Zheyuan Hu

I am a 2nd year Ph.D. student at CMU Robotics Institute advised by Prof. Aviral Kumar and Prof. Zackory Erickson. I received my Bachelor's degrees in Computer Science and Applied Mathematics from UC Berkeley, advised by Prof. Sergey Levine. Previously, I had the privilege of working with Prof. Abhishek Gupta and Dr. Kelvin Xu.

My research focus on developing the intelligence needed for solving general robotic manipulation problems in the real world. This includes scalable systems and algorithms that can learn from diverse data, enable test-time compute, and autonomously acquire new skills through online interactions.

GitHub  /  Google Scholar  /  LinkedIn

Research

RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction

RaC scales up recovery & correction data via a simple yet effective human-in-the-loop data collection protocol, enabling robots to spend more rollout budget to mitigate compounding errors in complex long-horizon tasks.

Yell At Your Robot: Improving On-the-Fly from Language Corrections

YAY Robot leverages verbal corrections to enable on-the-fly adaptation and continuous policy improvement on complex long-horizon tasks.

SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning

SERL (Sample-Efficient Robotic reinforcement Learning) provides an open-source software framework that aims to facilitate wider adoption of RL in real-world robotics.

REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation

REBOOT learns dexterous manipulation skills autonomously and entirely in the real world in less than 8 hours by bootstrapping from prior data. The method achieves 2X speed up than learning from scratch. Our method is tested on a multi-fingered robot hand learning dexterous in-hand rotation tasks.

Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance

AVAIL allows robots to learn long horizon manipulation skills through autonomous real-world interaction without manual engineering, using a framework for users to breakdown a long task into multiple sub-tasks with image examples and deep RL. The method was tested on a four-finger robot hand and complex dexterous manipulation tasks in the real world.

Design and source code from Jon Barron's website