Human-in-the-Loop Uncertainty Analysis in Self-Adaptive Robots Using LLMs

2026-05-04

AI Summary

In dynamically unpredictable environments, adaptive robots often incur safety violations or operational failures due to difficulties in systematically identifying and addressing uncertainty. To address this challenge, this work proposes RoboULM, the first uncertainty taxonomy tailored specifically for adaptive robotics, and introduces a human-in-the-loop analytical framework that synergistically integrates large language models with domain expert knowledge. This framework supports structured prompting and iterative refinement to enhance uncertainty reasoning. Evaluated by 16 practitioners across four industrial scenarios, RoboULM demonstrates significant improvements in the systematicity and efficiency of uncertainty analysis, while maintaining strong practicality and interpretability.

Abstract

Self-adaptive robots operate in dynamic, unpredictable environments where unaddressed uncertainties can lead to safety violations and operational failures. However, systematically identifying and analyzing these uncertainties, including their sources, impacts, and mitigation strategies, remains a significant challenge given the inherent complexity of real-world environments, dynamic robotic behavior, and the rapid evolution of robotic technologies. To address this, we introduce RoboULM, a human-in-the-loop methodology and tool that supports practitioners in systematically exploring uncertainties at the design stage using large language models (LLMs). Moreover, we present an uncertainty taxonomy that provides a detailed catalog of uncertainties in self-adaptive robots. We evaluated RoboULM with 16 practitioners from four industrial use cases. The results show that RoboULM was perceived as both useful and easy to understand, with the participants particularly valuing structured prompting and iterative refinement support. These findings demonstrate the potential of RoboULM as a viable solution for systematic uncertainty analysis in complex robots.

Problem

• self-adaptive robots
• uncertainty analysis
• human-in-the-loop
• safety violations
• operational failures

Innovation

• Human-in-the-Loop
• Large Language Models
• Uncertainty Analysis
• Self-Adaptive Robots
• Uncertainty Taxonomy