自动化学报2026，Vol.52Issue(1)：52-64,13.DOI:10.16383/j.aas.c250278
融合进化算法和深度强化学习的飞行器制导控制一体化
Integrated Guidance and Control of Flight Vehicles by Fusing Evolutionary Algorithms and Deep Reinforcement Learning
摘要
Abstract
Aiming at the challenging problem of guidance and control for hypersonic flight vehicles under external disturbances and model uncertainties,this paper proposes an evolutionary reinforcement learning framework that integrates the twin delayed deep deterministic policy gradient and cross-entropy method(CEM).First,the motion model and integrated guidance and control model of the hypersonic flight vehicle are constructed.Second,the multi-constraint control problem in complex disturbed environments is transformed into a reinforcement learning decision optimization process.Leveraging the model-free,data-driven nature of deep reinforcement learning,an end-to-end mapping mechanism from state observations to rudder deflection commands is established.Meanwhile,a CEM-based action space sampling mechanism is introduced,which screens elite candidate action sets through the Q-value maximization criterion and uses the value function to guide the direction of evolutionary search.This effectively overcomes the defects of inefficient and highly blind exploration in traditional reinforcement learning and improves sample utilization efficiency.Finally,simulation results show that the proposed algorithm can adapt to variable mis-sion flight conditions such as initial altitude deviations of±300 m,velocity deviations of±200 m/s,and aerodynam-ic parameter uncertainties of±40%.It also significantly outperforms traditional control methods in core indicators such as terminal control accuracy and robustness.关键词
高超声速飞行器/制导控制一体化/深度强化学习/进化算法Key words
hypersonic flight vehicles/integrated guidance and control/deep reinforcement learning/evolutionary al-gorithm引用本文复制引用
陈建国,姚蔚然,孙光辉,吴立刚..融合进化算法和深度强化学习的飞行器制导控制一体化[J].自动化学报,2026,52(1):52-64,13.基金项目
国家自然科学基金(U23A20346,62473109),黑龙江省龙江科技英才春雁支持计划(CYQN24036)资助 Supported by National Natural Science Foundation of China(U23A20346,62473109)and the Heilongjiang Provincial Science and Technology Talent Support Program(CYQN24036) （U23A20346,62473109）
