Probabilistic modelling and safety assurance of an agriculture robot providing light-treatment

2025-06-24

AI Summary

To address reliability, robustness, and safety challenges in obstacle and personnel avoidance for agricultural robots performing phototherapy on delicate crops, this paper proposes a probabilistic safety assurance framework tailored for early-stage development. Methodologically, it integrates hazard identification, risk assessment matrices, and state-machine-based automated functional risk modeling, coupled with probabilistic model checking using PRISM to quantify the contributions of perception performance, warning mechanisms, and design decisions to overall safety. The key contribution is the first synergistic application of state-machine-driven risk modeling and probabilistic verification in early agricultural robot design, enabling multi-stage, quantitatively comparable safety evaluations. Experimental results demonstrate that the framework effectively identifies critical failure paths and enables quantitative comparison of safety margins across diverse perception configurations, thereby providing data-driven decision support for developing highly reliable agricultural robots. (149 words)

Technology Category

• Intelligent Robots: State Estimation
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Natural Language Processing: Safety and Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements

Abstract

Continued adoption of agricultural robots postulates the farmer's trust in the reliability, robustness and safety of the new technology. This motivates our work on safety assurance of agricultural robots, particularly their ability to detect, track and avoid obstacles and humans. This paper considers a probabilistic modelling and risk analysis framework for use in the early development phases. Starting off with hazard identification and a risk assessment matrix, the behaviour of the mobile robot platform, sensor and perception system, and any humans present are captured using three state machines. An auto-generated probabilistic model is then solved and analysed using the probabilistic model checker PRISM. The result provides unique insight into fundamental development and engineering aspects by quantifying the effect of the risk mitigation actions and risk reduction associated with distinct design concepts. These include implications of adopting a higher performance and more expensive Object Detection System or opting for a more elaborate warning system to increase human awareness. Although this paper mainly focuses on the initial concept-development phase, the proposed safety assurance framework can also be used during implementation, and subsequent deployment and operation phases.

Problem

• Ensuring safety of agricultural robots in obstacle detection
• Developing probabilistic models for early-stage risk analysis
• Evaluating design choices for risk mitigation effectiveness

Innovation

• Probabilistic modeling with PRISM checker
• Three state machines for hazard capture
• Auto-generated model for risk analysis