The Robotability Score
Enabling Harmonious Robot Navigation on Urban Streets
@ CHI '25: ACM Conference on Human Factors in Computing Systems
Project Team
What is The Robotability Score?
The Robotability Score (R) is a novel metric that quantifies how suitable urban environments are for autonomous robot navigation. Through expert interviews and surveys, we've developed a standardized framework for evaluating urban landscapes to reduce uncertainty in robot deployment while respecting established mobility patterns.
Streets with high Robotability are both more navigable for robots and less disruptive to pedestrians. We've constructed a proof-of-concept Robotability Score for New York City using a wealth of open datasets from NYC OpenData, and inferred pedestrian distributions from a dataset of 8 million dashcam images taken around the city in late 2023.
Explore the spatial distribution of Robotability Scores across New York City from our proof-of-concept deployment.
Key Features
Our findings reveal that these factors collectively account for 48% of the total Robotability Score. Areas with highest R are 4.3 times more "robotable" than areas with lowest R.
Complete Indicator List
Each indicator is paired with a sample set of weights to show how the Robotability Score might change under different indicator values.
Sidewalk width
(e.g., 0 = narrow, 1 = wide)
Pedestrian density
(e.g., 0 = high density, 1 = low density)
Density of street furniture (e.g. garbage, poles)
(e.g., 0 = high density, 1 = moderate density, 2 = low density, 3 = no furniture)
Sidewalk / Surface roughness
(e.g., 0 = gravel, 1 = cobblestones, 2 = smooth asphalt)
Surface condition
(e.g., 0 = potholes, 1 = major cracks, 2 = minor cracks, 3 = smooth)
Wireless communication infrastructure
(e.g., 0 = no infrastructure, 1 = basic Wi-Fi, 2 = 5G, IoT)
Slope gradient
(e.g., 0 = high slope, 1 = no slope)
Presence of charging stations
(e.g., 0 = no charging stations nearby, 1 = multiple charging stations in proximity)
Local attitudes towards robots
(e.g., 0 = highly negative, 1 = somewhat negative, 2 = neutral, 3 = somewhat positive, 4 = highly positive)
Curb ramp availability
(e.g., 0 = no curb ramps, 1 = curb ramps at some intersections, 2 = curb ramps at most intersections, 3 = curb ramps with tactile paving)
Weather conditions
(e.g., 0 = ice, 1 = snow, 2 = puddles, 3 = leaves, 4 = clear)
Crowd dynamics
(e.g., 0 = emergency, 1 = commuting, 2 = shopping, 3 = leisure)
Traffic management
(e.g., 0 = no system, 1 = basic signage, 2 = street lights, 3 = advanced traffic control)
Surveillance coverage (CCTV)
(e.g., 0 = no coverage, 1 = low coverage, 2 = moderate coverage, 3 = high coverage)
Zoning laws and regulation
(e.g., 0 = no regulations, 1 = moderate stringency, 2 = high stringency)
Bike lane availability
(e.g., 0 = no bike lanes, 1 = bike lanes on most roads, 2 = separated bike lanes on all roads)
Street lighting
(e.g., 0 = no lighting, 1 = excellent lighting)
Existence of shade
(e.g., 0 = no shade, 1 = extensive shade)
GPS signal strength
(e.g., 0 = no signal, 1 = very strong signal)
Pedestrian flow
(e.g., 0 = very high flow, 1 = very low flow)
Bicycle traffic
(e.g., 0 = very high traffic, 1 = very low traffic)
Vehicle traffic
(e.g., 0 = very high traffic, 1 = very low traffic)
Existence of detailed digital maps
(e.g., 0 = no digital maps, 1 = highly detailed maps)
Intersection safety
(e.g., 0 = no infrastructure, 1 = basic crosswalks, 2 = zebra crossings with signals, 3 = advanced intersection management)
Paper Citation
If you use our work in your research, please cite our paper:
@inproceedings{10.1145/3706598.3714009,
author = {Franchi, Matthew and Parreira, Maria Teresa and Bu, Fanjun and Ju, Wendy},
title = {The Robotability Score: Enabling Harmonious Robot Navigation on Urban Streets},
year = {2025},
isbn = {9798400713941},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3706598.3714009},
doi = {10.1145/3706598.3714009},
booktitle = {Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems},
articleno = {737},
numpages = {17},
series = {CHI '25}
}