Safety Case Patterns for VLA-based driving systems: Insights from SimLingo

TL;DR

This paper introduces RAISE, a safety case design approach for VLA-based autonomous driving systems, emphasizing hazard analysis, safety patterns, and evidence-based safety claims to address safety challenges posed by natural language integration.

Contribution

The paper presents a novel safety case methodology tailored for instruction-based VLA driving systems, including new safety patterns and an extension of HARA for safety assurance.

Findings

RAISE enables systematic safety case construction for VLA systems.

Application to SimLingo demonstrates effective safety claim formulation.

The approach enhances trustworthiness of instruction-responsive autonomous vehicles.

Abstract

Vision-Language-Action (VLA)-based driving systems represent a significant paradigm shift in autonomous driving since, by combining traffic scene understanding, linguistic interpretation, and action generation, these systems enable more flexible, adaptive, and instruction-responsive driving behaviors. However, despite their growing adoption and potential to support socially responsible autonomous driving as well as understanding high-level human instructions, VLA-based driving systems may exhibit new types of hazardous behaviors. For instance, the integration of open-ended natural language inputs (e.g., user or navigation instructions) into the multimodal control loop, may lead to unpredictable and unsafe behaviors that could endanger vehicle occupants and pedestrians. Hence, assuring the safety of these systems is crucial to help build trust in their operations. To support this, we propose a novel safety case design approach called RAISE. Our approach introduces novel patterns tailored to instruction-based driving systems such as VLA-based driving systems, an extension of Hazard Analysis and Risk Assessment (HARA) detailing safe scenarios and their outcomes, and a design technique to create the safety cases of VLA-based driving systems. A case study on SimLingo illustrates how our approach can be used to construct rigorous, evidence-based safety claims for this emerging class of autonomous driving systems.