Robust Multi-Agent Reinforcement Learning for Small UAS Separation Assurance under GPS Degradation and Spoofing

• URL: http://arxiv.org/abs/2603.28900v1
• Date: Mon, 30 Mar 2026 18:26:59 GMT
• Title: Robust Multi-Agent Reinforcement Learning for Small UAS Separation Assurance under GPS Degradation and Spoofing
• Abstract summary: We address robust separation assurance for small Unmanned Aircraft Systems (sUAS) under GPS degradation and spoofing.<n>We show that this expression approximates the true worst-case adversarial perturbation with second-order accuracy.<n>In a high-density sUAS simulation, we observe near-zero collision rates under corruption levels up to 35%, outperforming a baseline policy trained without adversarial perturbations.
• Score: 21.870113057418447
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We address robust separation assurance for small Unmanned Aircraft Systems (sUAS) under GPS degradation and spoofing via Multi-Agent Reinforcement Learning (MARL). In cooperative surveillance, each aircraft (or agent) broadcasts its GPS-derived position; when such position broadcasts are corrupted, the entire observed air traffic state becomes unreliable. We cast this state observation corruption as a zero-sum game between the agents and an adversary: with probability R, the adversary perturbs the observed state to maximally degrade each agent's safety performance. We derive a closed-form expression for this adversarial perturbation, bypassing adversarial training entirely and enabling linear-time evaluation in the state dimension. We show that this expression approximates the true worst-case adversarial perturbation with second-order accuracy. We further bound the safety performance gap between clean and corrupted observations, showing that it degrades at most linearly with the corruption probability under Kullback-Leibler regularization. Finally, we integrate the closed-form adversarial policy into a MARL policy gradient algorithm to obtain a robust counter-policy for the agents. In a high-density sUAS simulation, we observe near-zero collision rates under corruption levels up to 35%, outperforming a baseline policy trained without adversarial perturbations.

Related papers

• Runtime Safety Filtering for Learned Small UAS Separation Policies under GNSS Degradation [3.719121868494767]
  Learning-based separation assurance for small Unmanned Aircraft Systems fails in urban environments.<n>This raises a fundamental question for deploying learned separation policies under navigation degradation.<n>This work evaluates both approaches for multi-agent sUAS separation under adversarial constraints.
  arXiv  Detail & Related papers  (2026-07-10T22:33:35Z)
• Trust, Geometry, and Rules: A Credibility-Aware Reinforcement Learning Framework for Safe USV Navigation under Uncertainty [32.34854002457735]
  We propose a framework integrating credibility-aware learning, geometric safety shielding, and continuous rule-aware embedding.<n>We show improved training robustness against perceptual inconsistency and superior collision avoidance and COLREGs compliance over baselines.
  arXiv  Detail & Related papers  (2026-05-26T12:59:43Z)
• On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment [54.30690671490447]
  Existing safety-alignment signals are largely response-level or off-policy.<n>FATE transforms verifier-scored failures into repair supervision without expert demonstrations.<n>FATE reduces attack success rate by 33.5%, harmful compliance by 82.6%, and improves external trajectory-safety diagnosis by 6.5%.
  arXiv  Detail & Related papers  (2026-05-12T09:56:28Z)
• AgentDrift: Unsafe Recommendation Drift Under Tool Corruption Hidden by Ranking Metrics in LLM Agents [2.995458991057093]
  We introduce a paired-trajectory protocol that replays real financial dialogues under clean and contaminated tool-output conditions.<n>We observe the evaluation-blindness pattern: recommendation quality is largely preserved under contamination.<n>Even narrative-only corruption (biased headlines, no numerical manipulation) induces significant drift while completely evading consistency monitors.
  arXiv  Detail & Related papers  (2026-03-13T01:54:00Z)
• Sparse Threats, Focused Defense: Criticality-Aware Robust Reinforcement Learning for Safe Autonomous Driving [11.62520853262219]
  We introduce criticality-aware robust RL (CARRL) for handling sparse, safety-critical risks in autonomous driving.<n>CARRL consists of two interacting components: a risk exposure adversary (REA) and a risk-targeted robust agent (RTRA)<n>We show that our approach reduces the collision rate by at least 22.66% across all cases compared to state-of-the-art baseline methods.
  arXiv  Detail & Related papers  (2026-01-05T05:20:16Z)
• AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning [78.5751183537704]
  AdvEvo-MARL is a co-evolutionary multi-agent reinforcement learning framework that internalizes safety into task agents.<n>Rather than relying on external guards, AdvEvo-MARL jointly optimize attackers and defenders.
  arXiv  Detail & Related papers  (2025-10-02T02:06:30Z)
• Curriculum-Guided Antifragile Reinforcement Learning for Secure UAV Deconfliction under Observation-Space Attacks [6.367978467906828]
  Reinforcement learning policies are vulnerable to adversarial attacks in the observation space.<n>We propose an antifragile RL framework designed to adapt against curriculum of incremental adversarial perturbations.<n>Results show that the antifragile policy consistently outperforms standard and robust RL baselines.
  arXiv  Detail & Related papers  (2025-06-26T10:10:41Z)
• GCP: Guarded Collaborative Perception with Spatial-Temporal Aware Malicious Agent Detection [11.336965062177722]
  Collaborative perception is vulnerable to adversarial message attacks from malicious agents.<n>This paper reveals a novel blind area confusion (BAC) attack that compromises existing single-shot outlier-based detection methods.<n>We propose Guarded Collaborative Perception framework based on spatial-temporal aware malicious agent detection.
  arXiv  Detail & Related papers  (2025-01-05T06:03:26Z)
• Efficient Adversarial Training in LLMs with Continuous Attacks [99.5882845458567]
  Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses. C-AdvIPO is an adversarial variant of IPO that does not require utility data for adversarially robust alignment.
  arXiv  Detail & Related papers  (2024-05-24T14:20:09Z)
• Uniformly Safe RL with Objective Suppression for Multi-Constraint Safety-Critical Applications [73.58451824894568]
  The widely adopted CMDP model constrains the risks in expectation, which makes room for dangerous behaviors in long-tail states. In safety-critical domains, such behaviors could lead to disastrous outcomes. We propose Objective Suppression, a novel method that adaptively suppresses the task reward maximizing objectives according to a safety critic.
  arXiv  Detail & Related papers  (2024-02-23T23:22:06Z)
• Malicious Agent Detection for Robust Multi-Agent Collaborative Perception [52.261231738242266]
  Multi-agent collaborative (MAC) perception is more vulnerable to adversarial attacks than single-agent perception. We propose Malicious Agent Detection (MADE), a reactive defense specific to MAC perception. We conduct comprehensive evaluations on a benchmark 3D dataset V2X-sim and a real-road dataset DAIR-V2X.
  arXiv  Detail & Related papers  (2023-10-18T11:36:42Z)
• Safety Margins for Reinforcement Learning [53.10194953873209]
  We show how to leverage proxy criticality metrics to generate safety margins. We evaluate our approach on learned policies from APE-X and A3C within an Atari environment.
  arXiv  Detail & Related papers  (2023-07-25T16:49:54Z)
• Robust Reinforcement Learning on State Observations with Learned Optimal Adversary [86.0846119254031]
  We study the robustness of reinforcement learning with adversarially perturbed state observations. With a fixed agent policy, we demonstrate that an optimal adversary to perturb state observations can be found. For DRL settings, this leads to a novel empirical adversarial attack to RL agents via a learned adversary that is much stronger than previous ones.
  arXiv  Detail & Related papers  (2021-01-21T05:38:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.