Autonomous reconfiguration of robot shape by using Q-learning

A modular robot can be built with a shape and function that matches the working environment. We developed a four-arm modular robot system which can be configured in a planar structure. A learning mechanism is incorporated in each module constituting the robot. We aim to control the overall shape of the robot by an accumulation of the autonomous actions resulting from the individual learning functions. Considering that the overall shape of a modular robot depends on the learning conditions in each module, this control method can be treated as a dispersion control learning method. The learning object is cooperative motion between adjacent modules. The learning process proceeds based on Q-learning by trial and error. We confirmed the effectiveness of the proposed technique by computer simulation.

[1]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[2]  Mark Yim,et al.  New locomotion gaits , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[3]  Toshio Fukuda,et al.  Approach to the dynamically reconfigurable robotic system , 1988, J. Intell. Robotic Syst..

[4]  Peter Dayan,et al.  Technical Note: Q-Learning , 2004, Machine Learning.

[5]  Toshio Fukuda,et al.  Dynamically reconfigurable robotic system , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[6]  Wei-Min Shen,et al.  Hormone-inspired adaptive communication and distributed control for CONRO self-reconfigurable robots , 2002, IEEE Trans. Robotics Autom..

[7]  Daniela Rus,et al.  Locomotion versatility through self-reconfiguration , 1999, Robotics Auton. Syst..

[8]  Peter Dayan,et al.  Q-learning , 1992, Machine Learning.

[9]  Gregory S. Chirikjian,et al.  Useful metrics for modular robot motion planning , 1997, IEEE Trans. Robotics Autom..

[10]  Nancy M. Amato,et al.  Distributed reconfigurtion of metamorphic robot chains , 2000, PODC.

[11]  Marsette Vona,et al.  Crystalline Robots: Self-Reconfiguration with Compressible Unit Modules , 2001, Auton. Robots.

[12]  Christiaan J. J. Paredis,et al.  A rapidly deployable manipulator system , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[13]  Gregory S. Chirikjian,et al.  Modular Robot Motion Planning Using Similarity Metrics , 2001, Auton. Robots.

[14]  Daniela Rus,et al.  Cellular Automata for Decentralized Control of Self-Reconfigurable Robots , 2007 .