Learning dextrous manipulation skills using the evolution strategy

This paper presents an approach based on the evolution strategy for autonomous learning of dextrous manipulation primitives with a dextrous robot hand. We use heuristics derived from observations made on human hands to reduce the degrees of freedom of the task and make learning possible. Our system does not rely on simulation; all the experimentation is performed the 16-degree-of-freedom Utah/MIT hand. We present experimental results that show that accurate dextrous manipulation skills can be learned in a period of a few minutes. We also show the application of the learned primitives to perform an assembly task.

[1]  Olac Fuentes,et al.  Morphing Hands and Virtual Tools (or What Good is an Extra Degree of Freedom , 1994 .

[2]  Thomas H. Speeter.  Primitive based control of the Utah/MIT dextrous hand , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[3]  Olac Fuentes,et al.  Virtual Tools: A Framework for Simplifying Sensory-Motor Control in Complex Robotic Systems , 1995 .

[4]  A. E. Eiben,et al.  Global conver-gence of genetic algorithms: an infinite Markov chain analysis , 1991 .

[5]  Ingo Rechenberg,et al.  Evolutionsstrategie : Optimierung technischer Systeme nach Prinzipien der biologischen Evolution , 1973 .

[6]  Thea Iberall,et al.  The nature of human prehension: Three dextrous hands in one , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[7]  Sundar Narasimhan,et al.  Dexterous Robotic Hands: Kinematics and Control , 1988 .

[8]  R.C. Nelson,et al.  Experiments on dextrous manipulation without prior object models , 1996, Proceedings of the 1996 IEEE International Symposium on Intelligent Control.

[9]  A. E. Eiben,et al.  Global Convergence of Genetic Algorithms: A Markov Chain Analysis , 1990, PPSN.

[10]  M. Arbib.  Coordinated control programs for movements of the hand , 1985 .

[11]  Hans-Paul Schwefel,et al.  Numerical Optimization of Computer Models , 1982 .

[12]  Peter K. Allen,et al.  Compliant manipulation with a dextrous robot hand , 1993, [1993] Proceedings IEEE International Conference on Robotics and Automation.

[13]  R. Bellman.  Dynamic programming. , 1957, Science.

[14]  Olac Fuentes,et al.  Acquiring Visual-Motor Models for Precision Manipulation with Robot Hands , 1996, ECCV.

[15]  Stephen C. Jacobsen,et al.  Design of the Utah/M.I.T. Dextrous Hand , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[16]  W. Vent,et al.  Rechenberg, Ingo, Evolutionsstrategie — Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. 170 S. mit 36 Abb. Frommann‐Holzboog‐Verlag. Stuttgart 1973. Broschiert , 1975 .