Mohamed Mokbel
University of Minnesota, MN·Computer Science
Delivery companies, ride-sharing services and navigation apps all assume that the digital map underneath them is correct, but real maps are often wrong or incomplete. Reports cited in this project estimate that map errors cost US delivery companies billions of dollars a year.
- Fields
Computer Science
Engineering
- Topics
map services
map accuracy
trajectory data
- Grants
- 1 known grant, through Aug 2027
What they work on
- Infer missing road and traffic-related map information, beyond basic road layout, by combining vehicle trajectory data with open-source maps to build more complete and accurate maps.
- Characterize the error patterns of map query processors, the software behind routing and nearby-facility searches, and use those patterns to calibrate query results.
- Build software infrastructure that improves the efficiency of map services such as routing and location search by running them over the more accurate, metadata-rich maps.
More about the research
The cost will likely grow as more traffic shifts from casual drivers to delivery and ride-sharing fleets. This project aims to make map services more accurate by improving both the maps themselves and the software that answers questions about them.
Why it matters
More accurate maps and route queries could cut costly delays for delivery companies, ride-sharing services and other transportation and location-based services that handle large numbers of users. Map inaccuracy already costs US delivery firms billions of dollars a year, so even modest gains in map and query accuracy could save fuel, time and money.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Daniel Miller Runfola
William & Mary, VA·Social Science
Automate processing of administrative boundary data for the geoBoundaries platform, including georeferencing printed maps from library archives so historical borders can be placed on modern coordinates.
Michael Levin
University of Minnesota, MN·Engineering
Develop exact solution methods for transportation network design under user equilibrium that combine high-point relaxations, value-function cuts and strong duality cuts to find provably optimal designs faster.
Xuegang Ban
University of Washington, WA·Engineering
Adapt and scale privacy-preserving techniques so that traffic, trajectory, and naturalistic driving data can be shared securely under both centralized and distributed data-sharing models, and evaluate them on real-world transportation datasets.
The school
University of Minnesota: 88 labs on PI Pages, $1.4B a year on research, 722 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.