Henry Liao

I'm a Master's student at the Robotics Institute, part of the School of Computer Science at Carnegie Mellon University. I study deployable control algorithms, and am currently advised by John Dolan and mentored by Maitham Al-Sunni .

I completed my BS in Computer Science at the Georgia Institute of Technology in 2025. During my undergraduate studies, I co-founded the game AI organization & competition ByteFight under the mentorship of Abrahim Ladha.

During my studies I also worked as a TA for 16384 Robot Kinematics and Dynamics under Jeff Ichnowski, 16299 Introduction to Feedback Control Systems under Chris Atkeson, and CS2200 Systems and Networking under Daniel Forsyth.

Email  /  Google Scholar  /  GitHub  /  LinkedIn

Research

LBA-CBF: Rapidly Adaptive Safety Filters via Parallel Dynamics Inference

Application of the LLA framework to CBFs for provable safety with minimal conservatism. Ran experiments based off of previous embedded LLA-MPC work.

LLA-MPC on Embedded Hardware: Rapid Adaptive Control with Thousands of Parallel Models

Implemented the LLA-MPC framework for rapid adaptive system identification on embedded hardware. Includes a modular design with interchangeable vehicle dynamics and integrators. Validated on an F1Tenth with Fiala Tire dynamics.

Integrating Adversarial Competitions in University Programming Education: An Experience Report

We implemented the ByteFight competition as a live, scalable service for use as part of an existing graduate computer science course.

Other Projects

ByteFight @ GT

Founded the game AI organization and competition ByteFight @ GT alongide Tyler Kwok and Abrahim Ladha. The ByteFight platform has since been used in multiple classes as part of Georgia Tech’s computer science curriculum to teach AI development to students.

MIT Battlecode 2023

I lead a team in competing in the month-long game AI competition MIT Battlecode. Finished 7th-8th in finals.

Design and source code from Leonid Keselman's website, which is a fork of Jon Barron's website.