![Illustration of a multi-story indoor house layout used in the CapNav benchmark. The diagram asks: “Can [AGENT] go from the basement foyer to the top floor rest area?” The basement foyer (START) is at the bottom left, and the top floor rest area (END) is at the top right. Colored paths show different possible routes through labeled areas including Garage, First Floor Hallway, and Elevator. Icons on the left represent four agent types: a wheelchair user (allowed, green check), a quadruped robot (allowed, green check), a human (allowed, green check), and a sweeping robot (not allowed, red X). Red X markers and warning labels indicate constraints such as “Cannot go up stairs” and “Cannot operate elevator,” showing how different mobility capabilities affect route feasibility.](/media/projects/images/CapNav-Thumbnail.png.500x300_q85_box-135%2C10%2C2826%2C1627_crop_upscale.png)
CapNav
2025 – Present
Makeability Lab - Home
The Makeability Lab
We are an advanced research lab in Human-AI 🧠🤖 directed by Professor Jon E. Froehlich in the Allen School of Computer Science at the University of Washington.
We specialize in Human-Computer Interaction and applied machine learning for high-impact problems in:
- 🌆 Urban Computing / GeoAI: Building and studying accessible, intelligent cities
- 🥽 Augmented Reality: Enhancing human capabilities
- 🎨 Creativity Support Tools: Creating AI-powered imagination systems
- 🦽 Accessibility: Improving access via Human-AI techniques
To learn more, see our recent projects and our lab handbook.
Interested in working with us? If you are a current UW undergrad, UW MS student, or local Seattle high school student, please apply here. If you are a prospective PhD student, apply to the UW CSE PhD program and mention Professor Froehlich. Before applying, please read the "Prospective PhD Student" section of our lab handbook.
Recent Projects
GeoVisA11y
2024 – Present
BikeButler
2025 – Present
Project Sidewalk
2012 – Present
StreetReaderAI
2024 – Present
AccessParkCV
2023 – Present
RampNet
2025 – Present
SonoCraftAR
2025 – Present
Recent Papers
CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation
CVPR 2026 To Appear
GeoVisA11y: An AI-based Geovisualization Question-Answering System for Screen-Reader Users
CHI 2026
|
Best Paper Award
BikeButler: A Personalized, Context-sensitive Bike Routing Tool using Open Data and VLM-based Analyses of Street View Imagery
CHI 2026
Towards Human-AI Accessibility Mapping in India: VLM-Guided Annotations and POI-Centric Analysis in Chandigarh
AI4UP 2026
Street View for Whom? An Initial Examination of Google Street View’s Urban Coverage and Socioeconomic Indicators in the US
GeoIndustry 2025
Making Street View Accessible Using Context-Aware Multimodal AI: A Demo of StreetReaderAI
ASSETS 2025
Recent Videos
Recent Talks
BikeButler: Creating and Previewing Personalized, Context-Sensitive Bicycle Routes
Apr 17, 2026 | CHI
Barcelona, Spain
"You Don't Do HCI": Stories of Persistence, Pushback, and Pursuit
Apr 14, 2026 | SIGCHI Societal Impact Award Talk
Barcelona, Spain
"Where Can I Park?" Understanding Human Perspectives and Scalably Detecting Disability Parking from Aerial Imagery
Oct 26, 2025 | ASSETS
Denver, CO
RampNet: A Two-Stage Pipeline for Bootstrapping Curb Ramp Detection in Streetscape Images from Open Government Metadata
Oct 20, 2025 | ICCV CV4A11y Workshop
Honolulu, Hawaiʻi
John O'Meara, Jared Hwang, Zeyu Wang, Mikey Saugstad, Jon E. Froehlich
SonoCraftAR: Towards Supporting Personalized Authoring of Sound-Reactive AR Interfaces by Deaf and Hard of Hearing Users
Oct 08, 2025 | IDEATExR
Daejeon, South Korea
Jaewook Lee, Davin Win Kyi, Leejun Kim, Jenny Peng, Gagyeom Lim, Jeremy Zhengqi Huang, Dhruv Jain, Jon E. Froehlich
FlyMeThrough: Human-AI Collaborative 3D Indoor Mapping with Commodity Drones
Sep 30, 2025 | UIST 2025
Busan, South Korea
StreetReaderAI: Making Street View Accessible Using Context-Aware Multimodal AI
Sep 28, 2025 | UIST
Busan, Korea
Jon E. Froehlich, Alexander J. Fiannaca, Nimer Jaber, Victor Tsaran, Shaun K. Kane
Sponsors
Makeability Lab research is made possible by the generous support of our sponsors. Our research findings, opinions, and/or recommendations may not reflect their views.
