Learning for Robust Control and Optimization: Efficiency and Safety of Autonomous Transportation Systems

Learning for Robust Control & Optimization: Efficiency & Safety of Autonomous Transportation Systems

November 1, 2019

Fei MaoUniversity of Connecticut's Fei Mao presented Learning for Robust Control and Optimization: Efficiency and Safety of Autonomous Transportation Systems at 4 p.m. Nov. 1 at the ITS Transportation Seminar in 290 Hearst Memorial Mining Building.

Abstract

Ubiquitous sensing in smart cities enables large-scale multi-source data collected in real-time, poses several challenges and requires a paradigm-shift to data-driven cyber-physical systems (CPSs) that integrates optimization, control and machine learning. For instance, how to capture the complexity and analyze the dynamic interplay between urban-scale phenomena from data, and take actions to improve service efficiency and safety, is still a challenging problem in transportation systems. In this talk, we first present a data-driven dynamic robust resource allocation framework for autonomous ride-sharing and carpool systems, matching vehicle supply towards both current and predicted future demand. With spatial-temporal uncertainty of demand prediction, we then prove and develop computationally tractable methods that provide probabilistic guarantees for the system’s worst-case and expected performance. A dynamic pricing model is also designed for travel time reliability during peak hours. We show that the performance of the ride-sharing system is improved based on world taxi operational data. Lastly, recent work about an information sharing and decision-making framework considering safety and efficiency of connected autonomous vehicles is introduced.

Bio

Fei Miao is an Assistant Professor of the Department of Computer Science & Engineering, and she is also affiliated to the Department of Electrical & Computer Engineering, University of Connecticut since 2017. Her research interests lie in the intersection of control, optimization, and machine learning with application in cyber-physical systems efficiency, safety, and security. She has received a couple of awards from NSF, including S&AS, CPS, and S&CC programs. She received a Ph.D. degree, and the “Charles Hallac and Sarah Keil Wolf Award for Best Doctoral Dissertation” in Electrical and Systems Engineering, with a dual Master degree in Statistics at Wharton School from the University of Pennsylvania. She received a B.S. degree majoring in Automation from Shanghai Jiao Tong University. She was a postdoc researcher at the GRASP Lab and the PRECISE Lab of UPenn, from September 2016 to August 2017. She was a Best Paper Award Finalist at the 6th ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS) in 2015.