ROMAN: Reward-Orchestrated Multi-Head Attention Network for Autonomous Driving System Testing

• URL: http://arxiv.org/abs/2602.05629v1
• Date: Thu, 05 Feb 2026 13:09:58 GMT
• Title: ROMAN: Reward-Orchestrated Multi-Head Attention Network for Autonomous Driving System Testing
• Authors: Jianlei Chi, Yuzhen Wu, Jiaxuan Hou, Xiaodong Zhang, Ming Fan, Suhui Sun, Weijun Dai, Bo Li, Jianguo Sun, Jun Sun,
• Abstract summary: Automated Driving System (ADS) acts as the brain of autonomous vehicles, responsible for their safety and efficiency.<n>Current testing approaches face challenges: limited ability to generate complex and high-risk law-breaking scenarios.<n>We propose ROMAN, a novel scenario generation approach for ADS testing that combines a multi-head attention network with a traffic law weighting mechanism.
• Score: 8.899903216053035
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automated Driving System (ADS) acts as the brain of autonomous vehicles, responsible for their safety and efficiency. Safe deployment requires thorough testing in diverse real-world scenarios and compliance with traffic laws like speed limits, signal obedience, and right-of-way rules. Violations like running red lights or speeding pose severe safety risks. However, current testing approaches face significant challenges: limited ability to generate complex and high-risk law-breaking scenarios, and failing to account for complex interactions involving multiple vehicles and critical situations. To address these challenges, we propose ROMAN, a novel scenario generation approach for ADS testing that combines a multi-head attention network with a traffic law weighting mechanism. ROMAN is designed to generate high-risk violation scenarios to enable more thorough and targeted ADS evaluation. The multi-head attention mechanism models interactions among vehicles, traffic signals, and other factors. The traffic law weighting mechanism implements a workflow that leverages an LLM-based risk weighting module to evaluate violations based on the two dimensions of severity and occurrence. We have evaluated ROMAN by testing the Baidu Apollo ADS within the CARLA simulation platform and conducting extensive experiments to measure its performance. Experimental results demonstrate that ROMAN surpassed state-of-the-art tools ABLE and LawBreaker by achieving 7.91% higher average violation count than ABLE and 55.96% higher than LawBreaker, while also maintaining greater scenario diversity. In addition, only ROMAN successfully generated violation scenarios for every clause of the input traffic laws, enabling it to identify more high-risk violations than existing approaches.

Related papers

• Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents [68.20752678837377]
  We propose a principled taxonomy that transforms single-turn harmful tasks into multi-turn attack sequences.<n>Using this taxonomy, we construct MT-AgentRisk, the first benchmark to evaluate multi-turn tool-using agent safety.<n>We propose ToolShield, a training-free, tool-agnostic, self-exploration defense.
  arXiv  Detail & Related papers  (2026-02-13T18:38:18Z)
• HetroD: A High-Fidelity Drone Dataset and Benchmark for Autonomous Driving in Heterogeneous Traffic [49.31491001465465]
  HetroD is a dataset and benchmark for developing autonomous driving systems in heterogeneous environments.<n>HetroD targets the critical challenge of navi- gating real-world heterogeneous traffic dominated by vulner- able road users (VRUs)
  arXiv  Detail & Related papers  (2026-02-03T12:12:47Z)
• OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows [77.95511352806261]
  Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms.<n>We propose OS-Sentinel, a novel hybrid safety detection framework that combines a Formal Verifier for detecting explicit system-level violations with a Contextual Judge for assessing contextual risks and agent actions.
  arXiv  Detail & Related papers  (2025-10-28T13:22:39Z)
• Seeking to Collide: Online Safety-Critical Scenario Generation for Autonomous Driving with Retrieval Augmented Large Language Models [39.139025989575686]
  We introduce an online, retrieval-augmented large language model (LLM) framework for generating safety-critical driving scenarios.<n>Our model reduces the mean minimum time-to-collision from 1.62 to 1.08 s and incurs a 75% collision rate, substantially outperforming baselines.
  arXiv  Detail & Related papers  (2025-05-02T03:22:00Z)
• SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models [63.71984266104757]
  We propose SafeAuto, a framework that enhances MLLM-based autonomous driving by incorporating both unstructured and structured knowledge.<n>To explicitly integrate safety knowledge, we develop a reasoning component that translates traffic rules into first-order logic.<n>Our Multimodal Retrieval-Augmented Generation model leverages video, control signals, and environmental attributes to learn from past driving experiences.
  arXiv  Detail & Related papers  (2025-02-28T21:53:47Z)
• TeLL-Drive: Enhancing Autonomous Driving with Teacher LLM-Guided Deep Reinforcement Learning [61.33599727106222]
  TeLL-Drive is a hybrid framework that integrates a Teacher LLM to guide an attention-based Student DRL policy.<n>A self-attention mechanism then fuses these strategies with the DRL agent's exploration, accelerating policy convergence and boosting robustness.
  arXiv  Detail & Related papers  (2025-02-03T14:22:03Z)
• MARL-OT: Multi-Agent Reinforcement Learning Guided Online Fuzzing to Detect Safety Violation in Autonomous Driving Systems [1.1677228160050082]
  This paper introduces MARL-OT, a scalable framework that leverages MARL to detect safety violations of Autonomous Driving Systems (ADSs)<n>MARL-OT employs MARL for high-level guidance, triggering various dangerous scenarios for the rule-based online fuzzer to explore potential safety violations of ADSs.<n>Our approach improves the detected safety violation rate by up to 136.2% compared to the state-of-the-art (SOTA) testing technique.
  arXiv  Detail & Related papers  (2025-01-24T12:34:04Z)
• Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving [65.61999354218628]
  We take the first step toward designing black-box adversarial attacks specifically targeting vision-language models (VLMs) in autonomous driving systems.<n>We propose Cascading Adversarial Disruption (CAD), which targets low-level reasoning breakdown by generating and injecting semantics.<n>We present Risky Scene Induction, which addresses dynamic adaptation by leveraging a surrogate VLM to understand and construct high-level risky scenarios.
  arXiv  Detail & Related papers  (2025-01-23T11:10:02Z)
• CRASH: Challenging Reinforcement-Learning Based Adversarial Scenarios For Safety Hardening [16.305837225117607]
  This paper introduces CRASH - Challenging Reinforcement-learning based Adversarial scenarios for Safety Hardening. First CRASH can control adversarial Non Player Character (NPC) agents in an AV simulator to automatically induce collisions with the Ego vehicle. We also propose a novel approach, that we term safety hardening, which iteratively refines the motion planner by simulating improvement scenarios against adversarial agents.
  arXiv  Detail & Related papers  (2024-11-26T00:00:27Z)
• LMM-enhanced Safety-Critical Scenario Generation for Autonomous Driving System Testing From Non-Accident Traffic Videos [22.638869562921133]
  It is paramount to generate a diverse range of safety-critical test scenarios for autonomous driving systems.<n>Some accident-free real-world scenarios can not only lead to misbehaviors in ADSs but also be leveraged for the generation of ADS violations.<n>It is of significant importance to discover safety violations of ADSs from routine traffic scenarios.
  arXiv  Detail & Related papers  (2024-06-16T09:05:56Z)
• REDriver: Runtime Enforcement for Autonomous Vehicles [6.97499033700151]
  We propose REDriver, a general and modular approach to runtime enforcement of autonomous driving systems. ReDriver monitors the planned trajectory of the ADS based on a quantitative semantics of STL. It uses a gradient-driven algorithm to repair the trajectory when a violation of the specification is likely.
  arXiv  Detail & Related papers  (2024-01-04T13:08:38Z)

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.