Integrated Guidance and Control of Morphing Flight Vehicle via Sliding-Mode-Based Robust Reinforcement Learning
提出一种基于滑模鲁棒强化学习的变形飞行器制导与控制一体化方法，通过固定时间滑模观测器处理模型不确定性和外部扰动，离线训练后实现端到端实时控制，经测试验证了优越性和可靠性。
This article introduces an integrated guidance and control method for morphing flight vehicles, addressing model uncertainties and external disturbances through a robust deep reinforcement learning framework built on sliding-mode control (SMC). The method development begins with the establishment of a longitudinal guidance and control model and a detailed introduction to the necessary theoretical foundations. The proposed approach incorporates robust observation strategies enabled by a novel fixed-time SMC design. The agent’s actions, rewards, neural network structure, and training process are meticulously crafted to tackle practical guidance and control challenges effectively. Trained offline to achieve seamless integration of position and attitude control, the agent generates end-to-end control commands in real time during online operation. Extensive testing, including robustness evaluations, generalization assessments, and comparative performance analyses, demonstrates the superiority and reliability of the proposed method.