Argus: Resilience-Oriented Safety Assurance Framework for End-to-End ADSs

2025-11-12

AI Summary

End-to-end autonomous driving systems (ADS) often lack real-time safety responsiveness and robustness against dynamic, unpredictable traffic hazards. To address this, we propose the first resilience-centric, plug-and-play runtime safety assurance framework for ADS. Our framework operates in three lightweight, coordinated stages: trajectory monitoring, online risk assessment, and seamless control takeover—enabling non-intrusive integration with state-of-the-art end-to-end models including TCP, UniAD, and VAD. Experimental evaluation demonstrates an average 150.30% improvement in driving scores, up to a 64.38% reduction in safety violations, and an average latency of under 12 ms. This work pioneers the systematic incorporation of resilience principles into ADS runtime safety, significantly enhancing adaptive defense capabilities against previously unseen hazardous scenarios.

Technology Category

• Natural Language Processing: Safety and Robustness
• Computer Vision: Adversarial Attacks & Robustness
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements

Abstract

End-to-end autonomous driving systems (ADSs), with their strong capabilities in environmental perception and generalizable driving decisions, are attracting growing attention from both academia and industry. However, once deployed on public roads, ADSs are inevitably exposed to diverse driving hazards that may compromise safety and degrade system performance. This raises a strong demand for resilience of ADSs, particularly the capability to continuously monitor driving hazards and adaptively respond to potential safety violations, which is crucial for maintaining robust driving behaviors in complex driving scenarios. To bridge this gap, we propose a runtime resilience-oriented framework, Argus, to mitigate the driving hazards, thus preventing potential safety violations and improving the driving performance of an ADS. Argus continuously monitors the trajectories generated by the ADS for potential hazards and, whenever the EGO vehicle is deemed unsafe, seamlessly takes control through a hazard mitigator. We integrate Argus with three state-of-the-art end-to-end ADSs, i.e., TCP, UniAD and VAD. Our evaluation has demonstrated that Argus effectively and efficiently enhances the resilience of ADSs, improving the driving score of the ADS by up to 150.30% on average, and preventing up to 64.38% of the violations, with little additional time overhead.

Problem

• Addressing resilience gaps in autonomous driving systems against hazards
• Developing runtime framework to monitor and mitigate safety violations
• Enhancing driving performance while minimizing computational overhead

Innovation

• Monitors ADS trajectories for potential hazards
• Seamlessly takes control through hazard mitigator
• Integrates with state-of-the-art end-to-end ADSs