Probabilistic Safety Verification for an Autonomous Ground Vehicle: A Situation Coverage Grid Approach

2025-07-16

AI Summary

Addressing the challenge of quantifying safety assurance for industrial autonomous ground vehicles (AGVs) in diverse safety-critical environments, this paper proposes a systematic verification methodology integrating situation-coverage grids with probabilistic transition modeling. The approach automatically extracts operational situations, constructs a probabilistic state-transition model distinguishing normal and hazardous behaviors, and learns transition probabilities from scenario-based test data. Safety properties are formally specified using temporal logic, and probabilistic model checking is employed for rigorous safety verification. Its key innovation lies in the first deep coupling of situation-coverage grids with data-driven probabilistic modeling—enabling precise identification of high-risk situations and quantitative, verifiable safety confidence estimation. Experimental evaluation demonstrates that the method generates quantitative safety evidence compliant with ISO 26262 and IEC 61508, significantly enhancing regulatory compliance and trustworthiness of AGV deployment.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Security and Privacy: Large-scale security measurements

Abstract

As industrial autonomous ground vehicles are increasingly deployed in safety-critical environments, ensuring their safe operation under diverse conditions is paramount. This paper presents a novel approach for their safety verification based on systematic situation extraction, probabilistic modelling and verification. We build upon the concept of a situation coverage grid, which exhaustively enumerates environmental configurations relevant to the vehicle's operation. This grid is augmented with quantitative probabilistic data collected from situation-based system testing, capturing probabilistic transitions between situations. We then generate a probabilistic model that encodes the dynamics of both normal and unsafe system behaviour. Safety properties extracted from hazard analysis and formalised in temporal logic are verified through probabilistic model checking against this model. The results demonstrate that our approach effectively identifies high-risk situations, provides quantitative safety guarantees, and supports compliance with regulatory standards, thereby contributing to the robust deployment of autonomous systems.

Problem

• Ensures safe operation of autonomous ground vehicles in diverse conditions
• Develops probabilistic model for normal and unsafe system behavior
• Verifies safety properties through probabilistic model checking

Innovation

• Situation coverage grid for exhaustive environmental enumeration
• Probabilistic model from situation-based testing data
• Probabilistic model checking for safety verification