State-Following-Kernel-Based Online Reinforcement Learning Guidance Law Against Maneuvering Target

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. T...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on aerospace and electronic systems Ročník 58; číslo 6; s. 5784 - 5797
Hlavní autoři: Peng, Chi, Zhang, Hanwen, He, Yongxiang, Ma, Jianjun
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.12.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Approximation
Artificial neural networks
Disturbance observers
Extended disturbance observer (EDO)
Guidance (motion)
guidance law
Interception
Iterative methods
Kernel
Kernels
Learning
Maneuvering targets
Mathematical analysis
Mathematical models
Missiles
model-based reinforcement learning (RL)
Neural networks
Real-time systems
Reinforcement learning
state-following kernel
ISSN:0018-9251, 1557-9603
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9251
1557-9603
DOI:10.1109/TAES.2022.3178770