Robustness Requirement Coverage using a Situation Coverage Approach for Vision-based AI Systems

2025-07-17

AI Summary

To address the challenge of systematically defining and comprehensively covering robustness and safety requirements for automotive vision AI systems under camera sensor degradation, this paper proposes a synergistic analysis framework integrating noise-factor modeling with operational scenario coverage. Methodologically, it pioneers the joint consideration of physical sensor degradation mechanisms—such as motion blur, low illumination, and motion distortion—with operational design domain (ODD)-driven contextual coverage analysis, augmented by domain-, sensor-, and safety-expert knowledge to enhance interpretability of degradation impacts on AI perception performance. The key contributions include: (i) establishing an extensible paradigm for robustness requirement generation; (ii) enabling structured identification of typical camera degradation scenarios; and (iii) supporting comprehensive assessment of safety-critical scenes—thereby providing both theoretical foundations and practical methodologies for functional safety verification of vision-based AI systems.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Security and privacy of machine learning and AI applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

AI-based robots and vehicles are expected to operate safely in complex and dynamic environments, even in the presence of component degradation. In such systems, perception relies on sensors such as cameras to capture environmental data, which is then processed by AI models to support decision-making. However, degradation in sensor performance directly impacts input data quality and can impair AI inference. Specifying safety requirements for all possible sensor degradation scenarios leads to unmanageable complexity and inevitable gaps. In this position paper, we present a novel framework that integrates camera noise factor identification with situation coverage analysis to systematically elicit robustness-related safety requirements for AI-based perception systems. We focus specifically on camera degradation in the automotive domain. Building on an existing framework for identifying degradation modes, we propose involving domain, sensor, and safety experts, and incorporating Operational Design Domain specifications to extend the degradation model by incorporating noise factors relevant to AI performance. Situation coverage analysis is then applied to identify representative operational contexts. This work marks an initial step toward integrating noise factor analysis and situational coverage to support principled formulation and completeness assessment of robustness requirements for camera-based AI perception.

Problem

• Ensuring AI system safety under sensor degradation
• Managing complexity in safety requirement specification
• Integrating noise analysis with situation coverage

Innovation

• Integrates camera noise factor identification
• Uses situation coverage analysis
• Extends degradation model with expert input