Jiaheng Hu 胡佳恒

Welcome! My name is Jiaheng Hu (Jeff). I'm a 1st year Computer Science PhD student at UT-Austin researching at the intersection of Machine Learning and Robotics. I'm fortunate to be advised by Professor Peter Stone and Professor Roberto Martín-Martín. I have a research M.S. degree from the Robotics Institute of Carnegie Mellon Univeristy (thesis), supervised by Professor Howie Choset. I graduated summa cum laude from Columbia University with a B.S. in Computer Science, where I worked with Professor Peter Allen and Professor Tony Dear.

Email  /  LinkedIn  /  Github

Jiaheng Hu
Causal Policy Gradient for Whole-Body Mobile Manipulation
Jiaheng Hu, Peter Stone, Roberto Martín-Martín
RSS, 2023
GLSO: Grammar-guided Latent Space Optimization for Sample-efficient Robot Design Automation
Jiaheng Hu, Julian Whitman, Howie Choset
CoRL, 2022
code / poster
Modular Robot Design Optimization with Generative Adversarial Networks
Jiaheng Hu, Julian Whitman, Matthew Travers, Howie Choset
ICRA, 2022

Large-scale Heterogeneous Multi-Robot Coverage via Domain Decomposition and Generative Allocation
Jiaheng Hu, Howard Coffin, Julian Whitman, Matthew Travers, Howie Choset
WAFR, 2022

Communication Learning via Backpropagation in Discrete Channels with Unknown Noise
Benjamin Freed, Guillaume Sartoretti, Jiaheng Hu, Howie Choset
AAAI, 2020

Teleoperated Robot Grasping in Virtual Reality Spaces
Jiaheng Hu, David Watkins, Peter Allen
NEMS, 2019

Fun Facts
  • I'm a big fan of contract bridge, and have been playing in various tournaments over the years. My most noticeable achievment in bridge is probably the 2nd place in the 2022 NABC 0-10k pairs, and the champion of 2021 GNT flight C.
  • I like sports and music. I play soccer (Hala Madrid!), piano and guitar in my leisure.
  • I enjoy playing video games but haven't had much time to play recently. The two games I enjoy the most are Counter-Strike (CSGO MM rank: LE) and Pokemon (played main series Gen 1 - Gen 9, personal favorite gotta be Leaf Green).
  • I used to play the Chinese card game SGS quite seriously and had a win rate in GuoZhan that is on par with professional streamers, but eventually concluded that this game is too luck-dependant.
Community Service
  • Co-organizing workshop on "Causality for Robotics: Answering the Question of Why", to appear at IROS 2023.
  • Reviewer for AAAI (2022), ICRA (2023), IROS (2023).
  • Grad Level Course TA: Robot Learning (UT-Austin), Artificial Intelligence (Columbia), Computational Robotics (Columbia).

The template of this website is taken from Jon Barron with gratitude: source code.