Abstract
Multi-robot concurrent learning on how to cooperatively work through the interaction with the environment is one of the ultimate goals in robotics and artificial intelligence research. In this paper, we introduce a distributed multi-robot learning algorithm that integrates reinforcement learning and neural networks (weighting network). By retrieving continuous environment state and implicit feedback (reward), the robots can generate appropriate behaviors without deliberative hard coding. We test the learning algorithm in the “museum” problem, in which robots collaboratively track moving targets. Simulation results demonstrate the efficacy of our learning algorithms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Reference
Balch, T., and Parker, L. E. (2002), Robot Teams: From Diversity to Polymorphism, Natick, Massachusetts, A K Peters Ltd.
Cao, Y. U., Fukunaga, A. S., Kahng, A.B., and Meng, F. (1995), Cooperative Mobile Robotics: Antecedents and Directions, in proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, Vol:1, pp:226–234.
Tangamchit, P., Dolan, J. M., and Khosla, P. K. (2002), The Necessity of Average Rewards in Cooperative Multirobot Learning, in proceedings of IEEE International Conference on Robotics and Automation.
Mitchell, T. M. (1997), Machine Learning, McGraw Hill.
Mataric, M. J. (1997), Reinforcement Learning in the Multi-Robot Domain, in Autonomous Robots, Vol:4(1), pp:73–83.
Sutton, R. S., and Barto, A. G. (1998), Reinforcement Learning: An Introduction, MIT Press, Cambridge, MA.
Chu, H. T., and Hong, B. R. (2000), Cooperative Behavior Acquisition in Multi Robots Environment by Reinforcement Learning Based on Action Selection Level, in proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, Vol:2, pp: 1397–1402.
Kaelbling, L. P., Littman, M. L., and Moore, A. W. (1996), Reinforcement Learning: A Survey, in Artificial Intelligence Research, Vol: 4, pp237–285.
Kawakami, K. I., Ohkura, K., and Ueda, K. (1999), Adaptive Role Development in a Homogeneous Connected Robot Group, in proceedings of IEEE International Conference on Systems, Man, and Cybernetics, Vol:3, pp:254–256.
Uchibe, E., Asada, M., and Hosoda, K. (1998), Cooperative Behavior Acquisition in Multi Mobile Robots Environment by Reinforcement Learning Based on State Vector Estimation, in proceedings of IEEE International Conference on Robotics and Automation, Leuven, Belgium, Vol:l, pp:425–430.
Michael Bowling, and Manuela Veloso (2003), Simultaneous Adversarial Multi-Robot Learning, in proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, Acapulco, Mexico.
Parker, L. E. (2002), Distributed Algorithm for Multi-Robot Observation of Multiple Moving Targets, Autonomous Robots, vol. 12(3), May.
Parker, L. E., and Emmons, B. A. (1997), Cooperative Multi-robot Observation of Multiple Moving Targets, in proceedings of IEEE International Conference on Robotics and Automation, vol. 3, pp. 2082–2089, Albuquerque, New Mexico, USA.
Liu, Z., Ang, M. H., and Seah, W. K. G. (2003), A Searching and Tracking Framework for Multi-Robot Observation of Multiple Moving Targets, in International Journal of Advanced Computational Intelligence & Intelligent Informatics (JACI3), 8–1, 2004.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer
About this paper
Cite this paper
Zheng, L., Ang, M.H., Seah, W.K.G. (2007). Multi-Robot Concurrent Learning in Museum Problem. In: Alami, R., Chatila, R., Asama, H. (eds) Distributed Autonomous Robotic Systems 6. Springer, Tokyo. https://doi.org/10.1007/978-4-431-35873-2_7
Download citation
DOI: https://doi.org/10.1007/978-4-431-35873-2_7
Publisher Name: Springer, Tokyo
Print ISBN: 978-4-431-35869-5
Online ISBN: 978-4-431-35873-2
eBook Packages: EngineeringEngineering (R0)