Incremental learning of gestures for human–robot interaction
- 352 Downloads
For a robot to cohabit with people, it should be able to learn people’s nonverbal social behavior from experience. In this paper, we propose a novel machine learning method for recognizing gestures used in interaction and communication. Our method enables robots to learn gestures incrementally during human–robot interaction in an unsupervised manner. It allows the user to leave the number and types of gestures undefined prior to the learning. The proposed method (HB-SOINN) is based on a self-organizing incremental neural network and the hidden Markov model. We have added an interactive learning mechanism to HB-SOINN to prevent a single cluster from running into a failure as a result of polysemy of being assigned more than one meaning. For example, a sentence: “Keep on going left slowly” has three meanings such as, “Keep on (1)”, “going left (2)”, “slowly (3)”. We experimentally tested the clustering performance of the proposed method against data obtained from measuring gestures using a motion capture device. The results show that the classification performance of HB-SOINN exceeds that of conventional clustering approaches. In addition, we have found that the interactive learning function improves the learning performance of HB-SOINN.
KeywordsSocial robot Human–robot interaction Gesture recognition Unsupervised learning Clustering Incremental learning
Funding for this study was primarily provided by Kyoto University’s Global COE program. The authors express their appreciation.
- Argyle M (1988) Bodily Communication. Methuen & Co. Ltd, New YorkGoogle Scholar
- Bagnall AJ, Janacek GJ (2004) Clustering time series from ARMA models with clipped data. In: Proceedings of the tenth ACM SIGKDD international conference on knowledge discovery and data mining, pp 49–58Google Scholar
- Bellman RE (1961) Adaptive control processes. Princeton University Press, Princeton, New Jersey, USAGoogle Scholar
- Ernst J, Nau GJ, Bar-Joseph Z (2005) Clustering short time series gene expression data. Bioinformatics 21(suppl 1):59–68Google Scholar
- Hasanuzzaman M, Ampornaramveth V, Zhang T, Bhuiyan MA, Shirai Y, Ueno H (2004) Real-time vision-based gesture recognition for human robot interaction. IEEE international conference on robotics and biomimetics 2004 (Robio 2004), pp 413–418Google Scholar
- Iwahashi N (2006) Robots that learn language–developmental approach to human–machine conversations. In: Proceedings of international workshop on emergence and evolution of linguistic communication, pp 142–179Google Scholar
- Manning C, Raghavan P, Schutze H (2008) Introduction to information retrieval. Cambridge University Press, CambridgeGoogle Scholar
- Nishida T (2007) Social intelligence design and human computing. In: Huang TS et al (eds) Human computing, LNAI 4451, pp 190–214, Springer-Verlag New York, IncGoogle Scholar
- Störring M, Moeslund TB, Liu Y, Granum E (2004) Computer vision-based gesture recognition for an augmented reality interface. In: 4th IASTED international conference on visualization, imaging, and image processing, pp 766–771Google Scholar
- Wang T, Shum H, Xu Y, Zheng N (2001) Unsupervised analysis of Human gestures. In: IEEE pacific rim conference on multimedia, pp 174–181Google Scholar