According to transportation studies, a loss of approximately $160bn is incurred due to traffic congestion that includes seven billion hours of time lost to sitting in traffic and an extra three billion gallons of fuel burned.

A study conducted by the Massachusetts Institute of Technology (MIT) suggest that carpooling options offered by transportation companies such as Uber and Lyft can address the issue as it reduces the number vehicles on the road.

MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) director Daniela Rus along with other researchers has developed an algorithm that found 3,000 four-passenger cars can address 98% of taxi demand in New York City, with an average wait-time of only 2.7 minutes.

Rus said: “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.

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

The research team has also found that about 95% 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.

Based on the three million taxi rides data, 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 .

Rus further added: “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.

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

"The system is particularly suited to autonomous cars, since it can continuously reroute vehicles based on real-time requests."

The system creates a graph based on the all of the requests and all of the vehicles.

It then creates a second graph with all possible trip combinations, and uses a method called ‘integer linear programming’ to compute the best assignment of vehicles to trips.

After the assignment of the cars, the algorithm will rebalance the remaining idle vehicles by sending them to higher-demand areas.

Image: A map showing carpooling options. Photo: courtesy of Massachusetts Institute of Technology researchers.