Intro

I'm a second-year Ph.D. student in CS at Columbia University, advised by Prof. Yunzhu Li. I'm fortunate to receive mentorship from Prof. Yiyue Luo during my Ph.D.. I received M.S. from Mechanical and Aerospace Engineering at UC San Diego, advised by Prof. Xiaolong Wang. Prior to joining UCSD, I worked at Lab of Flexible Sensors and Intelligent Interaction with Prof.Geng Yang at Zhejiang University. I've also had great experiences working at NVIDIA Seattle Robotics Lab.

My research interests lie in Robot Learning, Dexterous Manipulation, Multi-Modal Perception. My research goal is to develop a robust robotic system that can function similarly to humans and possess a deep understanding of its surrounding environment - not just visually but also through touch and other physical cues.

Email / CV_24.09 / Google Scholar / twitter / Video Channel

Mentoring

I am always interested in mentoring highly-motivated undergrads/masters in ME/ECE/CS. If you are at Columbia (preferred) and want to discuss project ideas/research opportunities, please feel free to shoot me an email. If you want to schedule a meeting, please book an appointment with me: Schedule a Meeting.

I focus on Robot Learning and aim to significantly expand robots' perception and physical interaction capabilities, particularly through the following three directions:

• Multi-Modal Perception: Development of tactile sensing hardware and multi-modal learning systems, especially for visuo-tactile sensing.
• Dexterous Manipulation: Learning with multi-finger hands to equip robots with human-level dexterity. Expertise in robot control and teleoperation is highly desirable.
• Learning with Dynamic Tasks: Addressing challenging tasks that require dynamic robot motions such as throwing, catching, and contact-rich interactions.

News

• [2024/09] Three papers are accepted by CoRL 2024.
• [2023/08] My new journey will be a CS Ph.D. at Columbia University starting from 2024 Fall, working with Prof. Yunzhu Li.
• [2024/05] Started my internship at NVIDIA Seattle Robotics Lab
• [2024/01] Two papers are accepted by ICRA 2024.
• [2023/09] One paper is accepted by CoRL 2023.
• [2023/07] Our RSS paper Rotating without Seeing is covered in Scientific American.
• [2023/07] I am co-organizing the Workshop on Learning Dexterous Manipulation in RSS 2023.
• [2023/05] Invited Talk at Facebook AI Research(FAIR)
• [2023/03] My new journey will be a CS Ph.D. at UIUC starting from 2023 Fall, working with Prof. Yunzhu Li.
• [2023/03] Two Papers are accepted by RSS 2023.
• [2023/03] One Paper is accepted by RA-L 2023.
• [2023/03] Awarded the degree of Master of Science in Mechanical and Aerospace Engineering at University of California, San Diego (UCSD).
• [2023/08] One paper is accepted by CoRL 2022.

Publication

(* indicates equal contribution)

Dynamic Handover: Throw and Catch with Bimanual Hands
Binghao Huang*, Yuanpei Chen*, Tianyu Wang, Yuzhe Qin, Yaodong Yang, Nikolay Atanasov, Xiaolong Wang.
Conference on Robot Learning (CoRL), 2023
[webpage] [arxiv] [code]

Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensing
Ying Yuan*, Haichuan Che*, Yuzhe Qin*, Binghao Huang, Zhao-Heng Yin, Kang-Won Lee, Yi Wu, Soo-Chul Lim, Xiaolong Wang
International Conference on Robotics and Automation (ICRA), 2024
[webpage] [arxiv] [code]

Rotating without Seeing: Towards In-hand Dexterity through Touch
Zhao-Heng Yin*, Binghao Huang*, Yuzhe Qin, Qifeng Chen, Xiaolong Wang.
Robotics: Science and Systems (RSS), 2023
[webpage] [paper] [code]

AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System
Yuzhe Qin, Wei Yang, Binghao Huang, Karl Van Wyk, Hao Su, Xiaolong Wang, Yu-Wei Chao, Dietor Fox
Robotics: Science and Systems (RSS), 2023
[webpage] [paper]

DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation
Yuzhe Qin*, Binghao Huang*, Zhao-Heng Yin, Hao Su, Xiaolong Wang.
Conference on Robot Learning (CoRL), 2022
[webpage] [paper] [code]

Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrations
Jianglong Ye*, Jiashun Wang*, Binghao Huang, Yuzhe Qin, Xiaolong Wang.
IEEE Robotics and Automation Letters(RA-L), 2023
[webpage] [paper] [video]

Robot Systems

Tactile Dexterous Manipulation System

If you want to know more about how tactile sensors can benefit your robot system, feel free to contact me. Here, we propose Touch Dexterity, a new dexterous manipulation system to perform in-hand object rotation with only touch sensing. On the left, we show our hardware setup with 16 FSR sensors attached to an Allegro hand.

Bimanual Hand Robot System

We propose Dynamic Handover, a new bimanual dexterous hands system designed for throwing and catching tasks. The system consists of two Allegro Hands, each individually attached to a separate XArm robot, arranged in a facing configuration.

Humanoid Robot with Peception and Navigation

I have experience in developing a ROS-based control pipeline for a navigation system that utilizes 2D Lidar and depth cameras. Additionally, I have designed a vision-based tracking method that leverages object detection algorithms to enable obstacle avoidance for mobile robots. [paper] [code]

Work Experience

Research Intern, NVIDIA
05/20/2024 - Now

Mentor: Yu-Wei Chao, Jie Xu, Iretiayo Akinola, Wei Yang, Xiaolong Wang, and Dieter Fox

Professional Service

• Conference Reviewer: CoRL, ICLR, RSS, IROS, ICRA
• Journal Reviewer: IEEE T-RO, IEEE RA-L
• Workshop Organizer: Learning Dexterous Manipulation @RSS 2023
• Invited Speaker: Talk @ Facebook AI Research(FAIR)

Media Coverage

Interests

Robotics Video Channel

In addition to my research in Robotics, I am also a content creator with a strong passion for sharing my knowledge of the field. I currently manage a Robotics Video Channel with over 63,000 followers and 4 million views in total. One of my Most Popular Video, which discusses robots combined with brain-computer interfaces, has garnered over 1.84 million views and is widely recognized within the field.

Sad Stories with Robots

I possess practical experience in both building and repairing a wide range of robotic equipment. In doing so, I have encountered and addressed various dangerous situations, including instances where a robot lost control, a robot motor caught on fire, and a gearbox became damaged.

NEXTEV Formula Student Electric China (FSEC),Sep 2017

In, Nextev Formula Student Electric China (FSEC) team, I took on the role of designing the steering system for our formula car. The patent, titled "A Kind of University Student's Equation Motorcycle Race Steering, Manufacture and Its Installation Method," was granted under the number 2017105998790.1.
[Google Patent], [pdf]

Update: 2024.5

Credit: web source from Dr. Songfang Han