Aug 2026· 2026 6th International Conference on Mechanical, Electronics and Electrical and Automation Control (METMS)· pp. 700-703· 0 citations· 11 references
Abstract
This paper concentrates on the path following control problem of underactuated unmanned surface vehicles (USVs) and proposes an intelligent following control scheme based on deep reinforcement learning (DRL). The line-of-sight (LOS) guidance method is employed to convert the geometric path following problem into a heading angle following one, thereby circumventing the hard constraint that underactuated USVs cannot directly perform lateral movement. A Markov decision process (MDP) with a hierarchical reward function is designed, and an improved deep deterministic policy gradient (IDDPG) algorithm with an asynchronous update mechanism is adopted to train the controller, addressing the reliance of traditional methods on accurate models. Besides, a multi-path generator is used during training to enhance generalization capability across different desired paths. Simulation results verify the effectiveness of the developed control method.
The deep reinforcement learning (DRL) method shows great potential in unmanned underwater vehicle (UUV) motion control. Traditional control methods rely on an accurate UUV model. However, due to the nonlinearity of the UUV model and the complex underwater environment, it is difficult to obtain an accurate model in prac...
Bo Zhong, Shuai Niu, Lin-Lin Wang et al.· Journal of Marine Science an...· 0 citations
The DDPG-DLPID, an adaptive motion controller, including a Deep Deterministic Policy Gradient (DDPG) reinforcement learning that can acquire the parameters of PID controllers is introduced, which achieves faster response and higher tracking accuracy, while substantially reducing tracking errors under interference condi...
Ling Wang, Yan Shi· SAE technical paper series· 0 citations
This paper presents a comprehensive comparison of four representative reinforcement learning (RL) methods in autonomous vehicle (AV) decision-making, including: Fitted Value Iteration (FVI), Rollout Classification Policy Iteration (RCPI), Deep Q-Network (DQN), and a discrete-action adaptation of Deep Deterministic Poli...
This study investigates the penetration guidance problem for hypersonic glide vehicles in complex constrained environments and proposes a learning-based efficient evasion guidance framework. First, a baseline strategy for determining the vehicle’s reference heading in obstacle environments is designed using an artifi...
X. Tong, Jia Song, Wen-Ling Li et al.· Aeronautical Journal· 0 citations
Simulation results demonstrate that the proposed method outperforms robust control and adaptive model predictive control in tracking accuracy under varying attack intensities, validating the effectiveness of the unified RL-based framework for AVs under coupled physical-cyber threats.
