Towards a safe MLOps Process for the Continuous Development and Safety Assurance of ML-based Systems in the Railway Domain

TL;DR

This paper proposes a comprehensive, safe MLOps process tailored for the railway domain to ensure reliable development, deployment, and safety assurance of ML-based systems in autonomous train operations.

Contribution

It introduces an integrated workflow combining system engineering, safety assurance, and ML lifecycle management specifically for railway applications.

Findings

Outlined a safe MLOps process for railway ML systems

Identified challenges in automating safety-critical stages

Presented a workflow integrating safety and ML lifecycle management

Abstract

Traditional automation technologies alone are not sufficient to enable driverless operation of trains (called Grade of Automation (GoA) 4) on non-restricted infrastructure. The required perception tasks are nowadays realized using Machine Learning (ML) and thus need to be developed and deployed reliably and efficiently. One important aspect to achieve this is to use an MLOps process for tackling improved reproducibility, traceability, collaboration, and continuous adaptation of a driverless operation to changing conditions. MLOps mixes ML application development and operation (Ops) and enables high frequency software releases and continuous innovation based on the feedback from operations. In this paper, we outline a safe MLOps process for the continuous development and safety assurance of ML-based systems in the railway domain. It integrates system engineering, safety assurance, and the ML life-cycle in a comprehensive workflow. We present the individual stages of the process and their interactions. Moreover, we describe relevant challenges to automate the different stages of the safe MLOps process.