MIT said its Transit Lab will receive $2.1 million from Google.org to build the Public Transit Intelligence Hub (PTIQ), an open-source, AI-orchestrated platform for public transportation agencies. Google.org announced on Sept. 15 that the lab was one of 15 projects selected worldwide in its Impact Challenge: AI for Government Innovation.
What the project is
According to MIT, PTIQ aims to unify transit agencies' real-time monitoring, operations control and passenger communication systems into a single centralized platform, so control center staff can make better-informed, on-the-spot decisions and riders get more immediate and accurate information.
MIT described transit control centers as rooms filled with employees monitoring dozens of radio feeds and screens carrying camera data on stations, vehicle locations, riders, traffic and road conditions, with incoming information fragmented rather than integrated.
The decision support interface for control center staff will integrate predictive models, optimization engines and large language model-based contextual reasoning, MIT said, with final decisions left to transit staff.
Who is involved
Awad Abdelhalim, associate director of the Transit Lab, is co-principal investigator, project director and technical lead. Jinhua Zhao, the MIT Class of 1941 Professor of City and Transportation and head of the Department of Urban Studies and Planning, is the other co-principal investigator.
MIT Lecturer Jim Aloisi, a former secretary of transportation for the Commonwealth of Massachusetts, is program manager and directs the Transit Research Consortium, which will also work on the project. The consortium includes researchers from the Transit Lab, the MIT Mobility Initiative and Northeastern University, where Professor Haris Koutsopoulos takes the lead.
Beyond funding the three-year project, Google.org will provide pro bono support from its own engineers and AI product experts, MIT said.
What the researchers say
"Our goal isn't to automate those decisions, but to make sure the people making them have the best information possible," Abdelhalim said, adding that unifying data from siloed internal systems would improve the experience of riders and the transit workforce.
Zhao said the hard part of integrating AI in transit is not the technology but the institution, citing decades of work with agencies in Washington, D.C., Chicago, London, Boston, Tokyo and Hong Kong. He said PTIQ is designed to ground AI in the institutional reality and behavioral nuances of a transit agency.
Abdelhalim said evaluation of AI models relies heavily on deterministic, objective tasks such as solving mathematical equations or generating code, while real-world operational tasks like delivering transit services are dynamic, multi-stakeholder and lack a single correct answer.
Maggie Johnson, global head of Google.org, said in a statement that AI holds incredible potential to transform public services, "but there is often a gap between promise and practice," and that the program equips the 15 selected organizations with funding and pro bono support from Google's AI experts.
Key facts and where they come from
- Google.org is giving the MIT Transit Lab $2.1 million for the project.
the MIT Transit Lab is a recipient of $2.1 million in funding
- The grant was announced on Sept. 15 and covers one of 15 selected projects.
Google.org announced on Sept. 15 that the MIT Transit Lab is a recipient of $2.1 million in funding — one of only 15 projects selected
- PTIQ will centralize monitoring, operations control and passenger communication.
aims to unify public transportation agencies’ real-time monitoring, operations control, and passenger communication systems into a single centralized AI-orchestrated platform
- The project runs for three years and includes pro bono Google support.
In addition to providing funding for the three-year project, Google.org will provide pro bono support from its own engineers and AI product experts.
- The interface will combine predictive models, optimization engines and LLM-based reasoning.
PTIQ’s decision support interface for control center staff will integrate predictive models, optimization engines, and large language model-based contextual reasoning.
- Decisions remain with transit staff rather than being automated.
But ultimately the decision-making based on that information will be left to transit staff
- Northeastern University researchers take part through the Transit Research Consortium.
comprised of researchers from the Transit Lab, MMI, and Northeastern University, where Professor Haris Koutsopoulos takes the lead.