Identifying Uncertainty in Self-Adaptive Robotics with Large Language Models

2025-04-29

AI Summary

Adaptive robots operating in dynamic environments face significant challenges in systematically identifying and modeling uncertainties due to their inherent complexity and context sensitivity. Method: This study pioneers the systematic integration of large language models (LLMs) across the entire software engineering lifecycle, establishing an AI-driven framework for uncertainty source identification, impact analysis, and mitigation strategy generation. We conduct a comparative evaluation of ten state-of-the-art LLMs and validate our approach on four industrial robotic systems within a human-in-the-loop verification framework, enabling automated extraction and structured modeling of uncertainty knowledge. Results: Practitioner validation yields 63–88% agreement with LLM-generated outputs, confirming strong engineering utility for uncertainty modeling and decision support. Contribution: We introduce the first LLM-augmented uncertainty analysis paradigm specifically designed for adaptive robots, bridging domain experts’ intuition with AI-derived taxonomies and causal reasoning.

Technology Category

• Intelligent Robots: State Estimation
• Reasoning under Uncertainty: Uncertainty Representations
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Future self-adaptive robots are expected to operate in highly dynamic environments while effectively managing uncertainties. However, identifying the sources and impacts of uncertainties in such robotic systems and defining appropriate mitigation strategies is challenging due to the inherent complexity of self-adaptive robots and the lack of comprehensive knowledge about the various factors influencing uncertainty. Hence, practitioners often rely on intuition and past experiences from similar systems to address uncertainties. In this article, we evaluate the potential of large language models (LLMs) in enabling a systematic and automated approach to identify uncertainties in self-adaptive robotics throughout the software engineering lifecycle. For this evaluation, we analyzed 10 advanced LLMs with varying capabilities across four industrial-sized robotics case studies, gathering the practitioners' perspectives on the LLM-generated responses related to uncertainties. Results showed that practitioners agreed with 63-88% of the LLM responses and expressed strong interest in the practicality of LLMs for this purpose.

Problem

• Identifying sources and impacts of uncertainties in self-adaptive robots
• Evaluating LLMs for systematic uncertainty identification in robotics
• Assessing practicality of LLMs in mitigating robotic uncertainties

Innovation

• Using LLMs to identify robotic uncertainties
• Automating uncertainty analysis in self-adaptive robots
• Evaluating LLMs across industrial robotics case studies