About

I’m Chien Hua (Brian) Shu, an M.S. student in Computer Science at Purdue University. I work in the Cognitive Robot Autonomy & Learning (CoRAL) Lab with Prof. Ahmed H. Qureshi. I started in August 2026 and expect to finish in May 2028.

What I work on

Robot learning for long-horizon manipulation: tasks where a robot has to get many steps right in a row, not just one grasp. In practice that means imitation learning, post-training vision-language-action (VLA) models, and the benchmarks and evaluation that tell you whether a policy actually works. I tend to build the parts that come before training: the simulated task, the success check, the expert that produces demonstrations, and the pipeline that turns them into a dataset.

Right now that is a dishwasher-loading policy in NVIDIA Isaac Lab. Before Purdue I built the subtask environments and asset pipeline for Fiatlux, a benchmark in which a Unitree G1 humanoid climbs a ladder to replace a light bulb; the paper is under review at ICRA 2027. For the AI for Industry Challenge I wrote a force-monitored expert for cable insertion on a UR5 and trained ACT and Diffusion Policy on its demonstrations.

What I’m looking for

A robotics research internship for Summer 2027. I can work full-time from May 10 to August 20, 2027. If your lab or team works on manipulation, imitation learning or evaluation, I would like to hear from you: brianshu0915@gmail.com.

Where I come from

I came to Purdue from Hawaiʻi. At the University of Hawaiʻi at Mānoa I earned a B.S. in Computer Science and a second degree, a B.B.A. in Finance, finishing both in May 2026. Along the way I wrote Isabelle/HOL proofs as a software verification developer, interned in data science at Hyundai Card in Seoul, taught algorithms for the PANDA programming club, and kept the ACM chapter’s website running.

Outside work: video games, basketball and East Asian languages.