Research conducted by the Singapore-MIT Alliance for Research and Technology (SMART) Future Urban Mobility (FM) research group was recently featured in a Forbes article, titled “Could Robotaxis Replace Private Cars and Public Transit?”
The article discusses the SMART research, which examines how many robotaxis (self-driving, on-demand cars) would be needed to serve a city like Singapore by developing methods that determine fleet size and manage robotaxi routing. The SMART researchers used governmental data on travel patterns, traffic flows, and road networks to simulate a large-scale robotaxi system. The research demonstrates that a large robotaxi system could feasibly handle all transportation needs — including private and public cars, taxis, buses, and trains.
The researchers estimated that the direct cost per mile for robotaxis in Singapore would be about 30 percent less than human-driven cars. This analysis was based on conservative assumptions about technology cost and actual operational data from current car-sharing services such as ZipCar. When considering the value of time saved, the savings increased to almost 50 percent.
MIT professor of aeronautics and astronautics Emilio Frazzoli, lead principal investigator of FM, co-authored the paper, “Toward a Systematic Approach to the Design and Evaluation of Automated Mobility-on-Demand Systems: A Case Study in Singapore,” which was the basis for the Forbes article.
“Our study was more of a thought experiment: we assumed that there were no other means of transportation available," Frazzoli says in the article. "This is clearly unrealistic—but I think it sends a compelling message.”
The message is indeed compelling. The FM analysis showed that 250,000 robotaxis could potentially replace all modes of personal transportation and fulfill the transportation needs of the entire Singapore population. Maximum average wait time would be about 30 minutes during rush hour and lower during other times. By increasing the fleet to 300,000 vehicles, however, maximum wait time could drop to less than 15 minutes. This could result in a significant reduction in traffic congestion, as there are currently about 800,000 passenger vehicles in Singapore.
The research was funded by the Singapore National Research Foundation (NRF) under its Campus for Research Excellence And Technological Enterprise (CREATE) program.