SCALOFT: An Initial Approach for Situation Coverage-Based Safety Analysis of an Autonomous Aerial Drone in a Mine Environment

2025-05-27

AI Summary

Safety assurance of autonomous drones operating in dynamic, high-risk environments—such as mining sites—remains challenging due to the difficulty of systematically evaluating safety under diverse, evolving operational contexts. Method: This paper proposes a situation-coverage-driven safety verification paradigm: (i) a formal situation model is constructed; (ii) safety arguments are tightly coupled with quantifiable situation coverage metrics; and (iii) runtime monitoring, fault-injection testing, and uniquely identified logging are integrated to enable systematic safety testing, real-time behavioral supervision, and traceable violation analysis. Contribution/Results: The framework introduces situation coverage as a formally verifiable safety evidence criterion—the first such approach in this domain. It achieves 100% violation detection across multiple representative fault scenarios, significantly enhancing the reusability and interpretability of safety analyses. This work establishes a novel, rigorous methodology for trustworthiness assurance of autonomous systems in safety-critical, high-hazard settings.

Technology Category

• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Natural Language Processing: Safety and Robustness
• Reasoning under Uncertainty: Applications

Application Category

• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity

Abstract

The safety of autonomous systems in dynamic and hazardous environments poses significant challenges. This paper presents a testing approach named SCALOFT for systematically assessing the safety of an autonomous aerial drone in a mine. SCALOFT provides a framework for developing diverse test cases, real-time monitoring of system behaviour, and detection of safety violations. Detected violations are then logged with unique identifiers for detailed analysis and future improvement. SCALOFT helps build a safety argument by monitoring situation coverage and calculating a final coverage measure. We have evaluated the performance of this approach by deliberately introducing seeded faults into the system and assessing whether SCALOFT is able to detect those faults. For a small set of plausible faults, we show that SCALOFT is successful in this.

Problem

• Assessing safety of autonomous drones in mines
• Developing diverse test cases for safety analysis
• Detecting and logging safety violations in real-time

Innovation

• Framework for diverse test case development
• Real-time monitoring and safety violation detection
• Situation coverage measurement for safety argument