Adaptive Course Control System of an Unmanned Surface Vehicle (USV) Based on Back-propagation Neural Network (BPNN)
- DOI
- 10.2991/mmme-16.2016.175How to use a DOI?
- Keywords
- adaptive course control system; USV; back-propagation neural network; stochastic optimization
- Abstract
Unmanned Surface Vehicle (USV) is a small surface naval vessel which navigates and plans by itself. And undoubtedly, it plays a vital role in now and future naval battle and sea rescue. Adaptive course control is a necessary part of USV control, and in recent years, many researchers have done plenty of works on it, howev-er, many of their method did not solve the problem of the accuracy of transfer function or did not solve course maneuvering problems in a simple and efficient way. In view of this problem, we propose a novel adap-tive course control method based on back-propagation neural network (BPNN), PID (proportional, integral, derivative) algorithm and stochastic optimization. The method uses model reference adaptive theory and PID algorithm combined together to minimize the course error. And stochastic optimization is also utilized for weight adjustment of neural network. In this way, the system can output rudder angle efficiently and accu-rately in order to achieve course control of USV. Simulation results showed that the proposed method has great efficiency and theoretical feasibility and its response time is very short.
- Copyright
- © 2016, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Yang Fang AU - Huajun Zhang AU - Biao Wang AU - Chaochao Jiang PY - 2016/10 DA - 2016/10 TI - Adaptive Course Control System of an Unmanned Surface Vehicle (USV) Based on Back-propagation Neural Network (BPNN) BT - Proceedings of the 2016 4th International Conference on Mechanical Materials and Manufacturing Engineering PB - Atlantis Press SP - 732 EP - 735 SN - 2352-5401 UR - https://doi.org/10.2991/mmme-16.2016.175 DO - 10.2991/mmme-16.2016.175 ID - Fang2016/10 ER -