Learning movement primitives for force interaction tasks

Kinesthetic teaching is a promising approach to acquire robot skills in an intuitive way. This paper focuses on learning skills that do not solely rely on kinematics but also need to take into account interaction forces. We present three novel concepts towards learning such force interaction skills. Firstly, we determine segments from a small number of continuous kinesthetic demonstrations using contact information. Secondly, we associate each segment with a movement primitive, and determine its composition, i.e., the control variables and reference frames that allow to reproduce the demonstrated task. Lastly, we propose a concept to determine the transitions between the primitives during reproduction. The proposed methods are evaluated on a box pulling and flipping task, and show very good generalization abilities for objects with different geometries, and situations with different object arrangements.

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

[2]  John J. Craig,et al.  Hybrid position/force control of manipulators , 1981 .

[3]  Stefan Schaal,et al.  Towards Associative Skill Memories , 2012, 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012).

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

[5]  Andrej Gams,et al.  On-line periodic movement and force-profile learning for adaptation to new surfaces , 2010, 2010 10th IEEE-RAS International Conference on Humanoid Robots.

[6]  Darwin G. Caldwell,et al.  Imitation Learning of Positional and Force Skills Demonstrated via Kinesthetic Teaching and Haptic Input , 2011, Adv. Robotics.

[7]  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).

[8]  Olivier Mangin,et al.  Unsupervised learning of simultaneous motor primitives through imitation , 2011 .

[9]  Eren Erdal Aksoy,et al.  Learning the semantics of object–action relations by observation , 2011, Int. J. Robotics Res..

[10]  Aude Billard,et al.  Online learning of varying stiffness through physical human-robot interaction , 2012, 2012 IEEE International Conference on Robotics and Automation.

[11]  Ales Ude,et al.  Action sequencing using dynamic movement primitives , 2011, Robotica.

[12]  Dana Kulic,et al.  Incremental learning of full body motion primitives and their sequencing through human motion observation , 2012, Int. J. Robotics Res..

[13]  Andrej Gams,et al.  Coupling Movement Primitives: Interaction With the Environment and Bimanual Tasks , 2014, IEEE Transactions on Robotics.

[14]  Jochen J. Steil,et al.  Human-robot interaction for learning and adaptation of object movements , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Stefan Schaal,et al.  Learning force control policies for compliant manipulation , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  Tobias Luksch,et al.  Adaptive movement sequences and predictive decisions based on hierarchical dynamical systems , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[17]  Torgny Brogårdh,et al.  Present and future robot control development - An industrial perspective , 2007, Annu. Rev. Control..

[18]  Miles C. Bowman,et al.  Control strategies in object manipulation tasks , 2006, Current Opinion in Neurobiology.

[19]  Yoshihiko Nakamura,et al.  Learning Robot Skills Through Motion Segmentation and Constraints Extraction , 2013 .

[20]  Jan Peters,et al.  Learning to sequence movement primitives from demonstrations , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[21]  Marc Toussaint,et al.  Discovering relevant task spaces using inverse feedback control , 2014, Auton. Robots.

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

[23]  Sanjoy Dasgupta,et al.  Adaptive Control Processes , 2010, Encyclopedia of Machine Learning and Data Mining.

[24]  Oliver Kroemer,et al.  Learning sequential motor tasks , 2013, 2013 IEEE International Conference on Robotics and Automation.

[25]  Jernej Barbic,et al.  Segmenting Motion Capture Data into Distinct Behaviors , 2004, Graphics Interface.

[26]  Maja J. Matarić,et al.  Planning the Sequencing of Movement Primitives , 2004 .

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

[28]  Scott Kuindersma,et al.  Robot learning from demonstration by constructing skill trees , 2012, Int. J. Robotics Res..

[29]  Doina Precup,et al.  Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning , 1999, Artif. Intell..