New York City’s 13,000-plus taxis could be replaced by a fleet of just 3,000 ride-sharing cars, suggests research published this week by MIT’s Computer Science and Artificial Intelligence Laboratory.
Using public data from NYC taxi rides published by the University of Illinois to develop the algorithm, the CSAIL researchers determined that 3,000 four-person vehicles could meet 98% of the city’s voracious taxu demand with an average wait time of less than three minutes.
“Instead of transporting people one at a time, drivers could transport two to four people at once, results in fewer trips, in less time, to make the same amount of money,” says professor Daniela Rus, who led the research. “A system like this could allow drivers to work shorter shifts, while also creating less traffic, cleaner air and shorter, less stressful commutes.”
The researchers also found that 95% of taxi demand could be covered by 2,000 10-person vehicles.
“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,” says Rus. “What’s more, the system is particularly suited to autonomous cars, since it can continuously reroute vehicles based on real-time requests.”