Urban mobility is estimated to contribute 40% of CO2 emissions from road transport worldwide. Given recent urbanization trends, demand is projected to more than double by 2050. This growth has been driven by the emergence of the sharing economy and the ubiquity of smartphones. Ride-sharing services, such as Uber, Lyft, Grab, and Didi, have become immensely successful due to their promise of personal on-demand mobility at any time. Early proponents of ride-sharing suggested that these services would reduce reliance on privately-owned cars, traffic congestion, and carbon emissions. However, recent studies have estimated that a typical ride-sharing trip is less efficient than a personal car trip, mainly due to “deadhead” miles traveled by a passenger-less ride-share vehicle between consecutive hired rides, and that this generates 36-47% more CO2 emissions than an equivalent private car ride. In this project, we tackle the problem of equitable emissions-aware one-on-one and shared ride assignments in a ride-sharing system. The main objective is to equitably allocate an empty available car to single or shared requests, such that the long-term greenhouse gas (GHG) emissions of passenger rides and the passenger-less ``deadhead’’ mileage in-between pick-ups and drop-offs are minimized.
