Carpooling apps could reduce traffic 75% in New York City and help with pollution, energy usage: MIT study

Using carpooling options from companies like Uber and Lyft could reduce the number of vehicles on the road in the New York City by a factor of three without significantly impacting travel time, according to a new study from the Massachusetts Institute of Technology (MIT).

The new system found that 3,000 four-passenger cars could service 98% of taxi demand in New York City. Photo credit: Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Laboratory.

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% of taxi demand in New York City, with an average wait time of only 2.7 minutes. The team also found that 95% of demand would be covered by just 2,000 10-person vehicles, compared to the nearly 14,000 taxis that currently operate in NYC, CSAIL said in a statement on Wednesday.

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

Using data from three 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%, Rus reported.

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

Rus wrote an article about the work with former CSAIL postdoctoral associate Javier Alonso-Mora, Cornell University assistant professor Samitha Samaranayake, PhD student Alex Wallar and MIT professor Emilio Frazzoli. The article was published in this week’s issue of the journal Proceedings of the National Academy of Sciences.

While the concept of carpooling has been around for decades, it’s only in the last two years that services such as Uber and Lyft have leveraged smartphone data in a way that has made ride-sharing a cheap, convenient option, CSAIL suggested. However, existing approaches are still limited in their complexity. For example, some ridesharing systems require that user B be on the way for user A, and need to have all the requests submitted before they can create a route.

In contrast, the new system allows requests to be rematched to different vehicles. It can also analyze a range of different types of vehicles to determine, say, where or when a 10-person van would be of the greatest benefit.

CSAIL reported that the system works by first 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 algorithm can then rebalance the remaining idle vehicles by sending them to higher-demand areas.

“A key challenge was to develop a real-time solution that considers the thousands of vehicles and requests at once,” Rus acknowledged. “We can do this in our method because that first step enables us to understand and abstract the road network at a fine level of detail.”

The final product is what she called an “anytime optimal algorithm, which means that it gets better the more times [it is run]” – and she says she’s eager to see how much it can improve with further refinement.

“Ridesharing services have enormous potential for positive societal impact with respect to congestion, pollution and energy consumption,” she concluded. “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.”

According to a 2015 study from global software-as-a-service and data-as-a-service company INRIX and the Texas A&M Transportation Institute, the estimated nationwide annual cost of traffic congestion is US$160 billion, including “seven billion hours of time lost to sitting in traffic and an extra three billion gallons of fuel burned,” MIT said in the statement.