This paper describes a novel approach for autonomous and incremental learning of motion pattern primitives by observation of human motion. Human motion patterns are abstracted into a dynamic stochastic model, which can be used for both subsequent motion recognition and generation, analogous to the mirror neuron hypothesis in primates. The model size is adaptable based on the discrimination requirements in the associated region of the current knowledge base. A new algorithm for sequentially training the Markov chains is developed, to reduce the computation cost during model adaptation. As new motion patterns are observed, they are incrementally grouped together using hierarchical agglomerative clustering based on their relative distance in the model 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.
Bennewitz, M. , Burgard, W. , Cielniak, G. and Thrun, S. (2005). Learning motion patterns of people for compliant robot motion . International Journal of Robotics Research, 24(1): 31-48.
2.
Bentivegna, D.C. , Atkeson, C.G. and Cheng, G. (2006). Learning similar tasks from observation and practice . Proceedings of the International Conference on Intelligent Robots and Systems, pp. 2677-2683.
3.
Bernardin, K. , Ogawara, K. , Ikeuchi, K. and Dillmann, R. (2005). A sensor fusion approach for recognizing continuous human grasping sequences using hidden Markov models . IEEE Transactions on Robotics, 21(1): 47-57.
4.
Betkowska, A. , Shinoda, K. and Furui, S. (2006). FHMM for robust speech recognition in home environment . Proceedings of th Symposium on Large Scale Knowledge Resources, pp. 129-132.
5.
Billard, A. , Calinon, S. and Guenter, F. (2006). Discriminative and adaptive imitation in uni-manual and bi-manual tasks . Robotics and Autonomous Systems, 54: 370-384.
6.
Breazeal, C. and Scassellati, B. (2002). Robots that imitate humans . Trends in Cognitive Sciences, 6(11): 481-487.
7.
Calinon, S. and Billard, A. (2007a). Active teaching in robot programming by demonstration . Proceedings of the IEEE International Conference on Robot and Human Interactive Communication, pp. 702-707.
8.
Calinon, S. and Billard, A. (2007b). Incremental learning of gestures by imitation in a humanoid robot . Proceedings of the ACM/IEEE International Conference on Human-Robot Interaction, pp. 255-262.
9.
Calinon, S. , Guenter, F. and Billard, A. (2007). On learning, representing and generalizing a task in a humanoid robot . IEEE Transactions on Systems, Man and Cybernetics, Part B, 37(2): 286-298.
10.
Dillmann, R. (2004). Teaching and learning of robot tasks via observation of human performance . Journal of Robotics and Autonomous Systems , 47: 109-116.
11.
Dillmann, R. , Rogalla, O. , Ehrenmann, M. , Zollner, R. and Bordegoni, M. (1999). Learning robot behaviour and skills based on human demonstration and advice: the machine learning paradigm . Proceedings of the International Symposium on Robotics Research, pp. 229-238.
12.
Dixon, K.R. , Dolan, J.M. and Khosla, P.K. (2004). Predictive robot programming: theoretical and experimental analysis . International Journal of Robotics Research , 23(9): 955- 973.
13.
Ekvall, S. , Aarno, D. and Kragic, D. (2006). Online task recognition and real-time adaptive assistance for computer-aided machine control . IEEE Transactions on Robotics, 22(5): 1029-1033.
14.
Ezaki, H. (2000). Understanding actions of others through self-action components. Master's Thesis, University of Tokyo (in Japanese).
15.
Ghahramani, Z. and Jordan, M.I. (1997). Factorial hidden Markov models . Machine Learning, 29: 245-273.
16.
Ho, M.A.T. , Yamada, Y. and Umetani, Y. (2005). An adaptive visual attentive tracker for human communicational behaviors using HMM-based TD learning with new state distinction cpapbility . IEEE Transactions on Robotics, 21(3): 497-504.
17.
Iba, S. , Paredis, C.J.J. and Khosla, P.K. (2005). Interactive multi-modal robot programming . International Journal of Robotics Research, 24(1): 83-104.
18.
Inamura, T. , Toshima, I. , Tanie, H. and Nakamura, Y. (2004). Embodied symbol emergence based on mimesis theory . International Journal of Robotics Research, 23(4-5): 363 - 377 .
19.
Jacobs, R.A. , Jiang, W. and Tanner, M.A. (2002). Factorial hidden Markov models and the generalized backfitting algorithm . Neural Computation, 14: 2415-2437.
20.
Jain, A.K. , Murty, M.N. and Flynn, P.J. (1999). Data clustering: a review . ACM Computing Surveys, 31(3): 264-323.
21.
Kadone, H. and Nakamura, Y. (2005). Symbolic memory for humanoid robots using hierarchical bifurcations of attractors in nonmonotonic neural networks . Proceedings of the International Conference on Intelligent Robots and Systems, pp. 2900-2905.
22.
Kadone, H. and Nakamura, Y. (2006). Segmentation, memorization, recognition and abstraction of humanoid motions based on correlations and associative memory . Proceedings of the IEEE-RAS International Conference on Humanoid Robots, pp. 1-6.
23.
Kragic, D. , Marayong, P. , Li, M. , Okamura, A.M. and Hager, G.D. (2005). Human-machine collaborative systems for microsurgical applications . International Journal of Robotics Research, 24(9): 731-742.
24.
Kulić, D. , Takano, W. and Nakamura, Y. (2007a). Incremental on-line hierarchical clustering of whole body motion patterns . Proceedings of the IEEE International Symposium on Robot and Human Interactive Communication , pp. 1016- 1021.
25.
Kulić, D. , Takano, W. and Nakamura, Y. (2007b). Representability of human motions by factorial hidden Markov models . Proceedings of the IEEE International Conference on Intelligent Robots and Systems, pp. 2388-2393.
26.
Kuniyoshi, Y. , Inaba, M. and Inoue, H. (1989). Teaching by showing: generating robot programs by visual observation of human performance . Proceedings of the International Symposium on Industrial Robots, pp. 119-126.
27.
Kuniyoshi, Y. and Inoue, H. (1994). Learning by watching: extracting reusable task knowledge from visual observation of human performance . IEEE Transactions on Robotics and Automation, 10(6): 799-822.
28.
Lee, D. , Kulić, D. , and Nakamura, Y. (2008). Missing motion data recovery using factorial hidden Markov models . Proceedings of the IEEE International Conference on Robotics and Automation, pp. 1722-1728, 2008.
29.
Lee, D. and Nakamura, Y. (2005). Mimesis from partial observations . Proceedings of the International Conference on Intelligent Robots and Systems, pp. 1911-1916.
30.
Liu, S. and Asada, H. (1992). Transferring manipulative skills to robots: representation and acquisition of tool manipulative skills using a process dynamics model . Journal of Dynamic Systems, Measurement and Control, 114(2): 220- 228.
31.
Murphy, K.P. (1999). Bayesian map learning in dynamic environments. Advances in Neural Information Processing Systems. Cambridge, MA, MIT Press.
32.
Nakanishi, J. , Morimoto, J. , Endo, G. , Cheng, G. , Schaal, S. and Kawato, M. (2004). Learning from demonstration ADN adaptation of biped locomotion . Robotics and Autonomous Systems, 47: 79-91.
33.
Nicolescu, M.N. and Matarić, M.J. (2005). Task learning through imitation and human-robot interaction. Imitation and social Learning in robots, Humans and Animals: Behavioral, Social and Communicative Dimensions, Dautenhahn, K. and Nehaniv, C. (eds). Cambridge, Cambridge University Press.
34.
Ogata, T. , Sugano, S. and Tani, J. (2005). Open-end human- robot interaction from the dynamical systems perspective: mutual adaptation and incremental learning . Advanced Robotics, 19: 651-670.
35.
Ohkawa, K. and Nakamura, Y. (2005). Motion recognition by hierarchization and combination of statistical motion models . Proceedings of the JSME Conference on Robotics and Mechatronics, 1P1-S-009.
36.
Rabiner, L.R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition . Proceedings of the IEEE , 77(2): 257-286.
37.
Rizzolatti, G. and Craighero, L. (2004). The mirror-neuron system . Annual Reviews of Neuroscience, 27: 169-192.
38.
Rizzolatti, G. , Fogassi, L. and Gallese, V. (2001). Neurophysical mechanisms underlying the understanding and imitation of action . Nature Reviews: Neuroscience, 2: 661- 670.
39.
Schaal, S. , Ijspeert, A. and Billard, A. (2003). Computational approaches to motor learning by imitation . Philosophical Transactions of the Royal Society of London B: Biological Sciences, 358: 537 - 547.
40.
Startner, T. and Pentland, A. (1995). Visual recognition of american sign language using hidden Markov models . Proceedings of the International Conference on Automatic Face and Gesture Recognition, pp. 189-194.
41.
Takano, W. (2006). Stochastic segmentation, proto-symbol coding and clustering of motion patterns and their application to signifiant communication between man and humanoid robot. Ph.D. Thesis, University of Tokyo .
42.
Takano, W. and Nakamura, Y. (2006). Humanoid robot's autonomous acquisition of proto-symbols through motion segmentation . Proceedings of the IEEE-RAS International Conference on Humanoid Robots, pp. 425-431.
43.
Takano, W. , Yamane, K. , Sugihara, T. , Yamamoto, K. and Nakamura, Y. (2006). Primitive communication based on motion recognition and generation with hierarchical mimesis model . Proceedings of the IEEE International Conference on Robotics and Automation , pp. 3602-3608.
44.
Taylor, G.W. , Hinton, G.E. and Roweis, S. (2006). Modeling human motion using binary latent variables . Proceedings of the Conference on Neural Information Processing Systems, pp. 1345-1352.
45.
Yang, J. , Xu, Y. and Chen, C.S. (1997). Human action learning via hidden Markov model. IEEE Transactions on Systems , Man and Cybernetics-Part A: Systems and Humans, 27(1): 34-44.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
