Obstacle Avoidance Method for AUV Based on Adaptive Fuzzy Neural Network

DOI: https://doi.org/10.62517/jike.202504304

Author(s)

Jiacheng Xin1,2, Jiwei Zhao1,2, Kai Chen1,2, Dong Wang1,2, Jianguo Wu1,2

Affiliation(s)

1Tianjin Hanhai Lanfan Marine Technology Co., Ltd, Tianjin, China 2Tianjin Key Laboratory of Deep-sea Intelligent Mobile Survey Equipment, Tianjin, China

Abstract

Aiming at the problem of autonomous obstacle avoidance of autonomous underwater vehicle (AUV) in unknown underwater environment, an adaptive fuzzy neural network obstacle avoidance algorithm is proposed, which combines the logical reasoning ability of fuzzy control and the self-learning ability of neural network. Firstly, the obstacle avoidance model of AUV in the plane is established. Secondly, the structure of the fuzzy neural network is designed. The parameters of the fuzzy membership function and the weights of the neural network are optimized by using the learning ability of the neural network, and the output error is reduced. Finally, through the simulation of AUV respectively in the horizontal plane and vertical plane within the feasibility of the proposed algorithm of obstacle avoidance.

Keywords

Furry Neural Network; AUV; Autonomous Obstacle Avoidance; Adaptive Control

References

[1]Zheng Zeng, Lian Lian, Karl Sammut, Fangpo He, Youhong Tang, Andrew Lammas. A survey on path planning for persistent autonomy of autonomous underwater vehicles. Ocean Engineering,2015,110. [2]Guo Yiping, Wang Yimin, Ren Yuanzhou. Research on AUV Trajectory Tracking Control Technology Based on Line-of-Sight Guidance Method. Acoustics and Electronics Engineering, 2018(04):32-36+40. (in Chinese) [3]Yao Peng, Xie Zexiao. An AUV Autonomous Obstacle Avoidance Method Based on Modified Navigation Vector Field. Acta Automatica Sinica:1-11(2019-02-19). (in Chinese). [4]Johann Borenstein, Yoram Koren.Real-time avoidance for fast mobile robots. IEEE Transactions on Systems, Man and Cybernetics,1989, 19(5):1179-1187. [5]Yang Jian, Meng Fanchen. Research on Obstacle Avoidance Motion Method for Micro AUV Based on Artificial Potential Field Method. Mine Warfare and Ship Protection, 2017, 25(04):67-71. (in Chinese) [6]Xing Mingzhi. Research on AUV Planning and Obstacle Avoidance Method Based on Fish Swarm-Artificial Potential Field Algorithm. Harbin Engineering University, 2024. (in Chinese) [7]Pan Yunwei, Li Min, Zeng Xiangguang, et al. Obstacle Avoidance and Path Planning for Autonomous Underwater Vehicle Based on Artificial Potential Field and Improved Reinforcement Learning. Acta Armamentarii, 2025, 46(04):72-83. (in Chinese) [8]Xu Hongli, Feng Xisheng. Research on AUV Fuzzy Obstacle Avoidance Method Based on Event Feedback Monitoring. Proceedings of the Conference on Automation and Advanced Integration Technologies (II), 2007:704-708. (in Chinese) [9]Yu Jiancheng, Zhang Aiqun, Wang Xiaohui, Su Lijuan. Direct Adaptive Control for Underwater Robot Based on Fuzzy Neural Network. Acta Automatica Sinica, 2007(08):840-846. (in Chinese) [10]Zhang Yibo, Gao Bingpeng. Research on AUV Path Planning Based on Deep Reinforcement Learning. Journal of Northeast Normal University (Natural Science Edition), 2025, 57(01):53-62. (in Chinese) [11]Kong Lingwen, Li Pengyong, Du Qiaoling. Design of Closed-loop Control System for Autonomous Navigation of a Hexapod Robot Based on Fuzzy Neural Network. Robot, 2018, 40(01):16-23. (in Chinese)