An Experience Based Learning Controller

Debadutt Goswami, Ping Jiang
DOI: 10.4236/jilsa.2010.22011                

Abstract

The autonomous mobile robots must be flexible to learn the new complex control behaviours in order to adapt effectively to a dynamic and varying environment. The proposed approach of this paper is to create a controller that learns the complex behaviours incorporating the learning from demonstration to reduce the search space and to improve the demonstrated task geometry by trial and corrections. The task faced by the robot has uncertainty that must be learned. Simulation results indicate that after the handful of trials, robot has learned the right policies and avoided the obstacles and reached the goal.

Keywords

Mobile Robots, Learning from Demonstration, Neural Network Control, Reinforcement Learning

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	M. N. Nicolescus and M. J. Mataric, “Natural Methods for Robot Task Learning: Instructive Demonstrations, Generalization and Practice,” In Proceedings of the Second International Joint Conference on Autonomous Agents and Multi-Agent Systems, Melbourne, Australia, July 14-18, 2003, pp. 241-248.
[2]	M. N. Nicolescus and M. J. Mataric, “Learning and Interacting in Human—Robot Domains,” IEEE Transactions on systems, Man and cybernetics—Part A: Systems and Humans, Vol. 31, No. 5, 2001, pp. 419-430.
[3]	G. Hailu,“Symbolic Structures in Numeric Reinforcement for Learning Optimum Robot Trajectory,” Robotics and Automation Systems, Vol. 37, No. 1, 2001, pp. 53-68.
[4]	D. C. Bentivegna, C. G. Atkeson and G. Cheng, “Learning Tasks from Observation and Practice,” Robotics and Automation Systems, Vol. 47, No. 2-3, 2004, pp. 163-169.
[5]	G. Hailu and G. Sommer, “Learning by Biasing,” IEEE International Conference on Robotics and Automation, Leuvem, Belgium, 1998, pp. 16-21.
[6]	J. R. Millan, “Reinforcement Learning of Goal Directed Obstacle Avoiding Reaction Strategies in an Autonomous Mobile Robot,” Robotics and Autonomous Systems, Vol. 15, No. 4, 1995, pp. 275-299.
[7]	A. Johannet and I. Sarda, “Goal-Directed Behaviours by Reinforcement Learning,” Neurocomputing, Vol. 28, No. 1-3, 1990, pp. 107-125.
[8]	P. M. Bartier and C. P. Keller, “Multivariate Interpolation to Incorporate Thematic Surface Data Using Inverse Distance Weighting (IDW),” Computers & Geosciences, Vol. 22, No. 7, 1996, pp. 795-799.
[9]	H. Friedrich, M. Kaiser and R. Dillmann, “What Can Robots Learn from Humans,” Annual Reviews in Control, Vol. 20, 1996, pp. 167-172.
[10]	S. Thrun, “An Approach to Learning Mobile Robot Navigation,” Robotics and Automation Systems, Vol. 15, 1995, pp. 301-319.
[11]	M. Kasper, G. Fricke, K. Steuernagel and E. von Puttka-mer, “A Behaviour Based Learning Mobile Robot Architecture for Learning from Demonstration,” Robotics and Automation Systems, Vol. 34, No. 2-3, 2001, pp. 153-164.
[12]	W. Ilg and K. Berns, “A Learning Architecture Based on Reinforcement Learning for Adaptive Control of the Walking Machine LAURON,” Robotics and Automation Systems, Vol. 15, No. 4, 1995, pp. 321-334.
[13]	H. Friedrich, M. Kaiser and R. Dillmann, “PBD-The Key to Service Robot Programming,” AAAI Technical Report SS-96-02, American Association for Artificial Intelligence, America, 1996.
[14]	H. Friedrich, M. Kaiser and R. Dillmann, “Obtaining Good Performance from a Bad Teacher,” In Programming by Demonstration vs. Learning from Examples Workshop at ML’95, Tahoe, 1995.
[15]	R. Dillmann, M. Kaiser and A. Ude, “Acquisition of Elementary Robot Skills from Human Demonstration,” In International Symposium on Intelligent Robotics Systems, Pisa, Italy, 1995, pp. 185-192.
[16]	R. S. Sutton and A. G. Barto, “Reinforcement Learning: An Introduction,” The MIT Press Cambridge, Massachusetts London, England, 1998.
[17]	B. Bakker, V. Zhumatiy, G. Gruener and J. Schmidhuber, “A Robot that Reinforcement-Learns to Identify and Memorize Important Previous Observations,” Proceedings IEEE/RSJ International Conference on Intelligent Robots and Systems, Las Vegas, USA, October 27-31, 2003, pp. 430-435.
[18]	A. Billard, Y. Epars, S. Calinon, S. Schaal and G. Cheng, “Discovering Optimal Imitation Strategies,” Robotics and Automation Systems, Vol. 47, No. 2-3, 2004, pp. 69-77.
[19]	S. Russell and P. Norvig, “Artificial Intelligence: A Modern Approach,” Second Edition, Prentice Hall, New Jersey, USA, 2002.