This paper presents a novel Gaussian process (GP) based adaptive tracking control method for autonomous underwater vehicles subject to unknown system dynamics and uncertain smooth actuator nonlinearity. We deploy sparse online Gaussian process (SOGP) technique to estimate the unknown system dynamics and uncertain actuator nonlinearity simultaneously, with a given prior dynamic model. Based on an adaptive sliding mode control framework, the posterior means of GPs are used to compensate for all the unknown terms. Besides, the corresponding posterior variances, which indicate the probabilistic confidence intervals, are applied to update robust control gains. Theoretical analysis is performed to prove the stability of a closed-loop system with our proposed control law. Comparison simulation results validate the effectiveness of our GP-based adaptive tracking control method.
Learning Based Trajectory Tracking Control of Autonomous Underwater Vehicles with Actuator Nonlinearity
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 : 100 ; 1013-1024
2022-03-18
12 pages
Article/Chapter (Book)
Electronic Resource
English
British Library Conference Proceedings | 2022
|Tracking Control for Autonomous Underwater Vehicles
NTIS | 2002
|Trajectory-tracking Control of Underactuated Underwater Vehicles
Springer Verlag | 2009
|