Learning potential functions from human demonstrations with encapsulated dynamic and compliant behaviors
- 1.5k Downloads
We consider the problem of devising a unified control policy capable of regulating both the robot motion and its physical interaction with the environment. We formulate this control policy by a non-parametric potential function and a dissipative field, which both can be learned from human demonstrations. We show that the robot motion and its stiffness behaviors can be encapsulated by the potential function’s gradient and curvature, respectively. The dissipative field can also be used to model desired damping behavior throughout the motion, hence generating motions that follows the same velocity profile as the demonstrations. The proposed controller can be realized as a unification approach between “realtime motion generation” and “variable impedance control”, with the advantages that it has guaranteed stability as well as does not rely on following a reference trajectory. Our approach, called unified motion and variable impedance control (UMIC), is completely time-invariant and can be learned from a few demonstrations via solving two (convex) constrained quadratic optimization problems. We validate UMIC on a library of 30 human handwriting motions and on a set of experiments on 7-DoF KUKA light weight robot.
KeywordsPotential field Variable impedance control Compliant control Robot learning Physical interaction control Motion control Imitation learning Motion primitives
Mohammad Khansari is supported by the Swiss National Science Foundation.
Supplementary material 1 (mp4 22815 KB)
- Billard, A., Calinon, S., Dillmann, R., & Schaal, S. (2008). Robot programming by demonstration. In Handbook of Robotics (pp. 1371–1394). Berlin/Heidelberg: Springer.Google Scholar
- Brock, O., Kuffner, J., & Xiao, J. (2008). Handbook of robotics. In Motion for Manipulation Tasks (pp. 615–645). Berlin/Heidelberg: Springer. doi: 10.1007/978-3-540-30301-5_6.
- Calinon, S., Sardellitti, I., & Caldwell, D. G. (2010b). Learning-based control strategy for safe human-robot interaction exploiting task and robot redundancies. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 249–254).Google Scholar
- Calinon, S., Pistillo, A., & Caldwell, D. G. (2011). Encoding the time and space constraints of a task in explicit-duration hidden Markov model. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 3413–3418).Google Scholar
- Ferraguti, F., Secchi, C., & Fantuzzi, C. (2013). A tank-based approach to impedance control with variable stiffness. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) (pp. 4948–4953).Google Scholar
- Ganesh, G., Jarrasse, N., Haddadin, S., Albu-Schaeffer, A., & Burdet, E. (2012). A versatile biomimetic controller for contact tooling and haptic exploration. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) (pp. 3329–3334).Google Scholar
- Gomez, J. V., Alvarez, D., Garrido, S., & Moreno, L. (2012). Kinesthetic teaching via fast marching square. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 1305–1310).Google Scholar
- Gribovskaya, E. (2010). Seyed Mohammad Khansari-Zadeh, and Aude Billard. Learning Nonlinear Multivariate Dynamics of Motion in Robotic Manipulators. The International Journal of Robotics Research, 30, 1–37.Google Scholar
- Haddadin, S., Albu-Schaffer, A., De Luca, A., & Hirzinger, G. (2008). Collision detection and reaction: A contribution to safe physical human-robot interaction. In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2008. IROS 2008 (pp. 3356–3363).Google Scholar
- Hogan, N. (1985). Impedance control: An approach to manipulation. ASME Journal of Dynamic Systems, Measurement, and Control, 107.Google Scholar
- Hogan, N., & Buerger, S. P. (2005). Robotics and Automation Handbook, Impedance and Interaction Control. Boca Raton, FL: CRC.Google Scholar
- Howard, M., Klanke, S., Gienger, M., Goerick, C., & Vijayakumar, S. (2010). Methods for learning control policies from variable-constraint demonstrations. In From Motor Learning to Interaction Learning in Robots (vol. 264, pp. 253–291). Berlin/Heidelberg: Springer.Google Scholar
- Ijspeert, A. J., Nakanishi, J., & Schaal, S. (2002). Movement imitation with nonlinear dynamical systems in humanoid robots. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) (pp. 1398–1403).Google Scholar
- Khansari-Zadeh, S. M. (2011). Lasa human handwriting library. http://lasa.epfl.ch/khansari/LASA_Handwriting_Dataset.zip.
- Khansari-Zadeh, S. M. (2012). A Dynamical system-based approach to modeling stable robot control policies via imitation learning. Phd Thesis, cole Polytechnique Fdrale de Lausanne. http://infoscience.epfl.ch/record/182663.
- Khansari-Zadeh, S. M., Lemme, A., Meirovitch, Y., Schrauwen, B., Giese, M. A., Steil, J., Ijspeert, A. J., & Billard, A. (2013). Benchmarking of state-of-the-art algorithms in generating human-like robot reaching motions. In Workshop at the IEEE-RAS International Conference on Humanoid Robots (Humanoids). http://www.amarsi-project.eu/news/humanoids-2013-workshop.
- Khansari-Zadeh, S. M., Kronander, K., & Billard, A. (2014). Modeling robot discrete movements with state-varying stiffness and damping: A framework for integrated motion generation and impedance control. In Proceedings of Robotics: Science and Systems X (RSS 2014). Berkeley, California.Google Scholar
- Khatib, O., Sentis, L., & Park, J.-H. (2008). A unified framework for whole-body humanoid robot control with multiple constraints and contacts. In European Robotics Symposium 2008, volume 44 of Springer Tracts in Advanced Robotics (pp. 303–312). Berlin/Heidelberg: Springer.Google Scholar
- Kishi, Y., Yamada, Y., & Yokoyama, K. (2012). The role of joint stiffness enhancing collision reaction performance of collaborative robot manipulators. In 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 376–381).Google Scholar
- Koditschek, D. (1989). Robot Planning and Control Via Potential Functions (pp. 349–367).Google Scholar
- Kormushev, P., Calinon, S., & Caldwell, D. G. (2010). Robot motor skill coordination with EM-based reinforcement learning. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 3232–3237). Taipei, Taiwan.Google Scholar
- Lee, K., & Buss, M. (2008). Force tracking impedance control with variable target stiffness. In Proceedings of the International Federation of Automatic Control World Congress (pp. 6751–6756).Google Scholar
- Li, M., Yin, H., Tahara, K., & Billard, A. (2014). Learning object-level impedance control for robust grasping and dexterous manipulation. In 2014 IEEE International Conference on Robotics and Automation (ICRA) (pp. 6784–6791).Google Scholar
- Ott, C. (2008). Cartesian Impedance Control of Redundant and Flexible-Joint Robots. Springer Tracts in Advanced Robotics.Google Scholar
- Siciliano, B., Sciavicco, L., Villani, L., & Oriolo, G. (2009). Robotics: Modelling, Planning and Control. Advanced Textbooks in Control and Signal Processing. Springer.Google Scholar
- Villani, L., & De Schutter, J. (2008). Handbook of Robotics, Force Control (pp. 161–185). Berlin/Heidelberg: Springer.Google Scholar
- Wolf, S., & Hirzinger, G. (2008). A new variable stiffness design: Matching requirements of the next robot generation. In IEEE International Conference on Robotics and Automation, 2008. ICRA 2008 (pp. 1741–1746). doi: 10.1109/ROBOT.2008.4543452.