arXiv：cs.AI· Deepak Kumar Panda, Adolfo Perrusquia, Weisi Guo·· 16 小时前
面向对抗环境的无人机冲突消解：课程自适应鲁棒强化学习
Curriculum-Adapted Robust Reinforcement Learning for UAV Deconfliction in Adversarial Environments
AI 导读
研究者提出课程引导的鲁棒强化学习框架，通过逐步施加梯度对抗观测扰动并对齐各阶段TD误差分布，使策略无需针对特定攻击重训即可应对未见GNSS欺骗攻击。在动态3D障碍无人机冲突消解环境中，课程自适应策略（CurAd）在固定欺骗下实现约99-100%任务成功率，而最优鲁棒基线仅20-24%；在动态障碍诱骗下取得最高回合奖励，任务完成步数中位数最多减少22%。
正文
Abstract:Autonomous unmanned aerial vehicles (UAVs) increasingly rely on reinforcement learning (RL) for navigation, yet global navigation satellite system (GNSS) spoofing attacks can induce out-of-distribution observation shifts that corrupt value estimation and degrade mission performance. Existing robust RL methods often lack generalization to unseen attacks. To address this, we propose a curriculum-guided adaptation framework that progressively exposes a robust policy to gradient-based adversarial observation perturbations of increasing intensity while aligning temporal-difference (TD) error distributions across curriculum stages. By preserving TD-error consistency rather than targeting specific attack models, the framework promotes resilience across attack conditions. We further derive a TD-space generalization certificate that bounds performance degradation when the TD-error distribution under a test-time attack remains sufficiently close to that of the final curriculum stage. We evaluate the framework in a UAV deconfliction environment with dynamic 3D obstacles under unseen fixed and dynamic GNSS spoofing attacks. Under fixed spoofing, the curriculum-adapted (CurAd) policy achieves approximately 99-100% mission success across evaluated traffic densities, compared with 20-24% for the best-performing robust baseline, while also outperforming the non-robust vanilla baseline. Under dynamic obstacle-luring spoofing, CurAd achieves the highest episodic rewards and reduces median mission completion steps by up to 22% relative to the best-performing robust RL baseline. These findings demonstrate that adversarial curriculum adaptation transfers resilience from synthetic perturbations to unseen GNSS spoofing attacks without attack-specific retraining, enhancing robust autonomous UAV navigation.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2506.21129 [cs.LG] |
| (or arXiv:2506.21129v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2506.21129 arXiv-issued DOI via DataCite |
Submission history
From: Deepak Kumar Panda [view email]
[v1]
Thu, 26 Jun 2025 10:10:41 UTC (621 KB)
[v2]
Tue, 2 Jun 2026 15:41:02 UTC (2,889 KB)
[v3]
Sat, 10 Oct 2026 08:56:36 UTC (2,834 KB)
来源：arXiv：cs.AI · arxiv.org