Huaze Liu 刘铧泽

Hi! I am a senior undergraduate student at Harvey Mudd College majoring in Computer Science and Mathematics, with a social science concentration in Economics.

I work on robotics control, dexterous manipulation, and reinforcement learning. Broadly speaking, I'm interested in how systems perceive and acts in the real world robustly. At Harvey Mudd College, I closely worked with Prof. Adyasha Mohanty on sensor fusion for trustworthy autonomous navigation. I also worked on humanoid robot catching with Kehlani Fay and Arth Shukla, under the supervision of Prof. Michael Tolley and Prof. Hao Su at UC San Diego in 2025.

Email  /  Github  /  Linkedin  /  Google Scholar

My research focuses on:

• Dexterous Manipulation — integrating model-free learning with physics-based simulation, optimization, and control to solve contact-rich dexterous manipulation efficiently and reliably.
• Multimodal World Model — learning predictive models that fuse vision, tactile, and proprioception to support planning and robust closed-loop behavior in unstructured environments.

Designed and trained a UniTree G1 upper-body interception policy with hardware-aligned torque and safety constraints; implemented sim-to-real transfer using DAgger to deploy a vision-based controller at 50 Hz.

We designed an information-theoretic fusion framework that tracks consistency between camera and LiDAR maps; by treating semantic drift as a shift in probability distributions, the system detects when perception diverges from reality.

To address limitations of traditional uncertainty models under high-dimensional and non-Gaussian sensor noise, we applied conformal prediction to robotics perception, providing mathematically guaranteed bounds on prediction errors.