Research on 3D trajectory tracking of underactuated AUV under strong disturbance environment

Article Engineering, Marine

Finite-time self-structuring neural network trajectory tracking control of underactuated autonomous underwater vehicles

Haitao Liu et al.

Summary: A finite-time self-structuring neural network (SSNN) trajectory tracking control scheme is proposed for an input constrained underactuated autonomous underwater vehicle (AUV) with unknown external disturbances. The scheme includes a time-varying barrier Lyapunov function, a finite-time controller, and a finite-time SSNN method. Simulations demonstrate the effectiveness of the proposed scheme.

OCEAN ENGINEERING (2023)

添加到收藏夹

Article Engineering, Marine

MPC-based trajectory tracking control of unmanned underwater tracked bulldozer considering track slipping and motion smoothing

Yong Li et al.

Summary: The trajectory tracking control strategy of unmanned tracked underwater bulldozer (UUTB) can improve the efficiency of trenching and dredging. The proposed MPC-CSS strategy effectively reduces track slipping and improves the lateral stability of UUTB by 72.5%.

OCEAN ENGINEERING (2023)

添加到收藏夹

Article Engineering, Marine

AUV position tracking and trajectory control based on fast-deployed deep reinforcement learning method

Yuan Fang et al.

Summary: This study successfully applies deep reinforcement learning to achieve posture control of under-actuated and X-rudder AUV, demonstrating significant performance in position-tracking and trajectory control tasks.

OCEAN ENGINEERING (2022)

添加到收藏夹

Article Engineering, Marine

AUV path tracking with real-time obstacle avoidance via reinforcement learning under adaptive constraints

Chenming Zhang et al.

Summary: This paper proposes methods for underactuated autonomous underwater vehicle (AUV) to achieve three-dimensional (3D) path tracking and real-time obstacle avoidance. The errors in path tracking are generated using the Serret-Frenet frame and line-of-sight (LOS) guidance law, while the errors in obstacle avoidance are obtained using the carrier coordinate system to filter irrelevant environment information. To handle complex target paths and unknown obstacles, the controller is designed using the deep deterministic policy gradient (DDPG) algorithm and adaptive multi-constraints. Safety constraints are applied in reward functions to prevent unnecessary explorations and facilitate convergence. The proposed algorithm shows faster convergence compared to the original DDPG algorithm in training. Various simulations conducted under different initial conditions demonstrate the effectiveness of the proposed algorithm.

OCEAN ENGINEERING (2022)

添加到收藏夹

Article Engineering, Marine

Adaptive MPC trajectory tracking for AUV based on Laguerre function

Weiran Wang et al.

Summary: An adaptive predictive control method based on Laguerre function is designed in this paper to solve the problem of slow real-time performance and poor tracking accuracy of autonomous underwater vehicle (AUV) under complex hydrological conditions. The method includes an adaptive model predictive control (MPC) module for accurate trajectory tracking and a Laguerre function module for significant computation reduction. The simulation results show that the designed method has good performance in terms of dynamics, anti-interference, and robustness when AUV tracks the trajectory with less computation.

OCEAN ENGINEERING (2022)

添加到收藏夹

Article Automation & Control Systems