedYes
Event16th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN - Jeju, Korea, Republic of (South)
Duration: 26 Aug 200729 Aug 2007

Publication series

NameProceedings - IEEE International Workshop on Robot and Human Interactive Communication

Conference

Conference16th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN
CountryKorea, Republic of (South)
CityJeju
Period26/08/0729/08/07

Cite this