Incremental learning of full body motion primitives and their sequencing through human motion observation

International Journal of Robotics Research - Tập 31 Số 3 - Trang 330-345 - 2012
Dana Kulić1, Christian Ott2, Dongheui Lee3, Junichi Ishikawa4, Yoshihiko Nakamura4
1Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada
2[Institute of Robotics and Mechatronics, DLR, German Aerospace Center, Wessling, Germany]
3Department of Electrical Engineering and Information Technology, Technical University of Munich, Munich, Germany
4[Department of Mechano-Informatics, University of Tokyo Bunkyo-ku, Tokyo, Japan]

Tóm tắt

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.

Từ khóa


Tài liệu tham khảo

10.1177/105971230401200203

10.1109/ICHR.2006.321361

10.1016/j.robot.2006.01.007

10.1016/j.robot.2004.03.002

Breazeal C, 2005, Articifical Life, 11, 1, 10.1162/1064546053278928

10.1016/S1364-6613(02)02016-8

10.1109/ROMAN.2007.4415177

10.1145/1228716.1228751

10.1109/TSMCB.2006.886952

Dillmann R, 1999, Proceedings of the International Symposium on Robotics Research, 229

10.1109/ICHR.2008.4755974

10.1016/j.robot.2006.01.004

Ezaki H (2000) Understanding Actions of Others Through Self-action Components. Master’s thesis, University of Tokyo, 2000 (in Japanese).

10.1023/A:1013254724861

10.1109/ROBOT.2002.1014739

10.1142/S0219843604000320

10.1177/0278364904042199

10.1177/105971230401200202

10.1145/331499.331504

Janus B (2006) On-line motion segmentation algorithm for mimesis model. Master’s thesis, University of Tokyo.

10.1109/ICAR.2005.1507443

10.1142/S0219843604000186

10.1145/1015330.1015357

10.1109/IROS.2005.1545416

10.1109/ICHR.2006.321355

Kajita S, 2005, Humanoid Robot

Kohlmorgen, 2001, NIPS 2001: Advances in Neural Information Processing Systems, 793

10.1145/566654.566605

10.1163/156855307782148578

10.1109/ROMAN.2009.5326307

10.1109/IROS.2008.4650619

Kulić D, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 4300

10.1109/ROMAN.2007.4415231

10.1109/IROS.2007.4399325

Kulić D, 2007, Proceedings of the International Symposium of Robotics Research, 113

10.1109/ROBOT.2008.4543603

10.1177/0278364908091153

10.1109/TRO.2009.2026508

Kuniyoshi Y, 1989, Proceedings of the International Symposium on Industrial Robots, 119

10.1109/70.338535

Kurihara K, 2002, Proceedings of the IEEE International Conference on Robotics and Automation, 2, 1241

10.1109/IROS.2006.282525

10.1115/1.2896518

10.1109/ICHR.2008.4755984

10.1016/j.robot.2004.03.003

10.1109/3468.952716

10.1145/860575.860614

Nicolescu MN, 2005, Imitation and Social Learning in Robots, Humans and Animals: Behavioral, Social and Communicative Dimensions

10.1163/1568553054255655

10.1109/ROBOT.2002.1014741

10.1109/5.18626

10.1007/4-431-31381-8_23

10.1098/rstb.2002.1258

10.1007/3-540-47969-4_52

Startner T, 1995, Proceedings of the International Conference on Automatic Face and Gesture Recognition, 189

Sutton RS, 1998, Reinforcement Learning: An Introduction

Takano W (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.

10.1109/ICHR.2005.1573563

10.1109/ROBOT.2006.1642252

Taylor GW, 2006, Proceedings of the Conference on Neural Information Processing Systems, 1345

Yamaguchi Y, 2008, Proceedings of the JSME Conference on Robotics and Mechatronics, 1P1

10.1109/TVCG.2003.1207443

10.15607/RSS.2009.V.004

Thông tin
Thông tin xuất bản

International Journal of Robotics Research

Tập 31 Số 3

330-345

Thông tin tác giả