CISE Seminar: October 18, 2019 – Cathy Wu, Massachusetts Institute of Technology (MIT)

8 St. Mary’s Street, PHO 203
3:00pm – 4:00pm

Cathy Wu
Massachusetts Institute of Technology

Integrating Autonomy into Urban Systems

How will self-driving cars change urban mobility? Leveraging and advancing model-free deep reinforcement learning and control theory, the talk demonstrates the ability of these techniques to provide insights by discovering emergent behaviors in complex transportation dynamical systems. The work quantifies the dramatic potential impact of a small fraction of automated vehicles (5-10%) on low-level traffic flow dynamics, such as congestion, on a variety of important traffic contexts and even achieves near-optimal performance in certain situations. The talk further discusses early work and open challenges in machine learning and optimization for informing decision making in future urban systems, from vehicle design to transportation planning to the design of future mixed autonomy systems.

Cathy Wu is an Assistant Professor at MIT in LIDS, CEE, and IDSS. She holds a PhD from UC Berkeley, and B.S. and M.Eng from MIT, all in EECS, and recently completed a Postdoc at Microsoft Research AI. She works at the intersection of machine learning, optimization, autonomy, and urban systems. Her work has been acknowledged by several awards, including the 2019 Microsoft Location Summit Hall of Fame, 2018 Milton Pikarsky Memorial Dissertation Award, the 2016 IEEE ITSC Best Paper Award, and fellowships from NSF, Berkeley Chancellor, NDSEG, and Dwight David Eisenhower.

Faculty Host: Yannis Paschalidis
Student Host: Noushin Mehdipour