An autonomous path-planning strategy based on Skinner operant conditioning principle and reinforcement learning principle is developed in this paper. The core strategies are the use of tendency cell and cognitive learning cell, which simulate bionic orientation and asymptotic learning ability. Cognitive learning cell is designed on the base of Boltzmann machine and improved Q-Learning algorithm, which executes operant action learning function to approximate the operative part of robot system. The tendency cell adjusts network weights by the use of information entropy to evaluate the function of operate action. The results of the simulation experiment in mobile robot showed that the designed autonomous path-planning strategy lets the robot realize autonomous navigation path planning. The robot learns to select autonomously according to the bionic orientate action and have fast convergence rate and higher adaptability.
If the inline PDF is not rendering correctly, you can download the PDF file here.
1. Cai, Z.-X., H.-G. He, C. Hong. Mobile Robot Navigation Control Theory and Method in Unknown Environment. Science Press, 2009.
2. Koren, Y., J. Borenstein. Potential Field Methods and Their Inherent Limitations for Mobile Robot Navigation. - In: Proc. of 1991 IEEE International Conference on Robotics and Automation (Cat. No 91CH2969-4), 9-11 April 1991，Los Alamitos, CA, USA, IEEE Comput. Soc. Press，1991, pp. 1398-1404.
3. Qiao, J. F., R. Y. Fan, H. G. Han, X. G. Ruan. Research and Realization of Dynamic Neural Network Navigation Algorithm for Mobile Robot. - Control Theory & Applications, Vol. 27, January 2010, No 1, pp. 111-115.
4. Chaomin, L., S. X. Yang．A Bioinspired Neural Network for Real-Time Concurrent Map Building and Complete Coverage Robot Navigation in Unknown Environments. - IEEE Transactions on Neural Networks, Vol. 19, 2008, No 7, pp. 1279-1298.
5. Caihong, L., Z. Jingyuan, L. Yibin. Application of Artificial Neural Network Based on Q-Learning for Mobile Robot Path Planning. - In: Proc. of 2006 IEEE International Conference on Information Acquisition, 20-23 August 2006, Piscataway, NJ, USA, IEEE, 2006, pp. 978-982.
6. Qiao, J., R. Fan, H. Hanet al．Q-Learning Based on Dynamical Structure Neural Network for Robot Navigation in Unknown Environment. - In: Proc. of 6th International Symposium on Neural Networks, ISNN 2009, 26-29 May 2009, Wuhan, China, Springer Verlag, 2009, pp. 188-196.
7. Dalalah, D., M. T. Hayajneh. Dynamic Neural Model for Mobile Robot Navigation. - Neural Network World, Vol. 17, 2007, No 1, pp. 65-80.
8. Wang, X.-S., Y. Gao, Y.-H. Ceng. Knowledge Guided Genetical Gorithmfor Path Planning of Robot. - Control and Decision Making, Vol. 24, 2009, No 7, pp. 1043-1049.
9. Tzafestas, C. S., S. G. Tzafestas. Recent Algorithms for Fuzzy and Neurofuzzy Path Planning and Navigation of Autonomous Mobile Robots. - Systems Science, Vol. 25, 1999, No 2, pp. 25-39.
10. Chen, W.-D., B.-X. Li, Q.-G. Zhu. Application of Fuzzy Control in Mobile Robot Path Planning. - Computer Engineering and Applications, Vol. 45, 2009, No 31, pp. 221-223.
11. Yuhu, C., W. Xuesong, L. Ruhai. Fuzzy Control System for Path Following of Mobile Robots. - ICIC Express Letters, Vol. 3, 2009, No 3A, pp. 403-408
12. Zavlangas, P. G., S. G. Tzafestas. Motion Control for Mobile Robot Obstacle Avoidance and Navigation: A Fuzzy Logic-Based Approach. - Systems Analysis Modelling Simulation, Vol. 43, 2003, No 12, pp. 1625-1637.
14. Xu, Xi. Reforment Learning and Approximate Dynamic Programming. Science Press, 2010.
15. Ye, C., N. H. C. Yung, D. Wang. A Fuzzy Controller with Supervised Learning Assisted Reinforcement Learning Algorithm for Obstacle Avoidance. - Systems, Man, and Cybernetics, Part B: Cybernetics. - IEEE Transactions on, Vol. 33, 2003, No 1, pp. 17-27.
16. Boubertakh, H., M. Tadjine, P. Y. Glorennec. A New Mobile Robot Navigation Method Using Fuzzy Logic anda Modified Q-Learning Algorithm. - Journal of Intelligent and Fuzzy Systems, Vol. 21, 2010, No 1, pp. 113-119.
17. Chang, C., P. Gaudiano. Application of Biological Learning Theories to Mobile Robot Avoidance and Approach Behaviors. - Journal of Complex Systems, Vol. 1, 1998, pp. 79-114.