Journal of System Simulation
Abstract
Abstract: Aiming at the problem that the neural network autonomous docking controllers can only complete the docking of a specific ports, but cannot extend to other ports without training data, a coordinate system (berth coordinates with the berth vertex as theorigin and the shoreline as the Y Axis) is proposed. The relative position is used to train the controller. In V.Dragon-5000 navigation simulator, the container ship “Yinhe” is selected. After docking training at Dalian port, the docking controller is successfully extended to Shenzhen Shekou port and Singapore Changi port without training data. The simulation verifies that the application of the newly established coordinate system can greatly expand the application range of the neural network autonomous docking controller and reduce the cost required for training data.
Recommended Citation
Jia, Yupeng; Yong, Yin; and Zhu, Zhongxian
(2020)
"Research on Autonomous Berthing for Unmanned Ship Based on Berth Coordinates,"
Journal of System Simulation: Vol. 32:
Iss.
10, Article 8.
DOI: 10.16182/j.issn1004731x.joss.20-FZ0303
Available at:
https://dc-china-simulation.researchcommons.org/journal/vol32/iss10/8
First Page
1910
Revised Date
2020-06-04
DOI Link
https://doi.org/10.16182/j.issn1004731x.joss.20-FZ0303
Last Page
1917
CLC
U675.79
Recommended Citation
Jia Yupeng, Yin Yong, Zhu Zhongxian. Research on Autonomous Berthing for Unmanned Ship Based on Berth Coordinates[J]. Journal of System Simulation, 2020, 32(10): 1910-1917.
DOI
10.16182/j.issn1004731x.joss.20-FZ0303
Included in
Artificial Intelligence and Robotics Commons, Computer Engineering Commons, Numerical Analysis and Scientific Computing Commons, Operations Research, Systems Engineering and Industrial Engineering Commons, Systems Science Commons