"Does the cafe entrance look accessible? Where is the door?" Towards Geospatial AI Agents for Visual Inquiries

Jon E. Froehlich, Jared Hwang, Zeyu Wang, John S. O'Meara, Xia Su, William Huang, Yang Zhang, Alexander J. Fiannaca, Philip Nelson, Shaun Kane

Keywords: MLLM, AI Agents, Accessibility, Geospatial, Question-Answering, Geo-Visual Agents

TL;DR: We introduce our vision for Geo-Visual Agents—multimodal AI agents capable of understanding and responding to nuanced visual-spatial inquiries about the world.

Abstract: Interactive digital maps have revolutionized how people travel and learn about the world; however, they rely on pre-existing structured data in GIS databases (\textit{e.g.,} road networks, POI indices), limiting their ability to address geo-visual questions related to \textit{what} the world looks like. We introduce our vision for \textit{Geo-Visual Agents}—multimodal AI agents capable of understanding and responding to nuanced visual-spatial inquiries about the world by analyzing large-scale repositories of geospatial images, including streetscapes (e.g., Google Street View), place-based photos (e.g., TripAdvisor, Yelp), and aerial imagery (e.g., satellite photos) combined with traditional GIS data sources. We define our vision, describe sensing and interaction approaches, provide three exemplars, and enumerate key challenges and opportunities for future work.

Submission Number: 15