Fuzzy neural network control of underwater vehicles based on desired state programming

Abstract

Due to the nonlinearity and uncertainty, the precise control of underwater vehicles in some intelligent operations hasn’t been solved very well yet. A novel method of control based on desired state programming was presented, which used the technique of fuzzy neural network. The structure of fuzzy neural network was constructed according to the moving characters and the back propagation algorithm was deduced. Simulation experiments were conducted on general detection remotely operated vehicle. The results show that there is a great improvement in response and precision over traditional control, and good robustness to the model’s uncertainty and external disturbance, which has theoretical and practical value.

Keywords

underwater vehicle / motion control / fuzzy neural network / desired state programming

References

[1] Liu X., Liu J., Xu Y. Motion control of underwater vehicle based on least disturbance BP algorithm [J]. Journal of Marine Science and Application, 2002, 1(1): 16-20

[2] Peng L., Lu Y., Wan L., Sun J. Neural network control of autonomous underwater vehicles [J]. Marine Engineering, 1995, 13(2): 38-46

[3] Hou C. H., Qian J. X. Stability analysis for neural dynamics with time-varying delays [J]. IEEE Transactions on Neural Networks, 1998, 9(1): 221-223

[4] Song Q., Xiao J. Z., Soh Y. C. Robust back propagation training algorithm for multilayered neural tracking controller [J]. IEEE Transactions on Neural Networks, 1999, 10(5): 1133-1141

[5] Liu X., Xu Y.-ru. S control of autonomous underwater vehicles [J]. Ocean Engineering, 2001, 19(3): 81-84

[6] WANG Lirong, LIU Jiancheng, YU Huanan, XU Yuru. Sliding mode control of an autonomous underwater vehicle [A]. Proceedings of 2002 International Conference on Machine Learning and Cybernetics[C]. Beijing, 2002.

[7] Yoerger D. N., Slotione J. E. Robust trajectory control of underwater vehicles [J]. IEEE J Oceanic Eng, 1985, 10(4): 462-470