Data to 14 Oct 2026

Curriculum-Adapted Robust Reinforcement Learning for UAV Deconfliction in Adversarial Environments

arXiv 2506.21129 ↗First posted 26 Jun 2025cs.LG cs.AIcited by 1

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 32 of its 52 references that are in the map. First posted on arXiv 26 Jun 2025.

Builds on

32 of 52 references.

References · 32

2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
2016Progressive Neural Networkscited by 1,361
2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 371
2020Towards Continual Reinforcement Learning: A Review and Perspectivescited by 274
2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 238
2017Generate To Adapt: Aligning Domains using Generative Adversarial Networkscited by 183
2019Adaptive Gradient Methods with Dynamic Bound of Learning Ratecited by 183
2019Action Robust Reinforcement Learning and Applications in Continuous Controlcited by 174
2019Scalable methods for computing state similarity in deterministic Markov Decision Processescited by 133
2018A Sufficient Condition for Convergences of Adam and RMSPropcited by 126
2022Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexitycited by 87

20 more

2022On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgettingcited by 82
2020Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learningcited by 61
2018Finding Mixed Nash Equilibria of Generative Adversarial Networkscited by 49
2020Robust Reinforcement Learning via Adversarial training with Langevin Dynamicscited by 45
2021Distributionally Robust Learningcited by 44
2021Domain Adaptation In Reinforcement Learning Via Latent Unified State Representationcited by 35
2022Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptationcited by 28
2019Forget Me Not: Reducing Catastrophic Forgetting for Domain Adaptation in Reading Comprehensioncited by 27
2024Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithmscited by 26
2019On the Generalization Gap in Reparameterizable Reinforcement Learningcited by 22
2022A Survey on Reinforcement Learning in Aviation Applicationscited by 19
2022A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learningcited by 15
2025Rethinking the Foundations for Continual Reinforcement Learningcited by 15
2025Self-Composing Policies for Scalable Continual Reinforcement Learningcited by 11
2021Sensor Fusion-based GNSS Spoofing Attack Detection Framework for Autonomous Vehiclescited by 6
2023On the Benefit of Optimal Transport for Curriculum Reinforcement Learningcited by 6
2025On Corruption-Robustness in Performative Reinforcement Learningcited by 6
2019Adaptively Preconditioned Stochastic Gradient Langevin Dynamicscited by 5
2024Autonomous Option Invention for Continual Hierarchical Reinforcement Learning and Planningcited by 4
2019Detecting ADS-B Spoofing Attacks using Deep Neural Networkscited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

2025Real-Time Bayesian Detection of Drift-Evasive GNSS Spoofing in Reinforcement Learning Based UAV Deconflictioncited by 0

Similar, not cited

Close in wording, no citation either way