World Scientific
Skip main navigation

Cookies Notification

We use cookies on this site to enhance your user experience. By continuing to browse the site, you consent to the use of our cookies. Learn More
×
Our website is made possible by displaying certain online content using javascript.
In order to view the full content, please disable your ad blocker or whitelist our website www.worldscientific.com.

System Upgrade on Mon, Jun 21st, 2021 at 1am (EDT)

During this period, the E-commerce and registration of new users may not be available for up to 6 hours.
For online purchase, please visit us again. Contact us at [email protected] for any enquiries.

ON THE REPRESENTATION, LEARNING AND TRANSFER OF SPATIO-TEMPORAL MOVEMENT CHARACTERISTICS

    In this paper we present a learning-based approach for the modeling of complex movement sequences. Based on the method of Spatio-Temporal Morphable Models (STMMs) we derive a hierarchical algorithm that, in a first step, identifies automatically movement elements in movement sequences based on a coarse spatio-temporal description, and in a second step models these movement primitives by approximation through linear combinations of learned example movement trajectories. We describe the different steps of the algorithm and show how it can be applied for modeling and synthesis of complex sequences of human movements that contain movement elements with a variable style. The proposed method is demonstrated on different applications of movement representation relevant for imitation learning of movement styles in humanoid robotics.

    References

    • M. A. Giese and T. Poggio, Synthesis and recognition of biological motion pattern based on linear superposition of prototypical motion sequences, Proc. IEEE, MVIEW 99 Symp. (1999) pp. 73–80. Google Scholar
    • M. A. Giese and T. Poggio, Int. J. Comput. Vision 38(1), 59 (2000), DOI: 10.1023/A:1008118801668. Crossref, ISIGoogle Scholar
    • W. Ilg and M. A. Giese, Modeling of movement sequences based on hierarchical spatial- temporal correspondence of movement primitives, Workshop on Biologically Motivated Computer Vision (2002) pp. 528–537. Google Scholar
    • M. Unuma, K. Anjyo and R. Takeuchi, Fourier principles for emotion-based human figure animation, SIGGRAPH (1995) pp. 91–96. Google Scholar
    • A. Bruderlin and L. Williams, Motion signal processing, SIGGRAPH (1995) pp. 97–104. Google Scholar
    • A. Witkin and Z. Popovic, Motion warping, SIGGRAPH (1995) pp. 105–108. Google Scholar
    • M. Gleicher, Retargeting motion to new characters, SIGGRAPH (1998) pp. 33–42. Google Scholar
    • C. Rose, M. F. Cohen and B. Bodenheimer, IEEE Comput. Graphics Appl. 18(5), 32 (1998), DOI: 10.1109/38.708559. CrossrefGoogle Scholar
    • F. A. Mussa-Ivaldi, S. Gizter and E. Bizzi, Proc. Natl. Acad. Sci. 91, 7534 (1994), DOI: 10.1073/pnas.91.16.7534. Crossref, ISIGoogle Scholar
    • S.   Schaal , Dynamic movement primitives — A framework for motor control in humans and humanoid robots , Proc. 2nd Int. Symp. Adaptive Motion of Animals and Machines ( 2003 ) . Google Scholar
    • T. Flash and N. Hogan, J. Neurosci. 5, 1688 (1985). Crossref, ISIGoogle Scholar
    • T. D. Sanger, J. Neurosci. 20(3), 1066 (2000). Crossref, ISIGoogle Scholar
    • B. Rohreret al., J. Neurosci. 18, 8297 (2002). Google Scholar
    • A. Billard and M. Mataric, Robotics and Autonomous Systems 41(9), 1 (2001). ISIGoogle Scholar
    • M. J.   Mataric , Imitation in Animals and Artifacts , eds. K.   Dautenhahn and C.   Nehaniv ( MIT Press , 2002 ) . Google Scholar
    • S. Schaal, Trends Cogn. Sci. 3, 233 (1999), DOI: 10.1016/S1364-6613(99)01327-3. Crossref, ISIGoogle Scholar
    • A. Galata, N. Johnson and D. Hogg, J. Comput. Vision and Image Understanding 81, 398 (2001), DOI: 10.1006/cviu.2000.0894. Crossref, ISIGoogle Scholar
    • T. Mori and K. Uehara, Extraction of primitive motion and discovery of association rules from motion data, Proc. IEEE Int. Workshop Robot and Human Interactive Communication (2001) pp. 200–206. Google Scholar
    • A. Nakazawaet al., Imitating human dance motions through motion structure analysis, Proc. IEEE Int. Conf. Intelligent Robots and Systems (2002) pp. 2539–2544. Google Scholar
    • T. Caelli, A. McCabe and G. Binsted, On learning the shape of complex actions, Int. Workshop Visual Form (2001) pp. 24–39. Google Scholar
    • H. O.   Lim , A.   Ishi and A.   Takanishi , Emotion expression of a biped personal robot , Proc. IEEE Int. Conf. Intelligent Robots and Systems ( 2000 ) . Google Scholar
    • W. Ilg, J. Mezger and M. A. Giese, Estimation of skill level in sports based on hierarchical spatio-temporal correspondences, Proc. 25th DAGM Pattern Recognition Symposium pp. 523–531. Google Scholar
    • O. C. Jenkins and M. J. Mataric, Deriving action and behavor primitives from human motion data, IEEE/RSJ Int. Conf. Intelligent Robots and Systems (2002) pp. 2551–2556. Google Scholar
    • W. Ilget al., Hierarchical spatio-temporal morphable models for representation of complex movements for imitation learning, Proc. 11th IEEE Int. Conf. Advanced Robotics (2003) pp. 553–558. Google Scholar
    • J.   Hodgins et al. , Adapting human motion for the control of a humanoid robot , Proc. IEEE Int. Conf. Robotics and Automation ( 2002 ) . Google Scholar
    • A.   Ude , C.   Atkeson and M.   Riley , Automatic generation of kinematic models for the conversion of human motion capture data into humanoid robot motion , 1st IEEE-RAS Int. Conf. Humanoid Robots ( 2000 ) . Google Scholar
    • G.   Schreiber , C.   Ott and G.   Hirzinger , Interactive redundant robotics: Control of the inverted pendulum with nullspace motion , Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems ( 2001 ) . Google Scholar
    • G. H. Bakir, W. Ilg, M. O. Franz and M. A. Giese, Constraints measures and reproduction of style in robot imitation learning, Beitraege zur 6. Tuebinger Wahrnehmungskonferenz, 2003 . Google Scholar
    • A.   Safonova , N. S.   Pollard and J. K.   Hodgins , Optimizing human motion for the control of a humanoid robot , Proc. 2nd Int. Symp. Adaptive Motion of Animals and Machines ( 2003 ) . Google Scholar
    • M.   Brand , Style machines , SIGGRAPH ( 2000 ) . Google Scholar
    • A. D. Wilson and A. F. Bobick, IEEE Trans. Pattern Anal. Mach. Intell. 21(9), 884 (1999), DOI: 10.1109/34.790429. Crossref, ISIGoogle Scholar
    • Y. Yacoob and M. J. Black, J. Comput. Vision and Image Understanding 73(2), 398 (1999). Google Scholar
    • A. F. Bobick and J. Davis, An appearance-based representation of action, Proc. IEEE Conf. Pattern Recognition (1996) pp. 307–312. Google Scholar
    • C.   Bregler et al. , Turning to the masters: Motion capturing cartoons , SIGGRAPH ( 2002 ) . Google Scholar
    • A. Fod, M. J. Mataric and O. C. Jenkins, Autonomous Robots 12(1), 39 (2002), DOI: 10.1023/A:1013254724861. Crossref, ISIGoogle Scholar
    • J.   Lee and S. Y.   Shin , A hierarchical approach to interactive motion editing for human like figures , SIGGRAPH ( 1999 ) . Google Scholar
    • A.   Ude , C.   Atkenson and M.   Riley , Planning of joint trajectories for humanoid robots using B-spline wavelets , IEEE Int. Conf. Robotics and Automation ( 2000 ) . Google Scholar
    • H. Miyamoto and M. Kawato, Neural Networks 11, 1331 (1998), DOI: 10.1016/S0893-6080(98)00062-8. Crossref, ISIGoogle Scholar
    • W.   Ilg et al. , Quantitative movement analysis based on hierarchical spatial temporal correspondence of movement primitives , 11th Annual Meeting European Society for Movement Analysis in Adults and Children ( 2002 ) . Google Scholar
    Remember to check out the Most Cited Articles!

    Check out these Notable Titles in Robotics