Posts

Poster Presentation at Machine Learning in Certified Systems Workshop

Members of the CyberFactory#1 project consortium participated in the Machine Learning in Certified Systems Workshop organised by the DEEL project. Ana Pereira from the University of Applied Sciences Berlin (HTW) presented a poster on “Safety Hazards Analysis and Mitigation Strategies for Machine Learning-Based Safety-Critical Systems”.

Abstract:

Machine Learning (ML) is increasingly applied for the control of safety-critical Cyber-Physical Systems (CPS). As a consequence, the safety of machine learning became a focus area for research in recent years. Applying a classic technique of safety engineering, our work provides a methodological analysis of the safety hazards that could be introduced along the ML lifecycle, and that could compromise the safe operation of ML-based CPS. The comprehensive analysis presented here intends to be used as a basis for holistic approaches for safety engineering of ML-based CPS in safety-critical applications, and aims to support the use of ML-based control systems in highly safety-critical applications and their certification.

The poster was created by Ana Pereira and Carsten Thomas from the University of Applied Sciences Berlin (HTW).

You can download the poster here.

Challenges of Machine Learning Applied to Safety-Critical Cyber-Physical Systems

Abstract

Machine Learning (ML) is increasingly applied for the control of safety-critical Cyber-Physical Systems (CPS) in application areas that cannot easily be mastered with traditional control approaches, such as autonomous driving. As a consequence, the safety of machine learning became a focus area for research in recent years. Despite very considerable advances in selected areas related to machine learning safety, shortcomings were identified on holistic approaches that take an end-to-end view on the risks associated to the engineering of ML-based control systems and their certification. Applying a classic technique of safety engineering, our paper provides a comprehensive and methodological analysis of the safety hazards that could be introduced along the ML lifecycle, and could compromise the safe operation of ML-based CPS. Identified hazards are illustrated and explained using a real-world application scenario—an autonomous shop-floor transportation vehicle. The comprehensive analysis presented in this paper is intended as a basis for future holistic approaches for safety engineering of ML-based CPS in safety-critical applications, and aims to support the focus on research onto safety hazards that are not yet adequately addressed.

Access to Document

Link

Authors

Ana Pereira and Carsten Thomas (Hochschule für Technik und Wirtschaft Berlin)