强化学习
计算机科学
适应性
稳健性(进化)
人工智能
残余物
一般化
对抗制
机器学习
基线(sea)
工具箱
趋同(经济学)
编码(集合论)
威胁模型
时差学习
作者
Jiyue Tao,Tongsheng Shen,Dexin Zhao,Feitian Zhang
标识
DOI:10.1109/lra.2026.3662620
摘要
The target defense problem (TDP) for unmanned surface vehicles (USVs) concerns intercepting an adversarial USV before it breaches a designated target region, using one or more defending USVs. A particularly challenging scenario arises when the attacker exhibits superior maneuverability compared to the defenders, significantly complicating effective interception. To tackle this challenge, this letter introduces ARBoids, a novel adaptive residual reinforcement learning framework that integrates deep reinforcement learning (DRL) with the biologically inspired, force-based Boids model. Within this framework, the Boids model serves as a computationally efficient baseline policy for multi-agent coordination, while DRL learns a residual policy to adaptively refine and optimize the defenders' actions. The proposed approach is validated in a high-fidelity Gazebo simulation environment, demonstrating superior performance over traditional interception strategies, including pure force-based approaches and vanilla DRL policies. Furthermore, the learned policy exhibits strong adaptability to attackers with diverse maneuverability profiles, highlighting its robustness and generalization capability. The code of this letter is available athttps://github.com/taojy687/ARBoids.
科研通智能强力驱动
Strongly Powered by AbleSci AI