Congratulations to Yue Zhang in her successful Doctoral Thesis Defense!

Yue Zhang arrived at CODES Lab in 2013 after receiving her B.S. at Huazhong University of Science and Technology, a public research university in China. Her area of focus is Systems Engineering, and she grew primarily interested in control and optimization methods for autonomous vehicles, as well as big data analytics with applications to Intelligent Transportation Systems (ITS). To learn more about her, please go to her website.

Dr. Zhang at the end of her Thesis Defense with Professor Christos G. Cassandras.

In her time as a student at Boston University, Dr. Zhang successfully and efficiently finished multiple projects related to ITS. More specifically, she focused on the management of urban intersection considering Connected Automated Vehicles (CAVs) . She published 11 Conference Proceedings papers and 5 journal articles related to ITS (see more). Additional to her academic success, she interned with Oak Ridge National Lab (2015), Facebook (2018) and NVIDIA (2019) where she completed industry-related projects.

During her dissertation defense, she focused on three main areas.

  1. Optimal Control and Coordination of Connected Automated Vehicles at Urban Traffic Intersections
    • She addressed the problem of coordinating online a continuous flow of connected automated vehicles CAVs crossing two adjacent intersections in an urban area. She presented a decentralized optimal control framework whose solution yields the optimal acceleration/deceleration for every vehicle at any time in the sense of minimizing fuel consumption. This solution allows the vehicles to cross the intersections without the use of traffic lights, without creating congestion on the connecting road, and under the hard safety constraint of collision avoidance.
  2. The Street Bump Anomaly Detection and Decision Support System
    • She developed an anomaly detection and decision support system based on data collected through the Street Bump smartphone application. The system is capable of effectively classifying roadway obstacles into predefined categories using machine learning algorithms, as well as identifying actionable ones in need of immediate attention based on a proposed “anomaly index.”  Results on an actual data set provided by the City of Boston illustrate the feasibility and effectiveness of our system in practice.
  3. A Discrete-Event and Hybrid Simulation Framework for Intelligent Transportation System Analysis
    • She introduced a discrete-event and hybrid simulation framework based on SimEvents to study systems at the microscopic level. This framework enables users to apply different control strategies as well as communication protocols for CAVs. It also computes performance analysis of proposed algorithms by authoring customized discrete-event and hybrid systems which may include various designs such as entity flow, graphical programming, and object-oriented programming in MATLAB.

We wish her all the best in her future endeavors.

View all posts