Mixture of Attractors: A Novel Movement Primitive Representation for Learning Motor Skills From Demonstrations

In this letter, we introduce Mixture of Attractors, a novel movement primitive representation that allows for learning complex object-relative movements. The movement primitive representation inherently supports multiple coordinate frames, enabling the system to generalize a skill to unseen object positions and orientations. In contrast to most other approaches, a skill is learned by solving a convex optimization problem. Therefore, the quality of the skill does not depend on a good initial estimate of parameters. The resulting movements are automatically smooth and can be of arbitrary shape. The approach is evaluated and compared to other movement primitive representations on data from the Omniglot handwriting dataset and on real demonstrations of a handwriting task. The evaluations show that the presented approach outperforms other state-of-the-art concepts in terms of generalization capabilities and accuracy.

[1]  Joshua B. Tenenbaum,et al.  Human-level concept learning through probabilistic program induction , 2015, Science.

[2]  Aude Billard,et al.  Active Teaching in Robot Programming by Demonstration , 2007, RO-MAN 2007 - The 16th IEEE International Symposium on Robot and Human Interactive Communication.

[3]  Jan Peters,et al.  Probabilistic decomposition of sequential force interaction tasks into Movement Primitives , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[4]  Jan Peters,et al.  Probabilistic Movement Primitives , 2013, NIPS.

[5]  Darwin G. Caldwell,et al.  Variable duration movement encoding with minimal intervention control , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[6]  Darwin G. Caldwell,et al.  Learning optimal controllers in human-robot cooperative transportation tasks with position and force constraints , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[7]  Sang Hyoung Lee,et al.  Autonomous framework for segmenting robot trajectories of manipulation task , 2015, Auton. Robots.

[8]  Scott Niekum,et al.  Learning grounded finite-state representations from unstructured demonstrations , 2015, Int. J. Robotics Res..

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

[10]  Sylvain Calinon,et al.  Supervisory teleoperation with online learning and optimal control , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[11]  Aude Billard,et al.  Task Parameterization Using Continuous Constraints Extracted From Human Demonstrations , 2015, IEEE Transactions on Robotics.

[12]  A. Billard,et al.  Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models , 2011, IEEE Transactions on Robotics.

[13]  Joanna Bryson,et al.  A modular approach to learning manipulation strategies from human demonstration , 2016, Auton. Robots.

[14]  Andrea Lockerd Thomaz,et al.  Simultaneously learning actions and goals from demonstration , 2016, Auton. Robots.

[15]  Stefan Schaal,et al.  Data-Driven Online Decision Making for Autonomous Manipulation , 2015, Robotics: Science and Systems.

[16]  Jun Nakanishi,et al.  Movement imitation with nonlinear dynamical systems in humanoid robots , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[17]  Jochen J. Steil,et al.  Learning movement primitives for force interaction tasks , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[18]  Justus H. Piater,et al.  Robotic playing for hierarchical complex skill learning , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[19]  Joelle Pineau,et al.  Learning from Limited Demonstrations , 2013, NIPS.

[20]  Oliver Kroemer,et al.  Interaction primitives for human-robot cooperation tasks , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[21]  T. Flash,et al.  When practice leads to co-articulation: the evolution of geometrically defined movement primitives , 2004, Experimental Brain Research.

[22]  Nicolas Perrin,et al.  Fast diffeomorphic matching to learn globally asymptotically stable nonlinear dynamical systems , 2016, Syst. Control. Lett..

[23]  Nikolaos G. Tsagarakis,et al.  Statistical dynamical systems for skills acquisition in humanoids , 2012, 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012).