Abstract
In a previous paper, we proposed a solution to path planning of a mobile robot. In our approach, we formulated the problem as a discrete optimization problem at each time step. To solve the optimization problem we, used an objective function consisting of a goal term, a smoothness term and a collision term. This paper presents a theoretical method using reinforcement learning for adjusting weght parameters in the objective functions. However, the conventional Q-learning method cannot be applied to a non-Markov decision process. Thus, we applied William’s learning algorithm, REINFORCE, to derive an updating rule for the weight parameters. This is a stochasic hill-climbing method to maximize a value function. We verified the updating rule by experiment.
Chapter PDF
Similar content being viewed by others
References
Kortenkamp, D., Bonasso, R.P, and Murphy, R. (eds.), Artificial Intelligence and Mobile Robots. AAAI Press/The MIT Press (1998)
Hwang, Y.K. and Ahuja, N.(1992), Gross Motion Planning—A Survey. ACM Computing Surveys 24(3):219–291
Igarashi, H. and IOi, K., Path Planning and Navigation of a Mobile Robot as Discrete Optimization Problems. In Sugisaka, M. and Tanaka, H., editors, Proceedings of The Fifth International Symposium on Artificial Life and Robotics, ISBN4-9900462-0-X, Oita Japan, 2000:297–300
Burgard, W., Fox, D. and Thrun, S. (1997), Active Mobile Robot Localization. In: Proceedings of 15th Joint Conference on Artificial Intelligence (IJCAI97), Nagoya, Japan,August 23-29,1997, Vol.2, pp.1346–1352
Williams, R.J. (1992), Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning. Machine Learning 8:229–256
Thrun, S. et al., Map Learning and High-Speed Navigation in RHINO, in [1], pp. 21–52
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Igarashi, H. (2001). Path Planning of a Mobile Robot as a Discrete Optimization Problem and Adjustment of Weight Parameters in the Objective Function by Reinforcement Learning. In: Stone, P., Balch, T., Kraetzschmar, G. (eds) RoboCup 2000: Robot Soccer World Cup IV. RoboCup 2000. Lecture Notes in Computer Science(), vol 2019. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45324-5_32
Download citation
DOI: https://doi.org/10.1007/3-540-45324-5_32
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42185-6
Online ISBN: 978-3-540-45324-6
eBook Packages: Springer Book Archive