2022/05/30 by Chi Peng, Hanwen Zhang, Yongxiang He +1 · 31 citations
Computer Science · Engineering · Mathematics · #Adaptive Control of Nonlinear Systems #Adaptive Dynamic Programming Control #Algorithm #Artificial intelligence #Artificial neural network #Bellman equation #Bounded function #Computer science #Control (management) #Control theory (sociology) #Engineering #Function approximation #Guidance and Control Systems #Kernel (algebra) #Law #Lyapunov function #Mathematical optimization #Mathematics #Missile #Missile guidance #Nonlinear system #Observer (physics) #Optimal control #Proportional navigation #Reinforcement learning #State (computer science) #State observer
paper · doi:10.1109/taes.2022.3178770
published in IEEE Transactions on Aerospace and Electronic Systems 58(6), 5784-5797 (Institute of Electrical and Electronics Engineers)
openalex publication_date 2022/05/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/06/26
In this article, a state-following-kernel-based reinforcement learning method with an extended disturbance observer is proposed, whose application to a missile-target interception system is considered. First, the missile-target engagement is formulated as a vertical planar pursuit–evasion problem. The target maneuver is then estimated by an extended disturbance observer in real time, which leads to an infinite-horizon optimal regulation problem. Next, utilizing the local state approximation ability of state-following kernels, the critic neural network (NN) and actor NN for synchronous iteration are constructed to calculate the approximate optimal guidance policy. The states and NN weights are proven to be uniformly ultimately bounded using the Lyapunov method. Finally, numerical simulations against different types of nonstationary targets are effectively tested, and the results highlight the role of state-following kernels in the value function and policy approximation.