A Learning from Demonstration Approach fusing Torque Controllers

Torque controllers have become commonplace in the new generation of robots, allowing for complex robot motions involving physical contact with the surroundings in addition to task constraints at Cartesian and joint levels. When learning such skills from demonstrations, one is often required to think in advance about the appropriate task representation (usually either operational or configuration space). We here propose a probabilistic approach for simultaneously learning and synthesizing control commands which take into account task, joint space and force constraints. We treat the problem by considering different torque controllers acting on the robot, whose relevance is learned from demonstrations. This information is used to combine the controllers by exploiting the properties of Gaussian distributions, generating torque commands that satisfy the important features of the task. We validate the approach in two experimental scenarios using 7-DoF torque-controlled manipulators, with tasks requiring the fusion of multiple controllers to be properly executed.

[1]  Jochen J. Steil,et al.  Multiple task optimization with a mixture of controllers for motion generation , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[2]  Jun Nakanishi,et al.  Operational Space Control: A Theoretical and Empirical Comparison , 2008, Int. J. Robotics Res..

[3]  Darwin G. Caldwell,et al.  Learning Competing Constraints and Task Priorities from Demonstrations of Bimanual Skills , 2017, ArXiv.

[4]  Andrej Gams,et al.  Learning Compliant Movement Primitives Through Demonstration and Statistical Generalization , 2016, IEEE/ASME Transactions on Mechatronics.

[5]  Oussama Khatib,et al.  Control of Free-Floating Humanoid Robots Through Task Prioritization , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[6]  Giuseppe Oriolo,et al.  Learning soft task priorities for control of redundant robots , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[7]  Kevin M. Lynch,et al.  Modern Robotics: Mechanics, Planning, and Control , 2017 .

[8]  Sandra Hirche,et al.  Bayesian uncertainty modeling for programming by demonstration , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[9]  Nikos G. Tsagarakis,et al.  An attractor-based Whole-Body Motion Control (WBMC) system for humanoid robots , 2013, 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids).

[10]  Olivier Sigaud,et al.  Variance modulated task prioritization in Whole-Body Control , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[11]  Aude Billard,et al.  Learning from Humans , 2016, Springer Handbook of Robotics, 2nd Ed..

[12]  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).

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

[14]  Sylvain Calinon,et al.  A tutorial on task-parameterized movement learning and retrieval , 2016, Intell. Serv. Robotics.

[15]  Sandra Hirche,et al.  Risk-Sensitive Optimal Feedback Control for Haptic Assistance , 2012, 2012 IEEE International Conference on Robotics and Automation.

[16]  Aude Billard,et al.  Statistical Learning by Imitation of Competing Constraints in Joint Space and Task Space , 2009, Adv. Robotics.

[17]  Oussama Khatib,et al.  A unified approach for motion and force control of robot manipulators: The operational space formulation , 1987, IEEE J. Robotics Autom..

[18]  Olivier Sigaud,et al.  Many regression algorithms, one unified model: A review , 2015, Neural Networks.

[19]  Jun Nakanishi,et al.  Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors , 2013, Neural Computation.