Learning versatile sensorimotor coordination with goal babbling and neural associative dynamics

We combine an efficient exploration mechanism for bootstrapping of sensorimotor coordination skills with an associative network model to represent multiple coordination styles. Both approaches are integrated into a three-phased process of exploration, i.e. discovery of a new model, consolidation, the long-term storage of multiple models in a dynamical associative network, and exploitation of multiple models by the neural dynamics for versatile sensorimotor coordination. The proposed exploration-consolidation process is demonstrated for a planar robotic manipulator with ten degrees of freedom. Exploitation of sensorimotor coordination from the consolidated neural dynamics features motor hysteresis and additionally comprises a forward model that can be utilized to interpret proprioceptive feedback.

[1]  Alexander Verl,et al.  The Bionic Handling Assistant: a success story of additive manufacturing , 2011 .

[2]  J. Kelso,et al.  Multifunctionality and switching in the coordination dynamics of reaching and grasping , 1994 .

[3]  Jochen J. Steil,et al.  Explorative learning of inverse models: A theoretical perspective , 2014, Neurocomputing.

[4]  Mitsuo Kawato,et al.  Feedback-Error-Learning Neural Network for Supervised Motor Learning , 1990 .

[5]  Jochen J. Steil,et al.  Learning whole upper body control with dynamic redundancy resolution in coupled associative radial basis function networks , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[6]  Peter Tiño,et al.  Fast parzen window density estimator , 2009, 2009 International Joint Conference on Neural Networks.

[7]  Nicholas Roy,et al.  Real-Time Inverse Dynamics Learning for Musculoskeletal Robots Based on Echo State Gaussian Process Regression , 2013 .

[8]  Stefan Schaal,et al.  Learning inverse kinematics , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[9]  Pierre-Yves Oudeyer,et al.  Active learning of inverse models with intrinsically motivated goal exploration in robots , 2013, Robotics Auton. Syst..

[10]  Koh Hosoda,et al.  Anthropomorphic Muscular–Skeletal Robotic Upper Limb for Understanding Embodied Intelligence , 2012, Adv. Robotics.

[11]  Sandeep Gulati,et al.  Neutral learning of constrained nonlinear transformations , 1989, Computer.

[12]  Jochen J. Steil,et al.  Online Goal Babbling for rapid bootstrapping of inverse models in high dimensions , 2011, 2011 IEEE International Conference on Development and Learning (ICDL).

[13]  Joachim Hoffmann,et al.  Exploiting redundancy for flexible behavior: unsupervised learning in a modular sensorimotor control architecture. , 2007, Psychological review.

[14]  Jan Peters,et al.  Model learning for robot control: a survey , 2011, Cognitive Processing.

[15]  Jochen J. Steil,et al.  Goal Babbling Permits Direct Learning of Inverse Kinematics , 2010, IEEE Transactions on Autonomous Mental Development.

[16]  Jochen J. Steil,et al.  Multi-directional continuous association with input-driven neural dynamics , 2013, Neurocomputing.

[17]  John Baillieul,et al.  Kinematic programming alternatives for redundant manipulators , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[18]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[19]  Jochen J. Steil,et al.  Neural learning and dynamical selection of redundant solutions for inverse kinematic control , 2011, 2011 11th IEEE-RAS International Conference on Humanoid Robots.