AIMay 21

A Subjective Logic-based method for runtime confidence updates in safety arguments

arXiv:2605.225306.4
Predicted impact top 98% in AI · last 90 daysOriginality Incremental advance
AI Analysis

For safety-critical autonomous systems, this method provides a practical way to dynamically update assurance confidence at runtime, balancing responsiveness and computational simplicity.

The paper presents a Subjective Logic-based method for runtime confidence updates in safety arguments, integrating design-time evidence and runtime safety performance indicators. Demonstrated on an ML-based construction cone detection system, it shows how confidence evolves with observed violations.

We present a method for dynamic quantitative assurance that enhances static safety cases with continuous, runtime-driven confidence updates. The method quantifies and propagates confidence across the development lifecycle by integrating design-time evidence and windowed runtime Safety Performance Indicators (SPIs) within a single Subjective Logic (SL)-based assurance case. At runtime, SPI evidence is continuously evaluated, and targeted claims are updated using a rule that increases confidence in the absence of violations and imposes prompt penalties when violations occur. This design prioritizes safety-relevant responsiveness over exact classical Bayesian posterior updates. We demonstrate the method using a simulation-based construction zone assist function, focusing on an ML-based construction cone detection component, and show how confidence evolves as SPI evidence is observed in operation.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes