AUTHOR=Sun Kai , Han Zekai 

TITLE=Autonomous underwater vehicle docking system for energy and data transmission in cabled ocean observatory networks

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.960278

DOI=10.3389/fenrg.2022.960278

ISSN=2296-598X

ABSTRACT=Cabled ocean observatory networks(COON) is used for long-term all-weather observation of submarine scientific data, which contribute to low-carbon ocean energy research, and autonomous underwater vehicle (AUV) can provide it with active search capabilities. AUV need to connect with the recovery dock station (DS) on the COON to complete energy and data transmission in long-term detection tasks, low-carbon clean energy is been used by the entire system.  Many scholars have successfully completed the short-range docking and recovery task through visual detection algorithm and active landmarks, which has verified the feasibility of this technology. In this paper, an active landmarks tracking framework is proposed to estimate the position and attitude of the vehicle during docking. Firstly, we use neural network to detect and identify the DS, get the coordinates of the landmarks through the threshold segmentation algorithm, and then get the relative pose through the RPnP algorithm. Based on the two-stage docking algorithm, Kalman filter and Hungarian matching algorithm are introduced to improve the robustness of the algorithm . The reliability of the short-range docking algorithm is verified in the pool, and the robustness of the algorithm to the field environment is verified in the lake field experiment combined with long-distance guidance. The experimental results show that the algorithm framework can effectively use the landmarks information and enhance the scope of the visual guidance algorithm.