Modeling manipulation interactions by hidden Markov models

This paper describes a new approach on how to teach everyday manipulation tasks to a robot under the "Learning from Observation" framework. In our previous work, to acquire low-level action primitives of a task automatically, we proposed a technique to estimate essential interactions to complete a task by integrating multiple observations of similar demonstrations. But after many demonstrations are performed, there may be interactions which are the same in nature. These identical interactions should be grouped so that each action primitive becomes unique. For this purpose, a Hidden Markov Model based clustering algorithm is presented which automatically determines the number of independent interactions. We also show that the obtained interactions can be used as discriminators of human behavior. Finally, simulation and experimental results in which a real humanoid robot learns and recognizes essential actions by observing demonstrations are presented.

[1]  L. R. Rabiner,et al.  A probabilistic distance measure for hidden Markov models , 1985, AT&T Technical Journal.

[2]  L. Rabiner,et al.  An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[3]  Masayuki Inaba,et al.  Learning by watching: extracting reusable task knowledge from visual observation of human performance , 1994, IEEE Trans. Robotics Autom..

[4]  Katsushi Ikeuchi,et al.  Toward an assembly plan from observation. I. Task recognition with polyhedral objects , 1994, IEEE Trans. Robotics Autom..

[5]  Geir Hovland,et al.  Skill acquisition from human demonstration using a hidden Markov model , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[6]  Padhraic Smyth,et al.  Clustering Sequences with Hidden Markov Models , 1996, NIPS.

[7]  Adrian E. Raftery,et al.  How Many Clusters? Which Clustering Method? Answers Via Model-Based Cluster Analysis , 1998, Comput. J..

[8]  Katsushi Ikeuchi,et al.  Recognition of human task by attention point analysis , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).

[9]  Yoshihiko Nakamura,et al.  Imitation and primitive symbol acquisition of humanoids by the integrated mimesis loop , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[10]  Katsushi Ikeuchi,et al.  Acquiring hand-action models by attention point analysis , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[11]  Katsushi Ikeuchi,et al.  Generation of a task model by integrating multiple observations of human demonstrations , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).