Projects
A digital twin infrastructure calibrated on real-world corridor data
Imagine you’re driving on a congested freeway and find yourself caught in stop-and-go waves. These seemingly spontaneous traffic patterns—where vehicles repeatedly speed up and slow down—are surpri...
Jul 01, 2024
I-24 MOTION: A new instrument for traffic science
The Tennessee Department of Transportation’s I-24 Mobility Technology Interstate Observation Network (MOTION) is a four-mile section of I-24 in the Nashville-Davidson County Metropolitan area with ...
Nov 12, 2023
Real-time multi-object tracking on streaming data: a graph algorithm that actualy scales
Multi-object tracking (MOT) is a well-established problem in computer vision. However, the emerging challenge for modern traffic management lies in scaling these algorithms to operate in real-time....
Sep 12, 2023
Customized adaptive cruise control eases phantom jams: a massive field experiment
This Congestion Impacts Reduction via CAV-in-the-loop Lagrangian Energy Smoothing (CIRCLES) project aims to reduce instabilities in traffic flow, called “phantom jams,” that cause congestion and wa...
Nov 22, 2022
Rectify vehicle trajectory data from video tracking algorithms
Vehicle trajectory data has received increasing research attention over the past decades. With the technological sensing improvements such as high-resolution video cameras, in-vehicle radars and li...
Aug 05, 2022
Personalized ACC in a digital twin framework
Advanced driver-assistance systems (ADAS) have matured over the past few decades with the dedication to enhance user experience and gain a wider market penetration. However, personalization compone...
May 11, 2021
Learning adaptive cruise control driving behavior from on-board radar units
This project explores methods for model parameter estimation on a car-following model using data collected from Adaptive Cruise Control (ACC) enabled vehicles. The proposed methods are batch method...
Jun 14, 2019
I made an app with vibe coding
Summer offers a rare window to explore the “fun” ideas that often get pushed aside during the academic year. With the growing popular vibe coding tools and remarkably capable AI agents, I was drawn...
SQL webapp dashboard Jun 04, 2025
I-24 MOTION: A new instrument for traffic science
The Tennessee Department of Transportation’s I-24 Mobility Technology Interstate Observation Network (MOTION) is a four-mile section of I-24 in the Nashville-Davidson County Metropolitan area with ...
Nov 12, 2023
Real-time multi-object tracking on streaming data: a graph algorithm that actualy scales
Multi-object tracking (MOT) is a well-established problem in computer vision. However, the emerging challenge for modern traffic management lies in scaling these algorithms to operate in real-time....
Sep 12, 2023
I made an app with vibe coding
Summer offers a rare window to explore the “fun” ideas that often get pushed aside during the academic year. With the growing popular vibe coding tools and remarkably capable AI agents, I was drawn...
SQL webapp dashboard Jun 04, 2025
A digital twin infrastructure calibrated on real-world corridor data
Imagine you’re driving on a congested freeway and find yourself caught in stop-and-go waves. These seemingly spontaneous traffic patterns—where vehicles repeatedly speed up and slow down—are surpri...
Jul 01, 2024
I-24 MOTION: A new instrument for traffic science
The Tennessee Department of Transportation’s I-24 Mobility Technology Interstate Observation Network (MOTION) is a four-mile section of I-24 in the Nashville-Davidson County Metropolitan area with ...
Nov 12, 2023
Real-time multi-object tracking on streaming data: a graph algorithm that actualy scales
Multi-object tracking (MOT) is a well-established problem in computer vision. However, the emerging challenge for modern traffic management lies in scaling these algorithms to operate in real-time....
Sep 12, 2023
Customized adaptive cruise control eases phantom jams: a massive field experiment
This Congestion Impacts Reduction via CAV-in-the-loop Lagrangian Energy Smoothing (CIRCLES) project aims to reduce instabilities in traffic flow, called “phantom jams,” that cause congestion and wa...
Nov 22, 2022
Rectify vehicle trajectory data from video tracking algorithms
Vehicle trajectory data has received increasing research attention over the past decades. With the technological sensing improvements such as high-resolution video cameras, in-vehicle radars and li...
Aug 05, 2022
Estimation for heterogeneous traffic states
This work explores the state estimation problem for heterogeneous traffic (a multiclass flow composed of vehicles with distinct sizes and driving behaviours) usingparticle filtering (PF) approaches...
Nov 18, 2021
Personalized ACC in a digital twin framework
Advanced driver-assistance systems (ADAS) have matured over the past few decades with the dedication to enhance user experience and gain a wider market penetration. However, personalization compone...
May 11, 2021
Identifiability of car-following dynamics
The advancement of in-vehicle sensors provides abundant datasets to estimate parameters of car-following models that describe driver behaviors. The question of parameter identifiability of such mod...
Jun 18, 2020
Large spatial-temporal data processing via tensor factorization
The US Environmental Protection Agency identifies that urban heat islands can negatively impact a community’s environment and quality of life. Using low cost urban sensing networks, it is possible ...
Jun 14, 2020
Learning adaptive cruise control driving behavior from on-board radar units
This project explores methods for model parameter estimation on a car-following model using data collected from Adaptive Cruise Control (ACC) enabled vehicles. The proposed methods are batch method...
Jun 14, 2019
Bridges to Prosperity (now Engineers in Action Bridge Program)
In the summer of 2016, Vivian Wong and I tagged along with a group of engineers from the University of Toronto to travel to Guatemala for a bridge-build project. Upon our turn, we co-founded a stud...
Feb 04, 2018