Bernie Hao Zhu

I am a researcher in the Machine Learning Department at Carnegie Mellon University, advised by Prof. Christopher Atkeson and Prof. Katerina Fragkiadaki.
I received my bachelor degree in Computer Science from Zhejiang University, with High Honors and minor in Electronic Engineering.

My work is TRASH: Teaching Robotic Agents Skills of Humans.

Robotics, Machine Perception, Machine Learning, especially the intersection of them.
Scene / Object Simulation and Understanding
Human Activity Sensing and Understanding
Human-Robot-Environment Interaction


I am applying for Ph.D. in North America. Please feel free to contact me. [Jul 12, 2020] I had a good time at RobRetro Workshop. Thanks to all the organizers and speakers! [Jun 24, 2020] One paper accepted at RSS RobRetro Workshop 2020. [Feb 23, 2020] One paper accepted at CVPR 2020. [Oct 30, 2019] I attended CoRL 2019 to give a presentation. Huge thanks to organizers for providing wheelchair for me! [Sep 07, 2019] One paper accepted at Conference on Robotics Learning (CoRL) 2019. [Jun 16, 2019] I attended CVPR 2019. [Mar 02, 2019] One paper accepted at CVPR 2019.


Benchmarking Object-Centric Manipulation Using a Simulated Environment
Hao Zhu
RSS RobRetro Workshop, 2020

SAPIEN: A SimulAted Part-based Interactive ENvironment
Fanbo Xiang, Yuzhe Qin, Kaichun Mo, Yikuan Xia, Hao Zhu, Fangchen Liu, Minghua Liu, Hanxiao Jiang, Yifu Yuan, He Wang, Li Yi, Angel X.Chang, Leonidas J. Guibas, Hao Su
CVPR 2020, Oral Presentation
[Paper] [Project] [Video]

We build SAPIEN simulator: an interaction-rich and physics-realistic simulation environment integrating PhysX engine and ROS control interface. I lead the team of building SAPIEN dataset: more than 2K 3D articulated models with 14K movable parts. The dataset is richly annotated with kinematic part motions and dynamic interactive attributes to support robot interaction.

S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenes
Yuzhe Qin*, Rui Chen*, Hao Zhu, Meng Song, Jing Xu, Hao Su (*Equal contribution)
CoRL 2019, Spotlight Presentation
[Paper] [Project] [Video] [Presentation]

We studied the problem of 6-DoF grasping by a parallel gripper in a cluttered scene captured using a commodity depth sensor from a single view point. Our learning based approach trained in a synthetic scene can work well in real-world scenarios, with improved speed and success rate compared with state-of-the-arts.

CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark
Jiefeng Li, Can Wang, Hao Zhu, Yihuan Mao, Hao-Shu Fang, Cewu Lu
CVPR 2019, Oral Presentation
[Paper] [Code] [Dataset] [Video]

We collect CrowdPose, a new dataset of crowded human poses. We propose a joint-candidate single person pose estimation (SPPE) and a global maximum joints association algorithm to tacklethe problem of pose estimation in a crowd. Our method surpasses the state-of-the-art method by 5.2 mAP on CrowdPose and replacing certain steps in the state-of-the-art method with our module would bring 0.8 mAP improvement on MSCOCO.



I am famous for a strong memory, which always enables me to get a high score in a very short period of time :-D I lost my hearing for a long time in 20s, fortunately, I got recovered when I had learnt how to read lips. My avatar is from Zombie Dance, a vocaloid song made by ilem.


Cooking I cook in western way but with Chinese seasonings.

Games I am good at strategy games, board games, poker games, etc.

Music I enjoy classical music and electronic music, especially trance. My faves: Daft Punk Approaching Nirvana