Facilitating Change Implementation for Continuous ML-Safety Assurance

2022/09/23 by Chih‐Hong Cheng, Cheng, Chih-Hong, Nguyen Anh Vu Doan +21
Computer Science · Engineering · #FOS: Computer and information sciences #Safety Systems Engineering in Autonomy #Semantic Web and Ontologies #Software Engineering (cs.SE) #Software Reliability and Analysis Research

paper · pdf · doi:10.48550/arxiv.2209.11632

openalex publication_date 2022/09/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose a method for deploying a safety-critical machine-learning component into continuously evolving environments where an increased degree of automation in the engineering process is desired. We associate semantic tags with the safety case argumentation and turn each piece of evidence into a quantitative metric or a logic formula. With proper tool support, the impact can be characterized by a query over the safety argumentation tree to highlight evidence turning invalid. The concept is exemplified using a vision-based emergency braking system of an autonomous guided vehicle for factory automation.

Related

• Ergo, SMIRK is Safe: A Safety Case for a Machine Learning Component in a Pedestrian Automatic Emergency Brake System
• A causal model of safety assurance for machine learning
• Safety Case Templates for Autonomous Systems
• Incorporating Failure of Machine Learning in Dynamic Probabilistic Safety Assurance
• Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)