◤ Biography
I am a second-year M.Phil. student at the
I obtained my B.Sc. degree of Computer Science (Honored Class) and Mathematics advised by
Here is my CV/Resume.
[Feb 2023] I will join UC Berkeley EECS as a Computer Science PhD student starting Fall 2023.
◤ Research
I am developing novel algorithms for robot learning. In particular, I am working on imitation learning and reinforcement learning. I have proposed imitation learning algorithms that can leverage cross domain expert data (ICRA'22), learn more sample efficiently with MCTS planning (NeurIPS'22), and generalize better with relational inductive bias (CoRL'22-W). I also study the application of these algorithms on real robotics problem, such as dexterous manipulation.
◤ Selected Publications
My recent representative works are marked with ★.
★ Rotating without Seeing: Towards In-hand Dexterity through Touch
Zhao-Heng Yin* , Binghao Huang*, Yuzhe Qin, Qifeng Chen, Xiaolong Wang
Preprint 2023    PDF    Project
Dexterous robotic hand with touch-only control.
★ Spatial Generalization of Visual Imitation Learning with Position-Invariant Regularization
Zhao-Heng Yin , Yang Gao, Qifeng Chen
CoRL 2022 Workshop (Long Paper)   PDF   Code
"Aligning Robot Representation with Humans"

★ Planning for Sample Efficient Imitation Learning
Zhao-Heng Yin , Weirui Ye, Qifeng Chen, Yang Gao
NeurIPS 2022   PDF   Code
We propose EfficientZero-Continuous and EfficientImitate for sample efficient robot learning.

★ Cross Domain Robot Imitation with Invariant Representation
Zhao-Heng Yin , Lingfeng Sun, Hengbo Ma, Masayoshi Tomizuka, Wu-Jun Li
ICRA 2022   PDF   Code

DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation
Yuzhe Qin*, Binghao Huang*, Zhao-Heng Yin , Hao Su, Xiaolong Wang
CoRL 2022   PDF

Diverse Critical Interaction Generation for Planning and Planner Evaluation
Zhao-Heng Yin* , Lingfeng Sun*, Liting Sun, Masayoshi Tomizuka, Wei Zhan
IROS 2021   PDF

TOMA: Topological Map Abstraction for Reinforcement Learning
Zhao-Heng Yin , Wu-Jun Li
arXiv 2020   PDF
◤ Miscellaneous
Some fun projects I participated in the past.

Bio-inspired* Direct-Drive Palmar Manipulation with Visual Imitation Learning
with Ka Hei Mak and Jungwon Seo (2021)
* guess where the inspiration comes from :P
My Chinese Name (surname first): 殷 兆恒.