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

TL;DR

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.

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.

Figures (6)

• Figure 1: 2oo2 design pattern for OD module or similar sense/perceive functions
• Figure 2: Overview of the probabilistic risk assessment and assurance approach
• Figure 3: Fault tree of the 2oo2-OD module for the top-level event $\mathbf{H}_\mathbf{OD}$
• Figure 4: SysML activity chart describing the data processing in the OD module
• Figure 5: Probabilistic program fragment showing parts of the NN channel and the voter. The influence on some of the FT events from Fig. \ref{['fig:fta']} is indicated.