.png){kind=icon}
.png){kind=icon}
Return
Joint Optimization of Jamming Resource Allocation and Trajectory Planning for Suppressing Netted Radar System Based on Hierarchical Modular Reinforcement Learning
.png){kind=icon}
PRE
AI
J
T
K
Z
J
L
DOI：10.1109/taes.2026.3713106.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This article investigates the joint optimization of jamming resource allocation and trajectory planning (JO-JRATP), which coordinately integrates jamming resources and kinematic control to enhance jamming effectiveness against a netted radar system. However, the JO-JRATP problem faces three significant challenges: high dimensionality, temporal coupling, and environmental uncertainty. To reduce problem dimensionality, a three-step decomposition method is adopted to decompose the JO-JRATP problem into three subproblems including jamming beam allocation, trajectory planning, and jamming power allocation. Subsequently, to tackle the temporal coupling and environmental uncertainty, a hierarchical modular reinforcement learning framework is established to improve the sequential decision-making and generalization capabilities. Specifically, three specialized modules are designed using greedy policy-based and twin delayed deep deterministic policy gradient-based methods to address the three subproblems, respectively. Simulation results demonstrate that the proposed method outperforms other comparative methods, exhibiting superior jamming performance and generalization capability in unknown environments.
Keywords:
Generalization capability
jamming resource allocation
netted radar system (NRS)
reinforcement learning
trajectory planning
Journal
IF:
5.7
Papers:
651
Citations:
2.4W
Organization
Cited Papers