Identifying qualitatively different outcomes of actions: Gaining autonomy through learning

Tim Oates, Matthew D. Schmill, Paul R Cohen

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

7 Scopus citations

Abstract

An unsupervised method for learning models of environmental dynamics based on clustering multivariate time series is presented. Experiments with a Pioneer-1 mobile robot demonstrate the utility of the method. It is shown that the models acquired by the robot correlate surprisingly well with human models of the environment.

Original languageEnglish (US)
Title of host publicationProceedings of the International Conference on Autonomous Agents
Pages110-111
Number of pages2
Publication statusPublished - 2000
Externally publishedYes
Event4th International Conference on Autonomous Agents - Barcelona, Spain
Duration: Jun 3 2000Jun 7 2000

Other

Other4th International Conference on Autonomous Agents
CityBarcelona, Spain
Period6/3/006/7/00

    Fingerprint

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Oates, T., Schmill, M. D., & Cohen, P. R. (2000). Identifying qualitatively different outcomes of actions: Gaining autonomy through learning. In Proceedings of the International Conference on Autonomous Agents (pp. 110-111)