How 3,000 Ubers Could Replace Taxis and Cut New York Traffic by 300 Percent

uber new york cab replace MIT
A figure from the MIT study showing how 30 vehicles (circle) would deal with 90 requests (star). MIT CSAIL

An algorithm implemented into ride-sharing apps like Uber in New York could reduce pollution and cut traffic by 300 percent—so long as people are willing to carpool.

Around 13,500 yellow cabs are licensed in New York, although 98 percent of the city's taxi demand could be met with just 3,000 four-person cars using the algorithm, researchers found.

The first-of-its-kind study, published in the journal Proceedings of the National Academy of the Sciences, was carried out by MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL).

"Instead of transporting people one at a time, drivers could transport two to four people at once, resulting in fewer trips, in less time, to make the same amount of money," said Daniela Rus, director of MIT's CSAIL.

"A system like this could allow drivers to work shorter shifts, while also creating less traffic, cleaner air and shorter, less stressful commutes."

The carpooling system works by creating a graph of all of the requests and all of the vehicles. It then calculates all of the possible trip combinations and computes the best way to assign the requests to the vehicles.

The algorithm is then able to redistribute any remaining idle vehicles to higher-demand areas. Rus called it an "anytime optimal algorithm," as it gets better the more times it is run.

"To our knowledge, this is the first time that scientists have been able to experimentally quantify the trade-off between fleet size, capacity, waiting time, travel delay, and operational costs for a range of vehicles, from taxis to vans and shuttles," Rus said.

"What's more, the system is particularly suited to autonomous cars, since it can continuously reroute vehicles based on real-time requests."