Dual Deep Neural Networks for Improving Trajectory Tracking Control of Unmanned Surface Vehicle

被引:1
作者
Sun, Wenli [1 ]
Gao, Xu [2 ]
Yu, Yanli [3 ]
机构
[1] Dalian Maritime Univ, Nav Coll, Dalian, Peoples R China
[2] Dalian Maritime Univ, Natl Engn Res Ctr Maritime Nav Syst, Dalian, Peoples R China
[3] Dalian Maritime Univ, Coll Transportat Engn, Dalian, Peoples R China
来源
2020 CHINESE AUTOMATION CONGRESS (CAC 2020) | 2020年
关键词
Trajectory tracking; dual deep neural network; line of sight; guidance law; unmanned surface vehicle;
D O I
10.1109/CAC51589.2020.9326517
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This study proposes a deep learning-based method for trajectory tracking control of Unmanned Surface Vehicle (USV). Trajectory tracking control is an effective approach for autonomous sailing, making the USV to track towards a desired route. Dual Deep Neural Networks (DualDNN) are presented in this study to evaluate and revise the traditional Line-of-Sight (LOS) guidance algorithm. In particular, One DNN is used to evaluate the sailing effect of USV, while the other DNN is used to estimate the cross-track distance and lateral distance of the guidance law. The experimental results demonstrate that by adopting the proposed Dual-DNN model, the trajectory tracking error is reduced by 5.3% and 21.7% compared to the Single-DNN model and the traditional LOS model, respectively. The magnitude and frequency of throttle and rudder manipulations have been reduced. The smooth curves from the actuators are more consistent with the regular mode of surface vehicle maneuvering.
引用
收藏
页码:3441 / 3446
页数:6
相关论文
共 22 条
[1]  
[Anonymous], 2011, HDB MARINE CRAFT HYD
[2]  
[Anonymous], 2019, ROBOTICA
[3]   Integral LOS Control for Path Following of Underactuated Marine Surface Vessels in the Presence of Constant Ocean Currents [J].
Borhaug, Even ;
Pavlov, A. ;
Pettersen, Kristin Y. .
47TH IEEE CONFERENCE ON DECISION AND CONTROL, 2008 (CDC 2008), 2008, :4984-4991
[4]   A review on improving the autonomy of unmanned surface vehicles through intelligent collision avoidance manoeuvres [J].
Campbell, S. ;
Naeem, W. ;
Irwin, G. W. .
ANNUAL REVIEWS IN CONTROL, 2012, 36 (02) :267-283
[5]  
Cao SJ, 2018, 2018 IEEE CSAA GUIDANCE, NAVIGATION AND CONTROL CONFERENCE (CGNCC)
[6]   Robust Adaptive Path Following Control of an Unmanned Surface Vessel Subject to Input Saturation and Uncertainties [J].
Fan, Yunsheng ;
Huang, Hongyun ;
Tan, Yuanyuan .
APPLIED SCIENCES-BASEL, 2019, 9 (09)
[7]   Line-of-Sight Path Following for Dubins Paths With Adaptive Sideslip Compensation of Drift Forces [J].
Fossen, Thor I. ;
Pettersen, Kristin Y. ;
Galeazzi, Roberto .
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2015, 23 (02) :820-827
[8]  
Goodfellow I., 2016, Deep Learning
[9]   A new guidance law for trajectory tracking of an underactuated unmanned surface vehicle with parameter perturbations [J].
Huang, Haibin ;
Gong, Mian ;
Zhuang, Yufei ;
Sharma, Sanjay ;
Xu, Dianguo .
OCEAN ENGINEERING, 2019, 175 :217-222
[10]   ESO-Based Line-of-Sight Guidance Law for Path Following of Underactuated Marine Surface Vehicles With Exact Sideslip Compensation [J].
Liu, Lu ;
Wang, Dan ;
Peng, Zhouhua .
IEEE JOURNAL OF OCEANIC ENGINEERING, 2017, 42 (02) :477-487