Ride-sharing could reduce congestion, says US study

A new Massachusetts Institute of Technology (MIT) study suggests that using carpooling options from companies like Uber and Lyft could reduce the number of vehicles on the road by a factor of three without significantly impacting travel time. Led by Professor Daniela Rus, director of MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), researchers developed an algorithm that found 3,000 four-passenger cars could serve 98 per cent of taxi demand in New York City, with an average wait-tim
January 6, 2017 Read time: 2 mins
A new 2024 Massachusetts Institute of Technology (MIT) study suggests that using carpooling options from companies like Uber and Lyft could reduce the number of vehicles on the road by a factor of three without significantly impacting travel time.

Led by Professor Daniela Rus, director of MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), researchers developed an algorithm that found 3,000 four-passenger cars could serve 98 per cent of taxi demand in New York City, with an average wait-time of only 2.7 minutes.

The team also found that 95 per cent of demand would be covered by just 2,000 10-person vehicles, compared to the nearly 14,000 taxis that currently operate in New York City.

Using data from 3 million taxi rides, the new algorithm works in real-time to reroute cars based on incoming requests, and can also proactively send idle cars to areas with high demand, a step that speeds up service 20 percent, according to Rus.

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

For more information on companies in this article

Related Content

  • Survey finds drivers trust traditional car makers more than tech companies to build AVs
    May 23, 2017
    Research by connected car services and location analytics provider Inrix indicates that consumers are more likely to trust a traditional car maker than a leading technology company when it comes to making autonomous vehicles (AVs).
    Read More
  • How C/AVs could serve rural communities
    July 23, 2019
    In Ireland, there is low population density and a lot of rain – which can make last-mile journeys a trial. Orla O’Halloran at Arup has some thoughts on how C/AVs could serve rural communities Connected and autonomous vehicles (C/AVs) have the potential to be a vital link for people in rural communities, as part of a wider Mobility as a Service (MaaS) solution. That is the view of Orla O’Halloran, intelligent mobility consultant at Arup. She believes that MaaS needs to be considered in conjunction with ot
    Read More
  • Researchers helping to reduce New Zealand’s congestion
    April 7, 2015
    Researchers at the University of Canterbury, New Zealand claim the impact of congestion in the country’s major cities could soon be greatly reduced. They are exploring how the movement of vehicles on New Zealand’s city roads can be more efficiently managed after accidents and breakdowns. University of Canterbury transport engineer Professor Alan Nicholson says their research shows drivers tend to divert off the motorway in large numbers only after a slow queue becomes visible. Along with Dr Glen Koorey and
    Read More
  • Auto safety initiative seeks to reduce driver errors
    December 2, 2013
    A push by the US National Highway Traffic Safety Administration to use technology to reduce traffic fatalities aims to keep drunk drivers off the roads by using in-vehicle technology that immobilises their cars. They are pushing for systems that prevent drivers from starting their cars, help cars avoid collisions and prevent vehicles from starting if the occupants don’t wear seat belts. "Ninety per cent of all crashes have an element of human error," NHTSA administrator David Strickland said. "We really
    Read More

Highlighted Content