Researchers at Vanderbilt University have developed an innovative software system that incorporates artificial intelligence with the aim of improving the efficiency of public transportation for people with special needs.
The research, led by Abhishek Dubey, associate professor of computer science and electrical and computer engineering, will be presented in a paper at the International Joint Conference on Artificial Intelligence (IJCAI) in August.
In the paper, Dubay and his team discuss their work with the Chattanooga Area Transit Authority (CARTA) to improve the operation of paratransit services, which began in 2020. Paratransit services are a key component of traditional transit services, providing door-to-door assistance to people who have difficulty using standard transit routes. Federal regulations also require compliance with pick-up and drop-off times for these people.
But like other transit systems across the nation, CARTA is struggling operationally with declining ridership and rising operating costs. To improve efficiency, the team developed a set of data-driven optimization modules incorporating AI to handle the online reservations, day-ahead schedules, and real-time requests that CARTA's paratransit agencies receive on Chattanooga-area routes. Recently, the team also began testing a microtransit version of the system, which it plans to open to the public.
Test results of the smart transit system developed by Dubey and his team showed that detours were significantly reduced and the percentage of trips carrying two or more passengers increased, thereby reducing the total distance that vehicles had to travel, the researchers said. Another improvement is the generation of manifests that show the pickup and drop-off sequences assigned to each vehicle.
“CARTA operators revealed that the algorithm was highly similar to manually generated manifests, and more importantly, it took the algorithm only one minute to generate a manifest, whereas it took the CARTA operators two weeks to manually generate a manifest,” said Dubey, a senior research scientist at the Institute for Software and Integrated Systems (ISIS). “To the best of our knowledge, this study is one of the first to use an open-source algorithmic approach for paratransit optimization.”
David Rogers, a research engineer at ISIS and co-author of the study, said the system prioritizes the needs of dispatchers, drivers and passengers.
“We are in ongoing communication with CARTA representatives to ensure our solutions are practical and beneficial to all stakeholders,” Rogers said.
The system is still in the testing phase, but Philip Pugliese, CARTA's general manager of planning and grants, said the results are promising.
“This project identified several key opportunities to improve our services,” Pugliese said, “and we look forward to continuing to develop and implement them.”
Other authors of the SmartTransit paper are Ayan Mukhopadhyay, Sophie Pavia, Jacob Buckelew and Samir Gupta. Vanderbilt also collaborated with professors Aron Laszka of Pennsylvania State University and Samitha Samaranayake of Cornell University. CARTA's Pugliese was also part of the team.
The project was funded by a grant from the National Science Foundation.
Recently, Dubay and another team developed an AI system that helps improve operations on Nashville’s public transportation network, which won the “Best Paper Award” at the 15th ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS), held May 13-16 in Hong Kong.
/Public Release. This material from the originating organization/author may be out of date and has been edited for clarity, style and length. Mirage.News does not take any organizational stance or position and all views, positions and conclusions expressed here are solely those of the authors. Read the full article here.
