Learning Force-Based Robot Skills from Haptic Demonstration

Locally weighted as well as Gaussian mixtures learning algorithms are suitable strategies for trajectory learning and skill acquisition, in the context of programming by demonstration. Input streams other than visual information, as used in most applications up to date, reveal themselves as quite useful in trajectory learning experiments where visual sources are not available. For the first time, force/torque feedback through a haptic device has been used for teaching a teleoperated robot to empty a rigid container. The memory-based LWPLS and the non-memory-based LWPR algorithms [1,2,3], as well as both the batch and the incremental versions of GMM/GMR [4,5] were implemented, their comparison leading to very similar results, with the same pattern as regards to both the involved robot joints and the different initial experimental conditions. Tests where the teacher was instructed to follow a strategy compared to others where he was not lead to useful conclusions that permit devising the new research stages, where the taught motion will be refined by autonomous robot rehearsal through reinforcement learning.

[1]  Stefan Schaal,et al.  Local Dimensionality Reduction , 1997, NIPS.

[2]  Stefan Schaal,et al.  Incremental Online Learning in High Dimensions , 2005, Neural Computation.

[3]  Masaru Uchiyama,et al.  Dynamic force sensing for high-speed robot manipulation using Kalman filtering techniques , 1989, Proceedings of the 28th IEEE Conference on Decision and Control,.

[4]  Anders Robertsson,et al.  Generalized contact force estimator for a robot manipulator , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[5]  C. Mavroidis,et al.  Robust Vibration Suppression in Flexible Payloads Carried by Robot Manipulators Using Digital Filtering of Joint Trajectories , 2000 .

[6]  Henk Nijmeijer,et al.  Robot Programming by Demonstration , 2010, SIMPAR.

[7]  Carme Torras,et al.  Robot learning of container-emptying skills through haptic demonstration , 2009 .

[8]  Stefan Schaal,et al.  Locally Weighted Projection Regression: Incremental Real Time Learning in High Dimensional Space , 2000, ICML.

[9]  Stefan Schaal,et al.  Real-time robot learning with locally weighted statistical learning , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[10]  Aude Billard,et al.  Learning of Gestures by Imitation in a Humanoid Robot , 2007 .

[11]  Stefan Schaal,et al.  Robot Programming by Demonstration , 2009, Springer Handbook of Robotics.

[12]  Aude Billard,et al.  On Learning, Representing, and Generalizing a Task in a Humanoid Robot , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[13]  Andrew W. Moore,et al.  Locally Weighted Learning , 1997, Artificial Intelligence Review.

[14]  Stefan Schaal,et al.  Locally Weighted Projection Regression : An O(n) Algorithm for Incremental Real Time Learning in High Dimensional Space , 2000 .

[15]  Stefan Schaal,et al.  Robot Program 59. Robot Programming by Demonstration , 2008 .

[16]  Carme Torras,et al.  Action rule induction from cause-effect pairs learned through robot-teacher interaction , 2008 .

[17]  Stefan Schaal,et al.  Scalable Techniques from Nonparametric Statistics for Real Time Robot Learning , 2002, Applied Intelligence.

[18]  Gordon Cheng,et al.  Learning to Act from Observation and Practice , 2004, Int. J. Humanoid Robotics.