Paper:
Language: English:
Fuzzy Genetic Network Programming with Noises for Mobile Robot Navigation
Siti Sendari, Shingo Mabu, Andre Tjahjadi,
and Kotaro Hirasawa
Graduate School of Information, Production and Systems, Waseda University, 2-7 Hibikino, Wakamatsu-ku, Kitakyushu, Fukuoka 808-0135, Japan
Received: March 14, 2011
Accepted: May 16, 2011
Keywords: genetic network programming, noise, reinforcement learning, robustness, wall following behavior
Journal ref: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.15, No.7 pp. 767-776, 2011
Abstract
Genetic Network Programming (GNP) has been proposed as one of the evolutionary algorithms, which is represented by graph structures. It was extended to GNP with Reinforcement Learning (GNP-RL) which combines online learning and evolution. GNP-RL succeeded in implementing the wall following behaviors of a Khepera robot. The objective of this paper is to improve the robustness of GNP-RL by introducing fuzzy GNP with noises. Fuzzy GNP overcomes the sharp boundary problem using the probabilistic transition on fuzzy judgment nodes, which improves the exploration ability. Furthermore, the robustness of fuzzy GNP can be improved by adding Gaussian noises to the sensors during the training phase. In order to evaluate the robustness of fuzzy GNP with noises, the wall following of a Khepera robot is simulated. Simulation results show that fuzzy GNP with noises is superior to GNP-RL.
Preview (PDF)
Reference
[1] S. Parasuraman, V. Ganapathy, and B. Shirinzadeh, “Behavior based Mobile Robot Navigation Technique for Real World Environment using Fuzzy Logic System,” in Proc. of the IEEE Int. Conf. on Systems, Man and Cybernetics, pp. 3359-3364, 2004.
[2] P. Rusu, E. M. Petriu, T. E. Whalen, A. Cornell, and H. J. W. Spoelder, “Behavior-Based Neuro-Fuzzy Controller for Mobile Robot Navigation,” IEEE Trans. on Instrumentation and Measurement, Vol.52, No.4, pp. 1335-1340, 2003.
[3] K. J. Lee and B. T. Zhang, “Learning Robot Behavior by Evolving Genetic Programs,” in Proc. of the 26th Annual Conf. of the IEEE Industrial Electronic Society IECON, Vol.4, pp. 2867-2872, 2000.
[4] S. Mabu, H. Hatakeyama, M. T. Thu, K. Hirasawa, and J. Hu, “Genetic Network Programming with Reinforcement Learning and Its Application to Making Mobile Robot Behavior,” IEEJ Trans. on Electronics, Information and System, Vol.126. No.8, pp. 1009-1015, 2006.
[5] M. J. Er and Y. Zhou, “Automatic Generation of Fuzzy Inference System via Unsupervised Learning,” Neural Networks, Vol.21, pp. 1556-1566, 2008.
[6] A. R. S. Fialho, M. T. C. Andrade, and F. L. Caversan, “Exploration of Transformations Between Fuzzy and Evolutionary Techniques,” in Proc. of the IEEE Int. Conf. on Intelligent Systems Design and applications, pp. 184-189, 2007.
[7] K. Hirasawa, M. Okubo, H. Katagiri, J. Hu, and J. Murata, “Comparison between Genetic Network Programming (GNP) and Genetic Programming (GP),” in Proc. of the IEEE Congress on Evolutionary Computation, Vol.2, pp. 1276-1282, 2001.
[8] S. Mabu, K. Hirasawa, and J. Hu, “A Graph-Based Evolutionary Algorithm: Genetic Network Programming (GNP) and Its Extension Using Reinforcement Learning,” Evolutionary Computation, Vol.15, No.3, pp. 369-398, 2007.
[9] Y. Lu, S. Mabu, and K. Hirasawa, “Multi-car Elevator Group Supervisory Control System using Genetic Network Programming,” IEEJ Trans. on Electronics, Information and System, Vol.125, No.1, 2005.
[10] Y. Chen, S. Mabu, K.Shimada, and K. Hirasawa, “Trading Rules on Stock Markets Using Genetic Network Programming with Sarsa Learning,” J. of Advanced Computational Intelligence and Intelligent Informatics, Vol.12, No.4, pp. 383-392, 2008.
[11] L. Wang, S. Mabu, F. Ye, S. Eto, X. Fan, and K. Hirasawa, “Genetic Network Programming with Rule Accumulation and Its application to Tile-World Problem,” J. of Advanced Computational Intelligence and Intelligent Informatics, Vol.13, No.5, pp. 551-560, 2009.
[12] S. Mabu, A. Tjahjadi, S. Sendari, and K. Hirasawa, “Evaluation on the Robustness of Genetic Network Programming with Reinforcement Learning,” in Proc. of the IEEE Int. Conf. on Systems, Man, and Cybernetics, 2010.
[13] T. M. Gureckis and B. C. Love, “Learning in Noise: Dynamic Decision-Making in a Variable Environment,” J. of Mathematical Psychology, Vol.53, pp. 180-193, 2009.
[14] “Cyberbotics,” [Online].
Available: http://www.cyberbotics.com/
[15] K. Taboada, S. Mabu, E. Gonzales, K. Shimada, and K. Hirasawa, “Mining Fuzzy Association Rules: A General Model Based on Genetic Network Programming and its Applications,” IEEJ Trans. on Electrical and Electronic Engineering, Vol.128, No.5, pp. 343-354, 2010.
[16] Y. Yang, S. Mabu, K. Shimada, and K. Hirasawa, “Fuzzy Intertransaction Class Association Rule Mining using Genetic Network Programming for Stock Market Prediction,” IEEJ Trans. on on Electrical and Electronic Engineering, Vol.129, No.1, pp. 1-8, 2011.
[17] R. S. Sutton and A. G. Barto, “Reinforcement Learning – An Introduction,” Cambridge, Massachusetts, London, England: MIT Press, 1998.
[18] Michalewicz, “Genetic Algorithms + Data Structures = Evolution Program, 3rd,” Revised and extended edition, Springer, p. 103, 1999.
[Notice]
* "Preview" is the first 2 pages of the article. You don't need the registration.
* To read the PDF file you will then need to download and install the Adobe Reader.
Adobe Reader is free and available for download here:
