Accessibility Scout: Personalized Accessibility Scans of Built Environments

2025-07-30

AI Summary

Traditional accessibility assessment methods suffer from insufficient personalization and poor scalability. Method: This study proposes a personalized built-environment accessibility evaluation framework that synergistically integrates large language models (LLMs) with visual understanding. Leveraging human-AI collaboration, the framework dynamically incorporates users’ specific mobility capabilities, preferences, and contextual concerns into image semantic analysis—thereby transcending the rigid constraints of universal standards such as the ADA and enabling adaptive, context-aware accessibility diagnostics. Contribution/Results: Technical evaluation on 500 images and a user study with 10 participants with disabilities demonstrate that the system significantly outperforms existing automated approaches in identifying diverse individual needs, achieving higher accuracy and user satisfaction. The framework establishes a novel paradigm for scalable, human-centered intelligent accessibility assessment.

Technology Category

• Humans and AI: AI for Accessibility
• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Language and Vision

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Assessing the accessibility of unfamiliar built environments is critical for people with disabilities. However, manual assessments, performed by users or their personal health professionals, are laborious and unscalable, while automatic machine learning methods often neglect an individual user's unique needs. Recent advances in Large Language Models (LLMs) enable novel approaches to this problem, balancing personalization with scalability to enable more adaptive and context-aware assessments of accessibility. We present Accessibility Scout, an LLM-based accessibility scanning system that identifies accessibility concerns from photos of built environments. With use, Accessibility Scout becomes an increasingly capable "accessibility scout", tailoring accessibility scans to an individual's mobility level, preferences, and specific environmental interests through collaborative Human-AI assessments. We present findings from three studies: a formative study with six participants to inform the design of Accessibility Scout, a technical evaluation of 500 images of built environments, and a user study with 10 participants of varying mobility. Results from our technical evaluation and user study show that Accessibility Scout can generate personalized accessibility scans that extend beyond traditional ADA considerations. Finally, we conclude with a discussion on the implications of our work and future steps for building more scalable and personalized accessibility assessments of the physical world.

Problem

• Personalized accessibility scans for built environments
• Balancing personalization and scalability in assessments
• Extending beyond traditional ADA considerations

Innovation

• LLM-based system for accessibility scans
• Personalized scans using user mobility data
• Combines Human-AI for adaptive assessments