Hazard and Safety Analysis of Machine-Learning-Based Perception Capabilities in Autonomous Vehicles

2024/10/15 by John Molloy, Sepeedeh Shahbeigi, John McDermid +1
Engineering · Computer Science · #Autonomous Vehicle Technology and Safety #Adversarial Robustness in Machine Learning

paper · doi:10.1109/mc.2024.3443751

Abstract

This article proposes an adapted safety analysis method tailored to autonomous systems perception systems. It rationalizes the selection of guidewords and demonstrates how results inform design and verification through partial analysis of a road vehicle, and discusses the broader role in a comprehensive safety process.

Related

• Safety Assessment for Autonomous Systems' Perception Capabilities
• Practical Solutions for Machine Learning Safety in Autonomous Vehicles
• Enhancing Autonomous Driving Safety Analysis with Generative AI: A Comparative Study on Automated Hazard and Risk Assessment
• Safe Perception -- A Hierarchical Monitor Approach
• Safety Monitoring of Machine Learning Perception Functions: a Survey