Multi-method learning and assimilation |
| |
| Affiliation: | 1. Department of Adaptive Machine Systems, Graduate School of Engineering, Osaka University, 2-1 Yamadaoka, Suita, Osaka, 565-0871, Japan;2. Mobile Robot Laboratory and GVU Center, College of Computing, Georgia Institute of Technology, Atlanta, GA, USA;1. Department of Economics, The New School for Social Research, 6 East 16th Avenue, New York, NY 10003, USA;2. Algorithmic Social Sciences Research Unit, Department of Economics, University of Trento, Trento, Italy;3. Algorithmic Social Sciences Research Unit & the School of Social Sciences, University of Trento, Via inama, 5, Trento, Italy;1. Washington University School of Medicine, St. Louis;2. University of Colorado Denver;3. National Institute of Mental Health (NIMH) Intramural Research Program, Bethesda, MD;4. University of Maryland, College Park;5. University of Waterloo, Waterloo, ON, Canada |
| |
| Abstract: | Considering the wide range of possible behaviours to be acquired for domestic robots, applying a single learning method is clearly insufficient. In this paper, we propose a new strategy for behaviour acquisition for domestic robots where the behaviours are acquired using multiple differing learning methods that are subsequently incorporated into a common behaviour selection system, enabling them to be performed in appropriate situations. An example of the implementation of this strategy applied to the entertainment humanoid robot QRIO is introduced and the results are discussed. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
