Answers are grounded in this paper and cite their sources.
This paper investigates the trajectory tracking problem of autonomous underwa-ter vehicles (AUV). In order to solve the problems of underdrive, non-completeness, strong cou-pling and modeling errors with random perturbations that may be encountered by underwater autonomous vehicles, in real operations. The ideal model, i.e., the nominal model, is firstly es-tablished based on the non-completely underdriven strongly coupled AUV dynamics, and the nominal model control rate is designed based on the backstepping method and Lyapunov function. Deep reinforcement learning techniques are then utilized to deal with modeling errors and stochastic perturbations of the system model in real operations, and a compensation method based on the Twin Delayed Deep Deterministic policy gradient(TD3) is proposed. Finally, numerical simulation is carried out, and the simulation results show that the control method proposedin this paper effectively reduces the effects of modeling errors and random perturbations, on the accurate trajectory tracking of AUV.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: