Omar ElSamadisy presents 'Microscopic vs. Macroscopic Freeway Efficiency Optimization using Reinforcement Learning'

Freeways are currently suffering from increasing congestion that restricts socioeconomic activities and degrades the available infrastructure capacity, especially when it is most needed -  during rush hours. This talk will present an overview of ongoing research on solving the congestion problem by optimizing the freeway efficiency both microscopically by developing a safe, efficient, and comfort car-following model for Autonomous Vehicles (AVs), and macroscopically by optimizing flow on freeways to prevent congestion and preserve safe and efficient flows at bottlenecks. The controllers are designed using the latest Artificial Intelligence (AI) methods and techniques.

About the speaker

Omar ElSamadisy is a fifth-year PhD candidate at the Civil & Mineral Engineering Department at U of T, working under the supervision of Professor Baher Abdulhai. His main research goal is to develop microscopic as well as macroscopic control strategies to prevent congestion and preserve safe and efficient flows on freeways using AI methods. He holds a master's degree in Communications Engineering with a focus on channel access in wireless communications from the Arab Academy for Science, Technology and Maritime Transport (Alexandria, Egypt), the university where he also completed his bachelor’s degree in electronics and communications engineering.

Presented by University of Toronto ITE Student Chapter, UT-ITE. Free. All are welcome.

If any specific accommodations are needed, please contact ite@studentorg.utoronto.ca. Requests should be made as early as possible.