Taxi-sharing services could cut congestion, study shows

Carpooling apps could significantly reduce congestion and pollution in cities, according to a new study.

Researchers at the Massachusetts Institute of Technology (MIT) found that ride-sharing with companies like Uber and Lyft could reduce the number of taxis in New York City from almost 14,000 to just 3,000.

Based on data from 3 million taxi rides, the researchers developed an algorithm which showed that 3,000 four-passenger cars could serve 98% of taxi demand in New York City, with an average wait-time of only 2.7 minutes. Alternatively, 95% of demand would be covered by just 2,000 10-person vehicles.

“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,” explained Professor Daniela Rus, director of MIT’s Computer Science and Artificial Intelligence Laboratory. “A system like this could allow drivers to work shorter shifts, while also creating less traffic, cleaner air, and shorter, less stressful commutes.”

The new algorithm reroutes cars based on incoming requests, and can also proactively send idle cars to areas with high demand, speeding up service.

According to MIT, the system works by creating a graph of all of the requests and all of the vehicles. It then creates a second graph of all possible trip combinations, and uses a method called “integer linear programming” to compute the best assignment of vehicles to trips.

After cars are assigned, the remaining idle vehicles are directed to higher-demand areas.

“Ride-sharing services have enormous potential for positive societal impact with respect to congestion, pollution and energy consumption,” Rus said. “It’s important that we as researchers do everything we can to explore ways to make these transportation systems as efficient and reliable as possible.”

“Huge volumes of travel data are already being gathered from mobiles and sensors in and around cities. The  next biggest developments in urban transport will come from using data analytics to make better informed decisions, which could potentially identify new business models. It’s fantastic to see how advances in carpooling apps are reducing congestion and pollution and creating benefits for both drivers as well as commuters.” Tom Sharpe, Associate.

Sign up to our newsletter

Meet our experts