A profile picture of hsuchieh.

Hsu-Chieh Hu

Introduction

I am a senior research scientist at Rapid Flow Technologies, a CMU spinoff that is working on commercializing Surtrac adaptive traffic signal control technology developed in the Robotics Institute. I completed my Ph.D. from Electrical and Computer Engineering Department and M.S. in Machine Learning from Machine Learning Department at Carnegie Mellon, working on planning, reinforcement learning and optimization to solve real-world coordination problems (including the applications of transportation and wireless networks) under the supervision of Stephen F. Smith of Robotics Institute. Prior to that, I have worked in communication industry for three years as a software engineer. [CV]

Contact

My first name (no dash) at RAPIDFLOWTECH dot COM

Research

See Publications for my published works. This section is a brief description of my research.

  1. Coordination for Schedule-Driven Traffic Control

A composite approach is proposed to real-time traffic control that uses sensed information on queue lengths to influence scheduling decisions and gracefully shift the signal control strategy to queue management in high volume/high congestion settings. [project website]

  1. DAPRA Grand Challenge: The Spectrum Collaboration Challenge

The DARPA Spectrum Collaboration Challenge (SC2) is the first-of-its-kind collaborative machine-learning competition to overcome scarcity in the radio frequency (RF) spectrum. Today, spectrum is managed by dividing it into rigid, exclusively licensed bands. This human-driven process is not adaptive to the dynamics of supply and demand, and thus cannot exploit the full potential capacity of the spectrum. [project website]

  1. Schedule-Driven Demand Shifting

We consider a setting where drivers have flexibility in the times that they can arrive and depart from the office, and all drivers must pass through a congestion bottleneck (e.g., a tunnel or a bridge).The goal is to produce a departure time for each driver that minimizes congestion at the bottleneck.

  1. V-TCP: A New TCP Protocol for Vehicles

This project is to design a new TCP protocol for vehicles to support QoS of high throughput transmission.

Publications

Teaching

This Page

Minimalism with GitHub-like CSS (licensed under MIT).