Artificial Intelligence for Optimizing Integrated Service in Mixed Fleet Transit Operations (Final Scientific Report)
Unknown · 2025
Read Artificial Intelligence for Optimizing Integrated Service in Mixed Fleet Transit Operations (Final Scientific Report) by Unknown (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/doe-osti-2587594-artificial-intelligence-for-optimizing-i.txt.
Description
Dated August 10, 2025, this final scientific report closes Department of Energy award DE-EE0009212. The project applied artificial intelligence to transit agencies that run mixed fleets, with a focus on paratransit: the demand-response service that carries riders who book trips in advance or on the day. Scheduling those trips well is a hard problem that changes hour by hour.
The report tracks three phases. Algorithms cover an offline vehicle routing problem that knows some bookings ahead, a rolling horizon scheduler, and an online scheduling method for requests that arrive live. A simulation environment called Transit-Gym, extended as E-Transit Bench with electric grid simulation, let the team test ideas safely. Other threads improved rider occupancy estimation with neural networks and computer vision, built a paratransit web application, and engaged the community. Later chapters prepare a field test and review go/no-go milestones.
Catalog record
| CREATOR | Unknown |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 392 KB |
| LICENSE | Public Domain |
| RIGHTS | PUBLIC DOMAIN |
| SOURCE | DOE OSTI |