mlsanityData to 14 Oct 2026

Revealing Safety-Critical Scenarios for UTM via Transformer

arXiv 2606.31114 ↗First posted 30 Jun 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Unmanned Traffic Management (UTM) systems are cloud-based platforms designed to manage and coordinate multiple aerial vehicles remotely. UTM systems are safety-critical which cannot tolerate failures like crash or collision. To reveal latent vulnerabilities, there are neither optimal failure-exposing demonstrations nor clear reward signals. Additionally, UTM's self-healing capability introduces the ``long-tail effect'' of critical failures. We propose framing UTM vulnerability discovery as a sequence modeling problem amenable to transformer-based RL architectures. Our approach leverages attention mechanisms to directly model the relationship among system states, and predict optimal actions. Our framework introduces a Policy Model that generates targeted test scenarios and an Action Sampler that enforces domain constraints. We use a risk-based reward function to guide exploration. Through extensive evaluation on a 700-hour simulation study, we demonstrate an 8× improvement in vulnerability discovery efficiency compared to expert-guided testing. It also discovers critical edge cases that traditional methods have missed.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 37 references that are in the map. First posted on arXiv 30 Jun 2026.

Builds on

23 of 37 references.

References · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  4. 2016Generative Adversarial Imitation Learningcited by 1,597
  5. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  6. 2018Self-Attention with Relative Position Representationscited by 1,120
  7. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 644
  8. 2020Long-tail learning via logit adjustmentcited by 618
  9. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 490
  10. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 298
  11. 2022A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problemscited by 231
  12. 2022Multi-Game Decision Transformerscited by 214
11 more
  1. 2023Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functionscited by 131
  2. 2021Scalable Vision Transformers with Hierarchical Poolingcited by 84
  3. 2018Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulationcited by 77
  4. 2020Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Methodcited by 75
  5. 2024In-Context Imitation Learning via Next-Token Predictioncited by 70
  6. 2023RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarioscited by 46
  7. 2023A Survey on Popularity Bias in Recommender Systemscited by 43
  8. 2021A Survey on Scenario-Based Testing for Automated Driving Systems in High-Fidelity Simulationcited by 21
  9. 2023When should we prefer Decision Transformers for Offline Reinforcement Learning?cited by 20
  10. 2023Safety-Critical Scenario Generation Via Reinforcement Learning Based Editingcited by 16
  11. 2024Towards the Unmanned Aerial Vehicle Traffic Management Systems (UTMs): Security Risks and Challengescited by 1

Built on by

Not cited yet.