Challenges of Machine Learning Applied to Safety-Critical Cyber-Physical Systems
Open Access
- 19 November 2020
- journal article
- research article
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 2 (4) , 579-602
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.Keywords
Funding Information
- German Federal Ministry of Education and Research (01IS18061D)
This publication has 47 references indexed in Scilit:
- Working Together: A Review on Safe Human-Robot Collaboration in Industrial EnvironmentsIEEE Access, 2017
- Cyber Physical System (CPS)-Based Industry 4.0: A SurveyJournal of Industrial Integration and Management, 2017
- Towards Unified Data and Lifecycle Management for Deep Learning2017
- The Synthetic Data Vault2016
- An Open Approach to Autonomous VehiclesIEEE Micro, 2015
- Adversarial machine learning2011
- Principles of engineering safety: Risk and uncertainty reductionReliability Engineering & System Safety, 2008
- Basic concepts and taxonomy of dependable and secure computingIEEE Transactions on Dependable and Secure Computing, 2004
- Data preparation for data miningApplied Artificial Intelligence, 2003
- Data miningACM SIGMOD Record, 2002