Unsupervised learning of action primitives

Action representation is a key issue in imitation learning for humanoids. With the recent finding of mirror neurons there has been a growing interest in expressing actions as a combination meaningful subparts called primitives. Primitives could be thought of as an alphabet for the human actions. In this paper we observe that human actions and objects can be seen as being intertwined: we can interpret actions from the way the body parts are moving, but as well from how their effect on the involved object. While human movements can look vastly different even under minor changes in location, orientation and scale, the use of the object can provide a strong invariant for the detection of motion primitives. In this paper we propose an unsupervised learning approach for action primitives that makes use of the human movements as well as the object state changes. We group actions according to the changes they make to the object state space. Movements that produce the same state change in the object state space are classified to be instances of the same action primitive. This allows us to define action primitives as sets of movements where the movements of each primitive are connected through the object state change they induce.

[1]  Daniel S. Hirschberg,et al.  Algorithms for the Longest Common Subsequence Problem , 1977, JACM.

[2]  Danica Kragic,et al.  Primitive-Based Action Representation and Recognition , 2011, Adv. Robotics.

[3]  Dana Kulic,et al.  Scaffolding on-line segmentation of full body human motion patterns , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  G. Rizzolatti,et al.  Action recognition in the premotor cortex. , 1996, Brain : a journal of neurology.

[5]  Byron Jones,et al.  Kullback–Leibler divergence for evaluating bioequivalence , 2003, Statistics in medicine.

[6]  Christopher W. Geib,et al.  The meaning of action: a review on action recognition and mapping , 2007, Adv. Robotics.

[7]  G. Rizzolatti,et al.  Parietal cortex: from sight to action , 1997, Current Opinion in Neurobiology.

[8]  Jochen J. Steil,et al.  Automatic selection of task spaces for imitation learning , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Maja J. Mataric,et al.  Automated Derivation of Primitives for Movement Classification , 2000, Auton. Robots.

[10]  Yiannis Aloimonos,et al.  A Language for Human Action , 2007, Computer.

[11]  Danica Kragic,et al.  Action recognition and understanding through motor primitives , 2007, Adv. Robotics.

[12]  Jeffrey K. Uhlmann,et al.  General Decentralized Data Fusion With Covariance Intersection (CI) , 2001 .

[13]  G. Orban,et al.  Observing Others: Multiple Action Representation in the Frontal Lobe , 2005, Science.

[14]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[15]  G. Rizzolatti,et al.  Neurophysiological mechanisms underlying the understanding and imitation of action , 2001, Nature Reviews Neuroscience.

[16]  Yiannis Aloimonos,et al.  A Sensory-Motor Language for Human Activity Understanding , 2006, 2006 6th IEEE-RAS International Conference on Humanoid Robots.

[17]  Ignazio Infantino,et al.  Learning High-Level Manipulative Tasks through Imitation , 2006, ROMAN 2006 - The 15th IEEE International Symposium on Robot and Human Interactive Communication.

[18]  Christopher G. Atkeson,et al.  Learning from observation using primitives , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[19]  Nathan Delson,et al.  Robot programming by human demonstration: adaptation and inconsistency in constrained motion , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[20]  Wolfram Burgard,et al.  Imitation learning with generalized task descriptions , 2009, 2009 IEEE International Conference on Robotics and Automation.

[21]  D. Bub,et al.  Gestural knowledge evoked by objects as part of conceptual representations , 2006 .

[22]  Betty J. Mohler,et al.  Learning perceptual coupling for motor primitives , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[23]  C. Breazeal,et al.  Robots that imitate humans , 2002, Trends in Cognitive Sciences.

[24]  Gordon Cheng,et al.  Discovering optimal imitation strategies , 2004, Robotics Auton. Syst..

[25]  Jun Nakanishi,et al.  Trajectory formation for imitation with nonlinear dynamical systems , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).