Probabilistic Risk Assessment of an Obstacle Detection System for GoA 4 Freight Trains

TL;DR

This paper presents a probabilistic risk assessment method for obstacle detection in automated freight trains, combining statistical analysis and stochastic modeling to evaluate safety and residual risks in neural network-based systems.

Contribution

It introduces a 5-step probabilistic assessment framework for obstacle detection systems in GoA 4 freight trains, integrating statistical methods with stochastic model checking.

Findings

Hazard rate becomes acceptable under certain assumptions.

High confidence in obstacle detection safety despite machine learning uncertainties.

The approach supports safety validation of neural network-based detection systems.

Abstract

In this paper, a quantitative risk assessment approach is discussed for the design of an obstacle detection function for low-speed freight trains with grade of automation (GoA)~4. In this 5-step approach, starting with single detection channels and ending with a three-out-of-three (3oo3) model constructed of three independent dual-channel modules and a voter, a probabilistic assessment is exemplified, using a combination of statistical methods and parametric stochastic model checking. It is illustrated that, under certain not unreasonable assumptions, the resulting hazard rate becomes acceptable for specific application settings. The statistical approach for assessing the residual risk of misclassifications in convolutional neural networks and conventional image processing software suggests that high confidence can be placed into the safety-critical obstacle detection function, even though its implementation involves realistic machine learning uncertainties.