A Behavior-Based Policy for Multirobot Formation Control

Abstract:

This paper presents an advanced method with hierarchical architecture for multirobot formation control. The control system consists of fundamental behavior module, supervisor module and velocity tuning module. Formation and obstacle avoidance behaviors are produced by fundamental behavior module, among which the obstacle avoidance behavior is produced by fuzzy logic technique. Then a FNN (Fuzzy Neural Network) is designed to fuse the two fundamental behaviors in supervisor module. The FNN is trained through reinforcement learning. At last, a velocity tuning module is designed to adjust the speed of the robot. Simulation results validate the feasibility of this method．

• Periodical: Applied Mechanics and Materials (Volumes 220-223)
• Pages: 1181-1185
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.220-223.1181
• Online since: November 2012
• Authors: Jie Dong, Hai Tao Chen, Sen Liu
• Keywords: Fuzzy Logic Technique, Fuzzy Neural Network (FNN), Hierarchical Architecture, Reinforcement Learning

References

[1] Y. Zhang, L. Zeng and Y. H. Li. Multirobot formation control using leader-follower for MANET[C]. Proceedings of the 2009 IEEE International Conference on Robotics and Biomimetics. Guilin, 2009: 337-342.

DOI: 10.1109/robio.2009.5420668

[2] T. Balch, R.C. Arkin. Behavior-based formation control for multirobot teams[J]. IEEE Transactions on Robotics and Automation. 1998, 14(6): 926-939.

DOI: 10.1109/70.736776

[3] J. Yuan, G.Y. Tang. Formation control for mobile multiple robots based on hierarchical virtual structures[C]. IEEE International Conference on Control and Automation. Xiamen, 2010: 393-398.

DOI: 10.1109/icca.2010.5524078

[4] M. Andreas. Collision avoiding continuation method for the inverse kinematics of redundant manipulators [C]. IEEE International Conference on Robotics and Automation. New Orleans, 2004, 2: 1593-1598.

DOI: 10.1109/robot.2004.1308051

[5] J.X. Feng, J.H. Ruan, Y.B. Li. Study on intelligent vehicle lane change path planning and control simulation[C]. IEEE International Conference on Information Acquisition. Weihai, 2006: 683-688.

DOI: 10.1109/icia.2006.305809

[6] Nguyen D P, Nguyen T T. A solution of obstacle collision avoidance for robotic fish based on fuzzy systems[C]. IEEE International Conference on Robotics and Biomimetics. Phuket, 2011: 1707-1711.

DOI: 10.1109/robio.2011.6181535

[7] M. Sisto, D.B. Gu. A fuzzy leader-follower approach to formation control of multiple mobile robots[C]. IEEE/RSJ International Conference on Intelligent Robots and Systems. Beijing, 2006: 2515-2520.

DOI: 10.1109/iros.2006.281698

[8] Y.M. Lei, Q.D. Zhu. The application of fuzzy neural networks in formation control for multi-robot system [J]. IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application. 2008, 1: 69-73.

DOI: 10.1109/paciia.2008.255

[9] M. Tan, S. Wang, Z.Q. Cao. Multi-robot System [M]. Beijing: Tsinghua University Press. 2005: 57.

[10] H.M. Xiao, C.Y. Su, W.F. Xie. Variable structure control based on the fuzzy neural networks[C]. Fuzzy Information Processing Society Annual meeting of the North American. Montreal, 2006: 206-210.

DOI: 10.1109/nafips.2006.365409