Ensuring Safe Autonomy: Navigating the Future of Autonomous Vehicles

TL;DR

The paper addresses the challenge of proving safe autonomous vehicle operation in the presence of perception unreliability and dynamic environments. It proposes a modular, self-adaptive autonomy framework that integrates dynamic risk management with behavior-based robotics to improve runtime safety assurance. It surveys existing safety paradigms (functional safety, RSS) and examines how situation-aware risk management and behavior networks can provide more flexible, context-sensitive decision-making, while noting integration and standardization gaps. The work argues that dynamic, system-level approaches offer practical advantages for dependable autonomous driving and outlines directions for demonstration and standardization.

Abstract

Autonomous driving vehicles provide a vast potential for realizing use cases in the on-road and off-road domains. Consequently, remarkable solutions exist to autonomous systems' environmental perception and control. Nevertheless, proof of safety remains an open challenge preventing such machinery from being introduced to markets and deployed in real world. Traditional approaches for safety assurance of autonomously driving vehicles often lead to underperformance due to conservative safety assumptions that cannot handle the overall complexity. Besides, the more sophisticated safety systems rely on the vehicle's perception systems. However, perception is often unreliable due to uncertainties resulting from disturbances or the lack of context incorporation for data interpretation. Accordingly, this paper illustrates the potential of a modular, self-adaptive autonomy framework with integrated dynamic risk management to overcome the abovementioned drawbacks.