# Revealing Safety-Critical Scenarios for UTM via Transformer

arXiv: https://arxiv.org/abs/2606.31114 · HTML: https://mlsanity.com/paper/2606.31114/

## 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 (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Offline Reinforcement Learning as One Big Sequence Modeling Problem](https://mlsanity.com/paper/2106.02039/) (2021)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress](https://mlsanity.com/paper/1806.06877/) (2018)
- [A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems](https://mlsanity.com/paper/2203.01387/) (2022)
- [Multi-Game Decision Transformers](https://mlsanity.com/paper/2205.15241/) (2022)
- [Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions](https://mlsanity.com/paper/2309.10150/) (2023)
- [Scalable Vision Transformers with Hierarchical Pooling](https://mlsanity.com/paper/2103.10619/) (2021)
- [Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation](https://mlsanity.com/paper/1811.00145/) (2018)
- [Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method](https://mlsanity.com/paper/2003.01197/) (2020)
- [In-Context Imitation Learning via Next-Token Prediction](https://mlsanity.com/paper/2408.15980/) (2024)
- [RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarios](https://mlsanity.com/paper/2312.13303/) (2023)
- [A Survey on Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2308.01118/) (2023)
- [A Survey on Scenario-Based Testing for Automated Driving Systems in High-Fidelity Simulation](https://mlsanity.com/paper/2112.00964/) (2021)
- [When should we prefer Decision Transformers for Offline Reinforcement Learning?](https://mlsanity.com/paper/2305.14550/) (2023)
- [Safety-Critical Scenario Generation Via Reinforcement Learning Based Editing](https://mlsanity.com/paper/2306.14131/) (2023)
- [Towards the Unmanned Aerial Vehicle Traffic Management Systems (UTMs): Security Risks and Challenges](https://mlsanity.com/paper/2408.11125/) (2024)

## 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.