New York’s famous yellow taxi fleet of over 13,000 Fords, Toyotas, Chevrolets et al. could be replaced by just 3000 vehicles utilising ridesharing.
A new study by the Computer Science and Artificial Intelligence Laboratory (CSAIL) at the Massachusetts Institute of Technology has created an algorithm that uses data taken from three million NYC taxi rides to calculate routes and schedules.
How the algorithm model looks to simpler minds.
Image: MIT CSAIL
Results revealed 3000 four-person cabs could help handle 98 percent of the city’s taxi transport demand and 3000 two-person cabs could accommodate 94 percent. The study also found 2000 10-person vehicles, such as minibuses, could easily cope with 95 percent of the city’s taxi demand.
Team leader Daniela Rus says it’s a first for this kind of transport issue.
“To our knowledge this is the first time 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,” she said in a press release.
“The system is particularly suited to autonomous cars, since it can continuously re-route vehicles based on real-time requests,” she added.
Rus’ system can re-allocate various vehicles when required, preparing
larger capacity vehicles or idle vehicles for high-demand services or areas. Researchers said this lets the system run roughly 20 percent faster than standard ridesharing systems like Uber or Lyft which are inherently a more rigid model.
“Ridesharing services have enormous potential for positive societal impact with respect to congestion, pollution and energy consumption,” Rus concludes, “I think 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.”
The cost to operate with an official NYC-issued taxi medallion rose by 50% between 2009 and 2014 to over US$1 million each. Transportation studies have shown annual congestion costs $160 billion and 7 billion hours of lost time due to being stationary in traffic, plus a further 11.3 billion litres of fuel burned.
Image: Pixabay
