In this paper we describe an approach for on-line, incremental learning of full body motion primitives from observation of human motion. The continuous observation sequence is first partitioned into motion segments, using stochastic segmentation. Next, motion segments are incrementally clustered and organized into a hierarchical tree structure representing the known motion primitives. Motion primitives are encoded using hidden Markov models, so that the same model can be used for both motion recognition and motion generation. At the same time, the temporal relationship between motion primitives is learned via the construction of a motion primitive graph. The motion primitive graph can then be used to construct motions, consisting of sequences of motion primitives. The approach is implemented and tested during on-line observation and on the IRT humanoid robot.
AndryPGaussierPNadelJHirsbrunnerB (2004) Learning invariant sensorimotor behaviors: a developmental approrach to imitation mechanisms. Adaptive Behavior12: 117–140.
2.
AsfourTGyarfasFAzadPDillmannR (2006) Imitation learning of dual-arm manipulation tasks in humanoid robots. In Proceedings of the IEEE International Conference on Humanoid Robots, pp. 40–47.
3.
BillardACalinonSGuenterF (2006) Discriminative and adaptive imitation in uni-manual and bi-manual tasks. Robotics and Autonomous Systems54: 370–384.
BreazealCBuchsbaumDGrayJGatenbyDBlumbergB (2005) Learning from and about others: towards using imitation to bootstrap the social understanding of others by robots. Articifical Life11: 1–32.
6.
BreazealCScassellatiB (2002) Robots that imitate humans. Trends in Cognitive Sciences6: 481–487.
7.
CalinonSBillardA (2007a) Active teaching in robot programming by demonstration. In Proceedings of the IEEE International Conference on Robot and Human Interactive Communication, pp. 702–707.
8.
CalinonSBillardA (2007b) Incremental learning of gestures by imitation in a humanoid robot. In Proceedings of the ACM/IEEE International Conference on Human-Robot Interaction, pp. 255–262.
9.
CalinonSGuenterFBillardA (2007) On learning, representing and generalizing a task in a humanoid robot. IEEE Transactions on Systems, Man and Cybernetics, Part B, 37: 286–298.
10.
DillmannRRogallaOEhrenmannMZollnerRBordegoniM (1999) Learning robot behaviour and skills based on human demonstration and advice: The machine learning paradigm. In Proceedings of the International Symposium on Robotics Research, pp. 229–238.
11.
DomineyPFMettaGNoriFNataleL (2008) Anticipation and initiative in human-humanoid interaction. In Proceedings of the IEEE International Conference on Humanoid Robots, pp. 693–699.
12.
ErlhagenWMukovskiyABichoEPaninGKissCKnollA. (2006) Goal-directed imitation for robots: A bio-inspired approach to action understanding and skill learning. Robotics and Autonomous Systems54: 353–360.
13.
EzakiH (2000) Understanding Actions of Others Through Self-action Components. Master’s thesis, University of Tokyo, 2000 (in Japanese).
14.
FodAMatarićMJJenkinsOC (2002) Automated derivation of primitives for movement classification. Autonomous Robots12: 39–54.
15.
IjspeertAJNakanishiJSchaalS (2002) Movement imitation with nonlinear dynamical systems in humanoid robots. In Proceedings of the IEEE International Conference on Robotics and Automation, pp. 1398–1403.
16.
IlgWBakirGHMezgerJGieseMA (2004) On the representation, learning and transfer of spatio-temporal movement characteristics. International Journal of Humanoid Robotics1: 613–636.
17.
InamuraTToshimaITanieHNakamuraY (2004) Embodied symbol emergence based on mimesis theory. The International Journal of Robotics Research, 23: 363–377.
18.
ItoMTaniJ (2004) On-line imitative interaction with a humanoid robot using a dynamic neural network model of a mirror system. Adaptive Behavior12: 93–115.
19.
JainAKMurtyMNFlynnPJ (1999) Data clustering: A review. ACM Computing Surveys31: 264–323.
20.
JanusB (2006) On-line motion segmentation algorithm for mimesis model. Master’s thesis, University of Tokyo.
21.
JanusBNakamuraY (2005) Unsupervised probabilistic segmentation of motion data for mimesis modeling. In Proceedings of the IEEE International Conference on Advanced Robotics, pp. 411–417.
22.
JenkinsOCMatarićM (2004a) Performance-derived behavior vocabularies: Data-driven acquisition of skills from motion. International Journal of Humanoid Robotics1: 237–288.
23.
JenkinsOCMatarićM (2004b) A spatio-temporal extension to isomap nonlinear dimension reduction. In Proceedings of the International Conference on Machine Learning, pp. 441–448.
24.
KadoneHNakamuraY (2005) Symbolic memory for humanoid robots using hierarchical bifurcations of attractors in nonmonotonic neural networks. In Proceedings of the International Conference on Intelligent Robots and Systems, pp. 2900–2905.
25.
KadoneHNakamuraY (2006) Segmentation, memorization, recognition and abstraction of humanoid motions based on correlations and associative memory. In Proceedings of the IEEE International Conference on Humanoid Robots, pp. 1–6.
26.
KajitaS (2005) Humanoid Robot. Ohmsha, 2005 (in Japanese).
27.
KohlmorgenLemmS (2001) A dynamic hmm for on-line segmentation of sequential data. In NIPS 2001: Advances in Neural Information Processing Systems, pp. 793–800.
28.
KovarLGleicherMPighinF (2002) Motion graphs. In Proceedings of the ACM SIGGRAPH, pp. 473–482.
29.
KruegerVKragicDUdeAGeibC (2007) The meaning of action: A review on action recognition and mapping. Advanced Robotics21: 1473–1501.
30.
KulićDImagawaHNakamuraY (2009) Online acquisition and visualization of motion primitives for humanoid robots. In Proceedings of the IEEE International Symposium on Robot and Human Interactive Communication, pp. 1210–1215.
31.
KulićDNakamuraY (2008) Scaffolding on-line segmentation of full body human motion patterns. In Proceedings of the IEEE/RJS International Conference on Intelligent Robots and Systems, pp. 2860–2866.
32.
KulićDNakamuraYOn-line segmentation of whole body human motion data for large kinematic models. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4300–4305.
33.
KulićDTakanoWNakamuraY (2007a) Incremental on-line hierarchical clustering of whole body motion patterns. In Proceedings of the IEEE International Symposium on Robot and Human Interactive Communication, pp. 1016–1021.
34.
KulićDTakanoWNakamuraY (2007b) Representability of human motions by factorial hidden markov models. In Proceedings of the IEEE International Conference on Intelligent Robots and Systems, pp. 2388–2393.
35.
KulićDTakanoWNakamuraY (2007c) Towards lifelong learning and organization of whole body motion patterns. In Proceedings of the International Symposium of Robotics Research, pp. 113–124.
36.
KulićDTakanoWNakamuraY (2008a) Combining automated on-line segmentation and incremental clustering for whole body motions. In Proceedings of the IEEE International Conference on Robotics and Automation, pp. 2591–2598.
37.
KulićDTakanoWNakamuraY (2008b) Incremental learning, clustering and hierarchy formation of whole body motion patterns using adaptive hidden Markov chains. International Journal of Robotics Research27: 761–784.
38.
KulićDTakanoWNakamuraY (2009) On-line segmentation and clustering from continuous observation of whole body motions. IEEE Transactions on Robotics25: 1158–1166.
39.
KuniyoshiYInabaMInoueH (1989) Teaching by showing: Generating robot programs by visual observation of human performance. In Proceedings of the International Symposium on Industrial Robots, pp. 119–126.
40.
KuniyoshiYInoueH (1994) Learning by watching: Extracting reusable task knowledge from visual observation of human performance. IEEE Transactions on Robotics and Automation10: 799–822.
41.
KuriharaKHoshinoSYamaneKNakamuraY (2002) Optical motion capture system with pan–tilt camera tracking and realtime data processing. In Proceedings of the IEEE International Conference on Robotics and Automation, vol. 2, pp. 1241–1248.
42.
LeeDNakamuraY (2006) Stochastic model of imitating a new observed motion based on the acquired motion primitives. In Proceedings of the IEEE International Conference on Intelligent Robots and Systems, pp. 4994–5000.
43.
LiuSAsadaH (1992) Transferring manipulative skills to robots: representation and acquisition of tool manipulative skills using a process dynamics model. Journal of Dynamic Systems, Measurement and Control114: 220–228.
44.
OttChLeeDNakamuraY (2008) Motion capture based human motion recognition and imitation by direct marker control. In Proceedings of the IEEE International Conference on Humanoid Robots, pp. 399–405.
45.
NakanishiJMorimotoJEndoGChengGSchaalSKawatoM (2004) Learning from demonstration adn adaptation of biped locomotion. Robotics and Autonomous Systems47: 79–91.
46.
NicolescuMNMatarićMJ (2001) Learning and interacting in human–robot domains. IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans31: 419–430.
47.
NicolescuMNMatarićMJ (2003) Natural methods for robot task learning: instructive demonstrations, generalization and practice. In Proceedings of the International Joint Conference on Autonomous Agents and Multi-Agent Systems, pp. 241–248.
48.
NicolescuMNMatarićMJ (2005) Task learning through imitation and human–robot interaction. In DautenhahnKNehanivC (eds), Imitation and Social Learning in Robots, Humans and Animals: Behavioral, Social and Communicative Dimensions. Cambridge: Cambridge University Press.
49.
OgataTSuganoSTaniJ (2005) Open-end human–robot interaction from the dynamical systems perspective: mutual adaptation and incremental learning. Advanced Robotics19: 651–670.
50.
OkadaMTataniKNakamuraY (2002) Polynomial design of the nonlinear dynamics for the brain-like information processing of whole body motion. In Proceedings of the IEEE International Conference on Robotics and Automation, pp. 1410–1415.
51.
RabinerLR (1989) A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE77: 257–286.
52.
SchaalS (2006) Dynamic movement primitives - a framework for motor control in humans and humanoid robotics. In KimuraHTsuchiyaKIshiguroAWitteH (eds), Adaptive Motion of Animals and Machines. Tokyo: Springer, pp. 261–280.
53.
SchaalSIjspeertABillardA (2003) Computational approaches to motor learning by imitation. Philosophical Transactions of the Royal Society of London B: Biological Sciences358: 537–547.
54.
SidenbladhHBlackMJSigalL (2002) Implicit probabilistic models of human motion for synthesis and tracking. In Proceedings of the European Conference on Computer Vision, pp. 784–800.
55.
StartnerTPentlandA (1995) Visual recognition of american sign language using hidden markov models. In Proceedings of the International Conference on Automatic Face and Gesture Recognition, pp. 189–194.
56.
SuttonRSBartoAG (1998) Reinforcement Learning: An Introduction. Cambridge, MA: MIT Press.
57.
TakanoW (2006) Stochastic segmentation, proto-symbol coding and clustering of motion patterns and their application to signifiant communication between man and humanoid robot. PhD thesis, University of Tokyo.
58.
TakanoWYamaneKNakamuraY (2005) Primitive communication of humanoid robot with human via hierarchical mimesis model on the proto symbol space. In Proceedings of the IEEE/RAS International Conference on Humanoid Robots, pp. 167–174.
59.
TakanoWYamaneKSugiharaTYamamotoKNakamuraY (2006) Primitive communication based on motion recognition and generation with hierarchical mimesis model. In Proceedings of the IEEE International Conference on Robotics and Automation, pp. 3602–3608.
60.
TaylorGWHintonGERoweisS (2006) Modeling human motion using binary latent variables. In Proceedings of the Conference on Neural Information Processing Systems, pp. 1345–1352.
61.
YamaguchiYYamaneKNakamuraY (2008) A large-scale human motion database and its application to character animation. In Proceedings of the JSME Conference on Robotics and Mechatronics, pp. 1P1–J18 (in Japanese).
62.
YamaneKNakamuraY (2003) Natural motion animation through constraining and deconstraining at will. IEEE Transactions on Visualization and Computer Graphics9: 352–360.
63.
YamaneKYamaguchiYNakamuraY (2009) Human motion database with a binary tree and node transition graphs. In Proceedings of Robotics: Science and Systems 2009.
