Bootstrapping inverse kinematics with Goal Babbling

We present an approach to learn inverse kinematics of redundant systems without prior- or expert-knowledge. The method allows for an iterative bootstrapping and refinement of the inverse kinematics estimate. We show that the information structure induced by goal-directed exploration enables an efficient resolution of inconsistent samples solely from observable data. The bootstrapped solutions are aligned for a maximum of movement efficiency, i.e. realizing an effector movement with a minimum of joint motion. We derive and illustrate the exploration and learning process with a low-dimensional kinematic example and show that the same procedure scales for high dimensional problems, such as hyperredundant planar arms with up to 50 degrees of freedom.

[1]  Y. Demiris,et al.  From motor babbling to hierarchical learning by imitation: a robot developmental pathway , 2005 .

[2]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[3]  Zoubin Ghahramani,et al.  Perspectives and problems in motor learning , 2001, Trends in Cognitive Sciences.

[4]  A. Meltzoff,et al.  The Robot in the Crib: A Developmental Analysis of Imitation Skills in Infants and Robots. , 2008, Infant and child development.

[5]  S. Grossberg,et al.  A Self-Organizing Neural Model of Motor Equivalent Reaching and Tool Use by a Multijoint Arm , 1993, Journal of Cognitive Neuroscience.

[6]  D M Wolpert,et al.  Multiple paired forward and inverse models for motor control , 1998, Neural Networks.

[7]  D. Wolpert,et al.  Internal models in the cerebellum , 1998, Trends in Cognitive Sciences.

[8]  J. Piaget,et al.  The origin of intelligence in the child , 1997 .

[9]  C. Hofsten,et al.  Neonatal finger and arm movements as determined by a social and an object context , 1994 .

[10]  James V. Stone,et al.  Recurrent cerebellar architecture solves the motor-error problem , 2004, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[11]  C. Hofsten.  An action perspective on motor development , 2004, Trends in Cognitive Sciences.

[12]  Michael I. Jordan.  Computational aspects of motor control and motor learning , 2008 .

[13]  Gregory D. Hager,et al.  Robot hand-eye coordination based on stereo vision , 1995 .

[14]  A. Meltzoff,et al.  Explaining Facial Imitation: A Theoretical Model. , 1997, Early development & parenting.

[15]  Jochen J. Steil,et al.  Efficient exploration and learning of whole body kinematics , 2009, 2009 IEEE 8th International Conference on Development and Learning.

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

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

[18]  Terence D. Sanger,et al.  Failure of Motor Learning for Large Initial Errors , 2004, Neural Computation.

[19]  Michael I. Jordan.  Chapter 2 Computational aspects of motor control and motor learning , 1996 .

[20]  Susumu Tachi,et al.  Goal-directed property of online direct inverse modeling , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[21]  Stephen Grossberg,et al.  Vector associative maps: Unsupervised real-time error-based learning and control of movement trajectories , 1991, Neural Networks.

[22]  C. Hofsten.  Eye–hand coordination in the newborn. , 1982 .