With the development of computer vision, the success ratio of underwater vehicle docking has been greatly improved. In this paper, relying on an EPnP visual positioning method, a docking pose estimation approach for autonomous underwater vehicles (AUVs) with extended Kalman filtering (EKF) is proposed. Firstly, the EPnP algorithm is implemented to calculate the relative positioning and posing of AUV to the recovery dock. Then, the EKF is used to minimize the influence of noise and visually measure the point features on the dock. Finally, the simulation of the actual docking environment was verified and attained high-precision experimental results.
An EPnP Based Extended Kalman Filtering Approach for Docking Pose Estimation of AUVs
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Chapter : 261 ; 2658-2667
2022-03-18
10 pages
Article/Chapter (Book)
Electronic Resource
English
An EPnP Based Extended Kalman Filtering Approach for Docking Pose Estimation of AUVs
British Library Conference Proceedings | 2022
|Docking and Tracking Technologies for AUVs
British Library Conference Proceedings | 2002
|