Overview
This webinar focused on opportunities for traffic management systems (TMSs) to use artificial intelligence/machine learning (AI/ML).
With exponential availability and growth in data generation capabilities, advancements in data storage/advanced computing techniques (e.g., cloud storage, edge computing), and innovations in algorithmic techniques (e.g., deep learning, machine vision, improved model accuracy), there is a great potential for AI/ML to enhance the safety, mobility, productivity, and operational efficiency of our surface transportation systems including TMSs. This webinar covers how to:
- Identify potential day-to-day operational functions or tasks performed by TMS operators, which may be conducted or improved by using AI/ML (e.g., automate retrieving of video recordings and responding to information requests)
- Assess challenges or issues (e.g., ability to modify software, existence of or ability to modify algorithms that are not proprietary, ability to monitor and evaluate the value added versus how functions and actions are currently performed) when considering potential opportunities to assess the capability, resources, and potential for AI/ML to improve or perform specific TMS functions or actions
Speakers included:
- Raj Ponnaluri, TSMO Practical Lead, WSP
- John Hibbard, Deputy Chief Engineer, Georgia DOT
- Jianming Ma, Director, Traffic Management Section, Texas DOT
- Athena Hutchins, Executive Director, Niagara International Transportation Technology Coalition (NITTEC
This webinar is part of an ongoing series focused on emerging TMS topics. It is hosted by the Traffic Management Center Pooled Fund Study and co-sponsored by the NOCoE and FHWA.
Raj Ponnaluri, WSP |
John Hibbard, Georgia DOT |
Jianming Ma, Texas DOT |
Athena Hutchins, NITTEC |