Autonomous Surface Selection For Manipulator-Based UV Disinfection In Hospitals Using Foundation Models

2025-11-23

AI Summary

Current UV surface disinfection in hospitals relies heavily on manually defined regions, while deep learning approaches require extensive labeled data and fine-tuning and lack scene understanding—leading to erroneous irradiation risks. Method: This paper proposes a foundation-model-driven approach leveraging Vision-Language Models (VLMs) to enable semantic-guided segmentation optimization, automatically identifying and precisely extracting target disinfection surfaces while filtering out small distractors. Integrated with a robotic arm and a simulated UV light source, it forms a closed-loop decision-execution system supporting partial-surface selection and non-contact autonomous disinfection. Contribution/Results: Evaluated in real clinical settings, the method achieves >92% segmentation accuracy for target versus non-target surfaces, significantly reducing human intervention and enhancing both automation and safety. It provides a lightweight, generalizable solution suitable for large-scale deployment in healthcare environments.

Technology Category

• Computer Vision: Segmentation
• Natural Language Processing: Safety and Robustness
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Ultraviolet (UV) germicidal radiation is an established non-contact method for surface disinfection in medical environments. Traditional approaches require substantial human intervention to define disinfection areas, complicating automation, while deep learning-based methods often need extensive fine-tuning and large datasets, which can be impractical for large-scale deployment. Additionally, these methods often do not address scene understanding for partial surface disinfection, which is crucial for avoiding unintended UV exposure. We propose a solution that leverages foundation models to simplify surface selection for manipulator-based UV disinfection, reducing human involvement and removing the need for model training. Additionally, we propose a VLM-assisted segmentation refinement to detect and exclude thin and small non-target objects, showing that this reduces mis-segmentation errors. Our approach achieves over 92% success rate in correctly segmenting target and non-target surfaces, and real-world experiments with a manipulator and simulated UV light demonstrate its practical potential for real-world applications.

Problem

• Automating UV surface disinfection selection in hospitals using foundation models
• Reducing human intervention and model training requirements for disinfection
• Improving segmentation accuracy to avoid unintended UV exposure

Innovation

• Leverages foundation models to simplify surface selection
• Uses VLM-assisted segmentation to exclude non-target objects
• Achieves over 92% success rate in surface segmentation