Socially Optimal Personalized Routing with Preference Learning

Project Number


Project Summary

The objective of this project is to improve routing efficiency (e.g., minimize aggregate delay, congestion, or pollution) in real-world transportation networks by proposing personalized socially optimal routes that are likely to be adhered to by the commuters. It is well known that socially optimal routes, which coordinate commuters to achieve a theoretically optimal result, are rarely preferred by drivers who tend to act “selfishly” without regard for the impact of their choices on the experience of the other commuters. The gap between the efficiency of the socially optimal (utopic) solution and the equilibrium (defacto) solution is referred to as the Price of Anarchy. In this project, we will exploit the heterogeneity in driver preferences in terms of the various route characteristics (e.g., path length, mode choice, tolerance level for travel time uncertainty, frequency of accidents, roadworks, or traffic jams) to propose socially optimal routes that are personalized to each driver and thus likely to be adhered to, thereby reducing the Price of Anarchy and improving routing efficiency.

Project Status




Topic Area

Urban Mobility

P.I. Name & Address

Assistant Professor, Industrial & Systems Engineering and Computer Science
University of Southern California
3650 McClintock Ave
Los Angeles, CA 90089
United States


Professor, Daniel J. Epstein Department of Industrial and Systems Engineering; USC Viterbi School of Engineering
University of Southern California
3715 McClintock Ave.
Ethel Percy Andrus Gerontology Center (GER) 206A
Los Angeles, CA 90089-0193
United States


Funding Source


Total Project Cost


Agency ID or Contract Number


Start and End Dates

9/1/2017 – 8/31/2018