Peng Zhou
| Google Scholar | Github |
|
Currently, I am an assistant professor with the School of Advanced Engineering of The Great Bay University,
and the Principal Investigator of the Embodied MAnipulation InteLligence (EMAIL) Robotics Lab. My research interests lie in the fields of robotics, machine learning and computer vision, with a focus on deformable object manipulation, robot perception and learning and task and motion planning.
Before that, I worked at the Robotic and Machine Intelligence (ROMI) Lab and received my Ph.D. degree in Robotics from The Hong Kong Polytechnic University, under the supervision of Dr. David Navarro-Alarcon.
I also worked as a Postdoctoral Research Fellow at the University of Hong Kong (HKU) advised by Dr. Pan Jia.
In 2021, I visited the Robotics, Perception and Learning (RPL) Lab at KTH as an exchange Ph.D. student under the supervision of Prof. Danica Kragic . Furthermore, during my Ph.D. study and subsequent research, I had the opportunity to collaborate with
Dr. Jihong Zhu ,
Prof. Hesheng Wang ,
Dr. Pai Zheng
and
Prof. Charlie Yang .
|
|
Bimanual Deformable Bag Manipulation Using a Structure-of-Interest Based Latent Dynamics Model
Peng Zhou,
Pai Zheng, Jiaming Qi, Chenxi Li, Hoi-yin Lee, Chenguang Yang, David Navarro-Alarcon, Jia Pan†
IEEE/ASME Transactions on Mechatronics (T-Mech), 2024
*, †: equal contribution, corresponding author
| arXiv |
project page |
This paper introduces a novel approach to deformable object manipulation (DOM) by emphasizing the identification and manipulation of structures of interest (SOIs) in deformable fabric bags. We propose a bimanual manipulation framework that leverages a graph neural network (GNN)-based latent dynamics model to succinctly represent and predict the behavior of these SOIs.
|
|
Interactive Perception for Deformable Object Manipulation
Zehang Weng*, Peng Zhou*†, Hang Yin, Alexander Kravberg, Anastasiia Varava, David Navarro-Alarcon, Danica Kragic
IEEE Robotics and Automation Letters (RA-L), 2024
*, †: equal contribution, corresponding author
| arXiv |
In this work, we address such a problem with a setup involving both an active camera and an object manipulator. Our approach is based on a sequential decision-making framework and explicitly considers the motion regularity and structure in coupling the camera and manipulator.
|
|
Reactive human–robot collaborative manipulation of deformable linear objects using a new topological latent control model
Peng Zhou, Pai Zheng, Jiaming Qi†, Chengxi Li, Hoi-Yin Lee, Anqing Duan, Liang Lu, Zhongxuan Li, Luyin Hu, David Navarro-Alarcon
Robotics and Computer-Integrated Manufacturing (RCIM), 2024
ESI Highly Cited + Hot Paper
*, †: equal contribution, corresponding author
| arXiv |
project page |
In this paper, a novel approach is proposed for real-time reactive deformable linear object manipulation in the context of human–robot collaboration. The proposed approach combines a topological latent representation and a fixed-time sliding mode controller to enable seamless interaction between humans and robots.
|
---- show more ----
|
Imitating tool-based garment folding from a single visual observation using hand-object graph dynamics
Peng Zhou,
Jiaming Qi,
Anqing Duan,
Shengzeng Huo,
Zeyu Wu,
David Navarro-Alarcon
IEEE Transactions on Industrial Informatics (T-II), 2024
ESI Highly Cited
*, †: equal contribution, corresponding author
| arXiv |
In this article, we propose a novel method of learning from demonstrations that enables robots to autonomously manipulate an assistive tool to fold garments. In contrast to traditional methods (that rely on low-level pixel features), our proposed solution uses a dense visual descriptor to encode the demonstration into a high-level hand-object graph (HoG) that allows to efficiently represent the interactions between the manipulated tool and robots.
|
|
Lasesom: A latent and semantic representation framework for soft object manipulation
Peng Zhou, Jihong Zhu, Shengzeng Huo, David Navarro-Alarcon
IEEE Robotics and Automation Letters (RA-L), 2021
*, †: equal contribution, corresponding author
| arXiv |
project page |
In this letter, we present LaSeSOM, a new feedback latent representation framework for semantic soft object manipulation. Our new method introduces internal latent representation layers between low-level geometric feature extraction and high-level semantic shape analysis.
|
|
Model predictive manipulation of compliant objects with multi-objective optimizer and adversarial network for occlusion compensation
Peng Zhou,
Pai Zheng,
Jiaming Qi†,
Chengxi Li,
Hoi-Yin Lee,
Anqing Duan,
Liang Lu,
Zhongxuan Li,
Luyin Hu,
David Navarro-Alarcon
Robotics and Computer-Integrated Manufacturing (RCIM), 2024
*, †: equal contribution, corresponding author
| arXiv |
In this paper, we propose a new vision-based controller to automatically regulate the shape of compliant objects with robotic arms. Our method uses an efficient online surface/curve fitting algorithm that quantifies the object's geometry with a compact vector of features; This feedback-like vector enables to establish an explicit shape servo-loop.
|
|
Neural reactive path planning with Riemannian motion policies for robotic silicone sealing.
Peng Zhou,
Pai Zheng,
Jiaming Qi†,
Chengxi Li,
Hoi-Yin Lee,
Anqing Duan,
Liang Lu,
Zhongxuan Li,
Luyin Hu,
David Navarro-Alarcon
Robotics and Computer-Integrated Manufacturing (RCIM), 2022
*, †: equal contribution, corresponding author
| arXiv |
project page |
In this paper, we present the development of a new method to automate silicone sealing with robotic manipulators. To this end, we propose a novel neural path planning framework that leverages fractional-order differentiation for robust seam detection with vision and a Riemannian motion policy for effectively learning the manipulation of a sealing gun.
|
|
Path planning with automatic seam extraction over point cloud models for robotic arc welding
Peng Zhou,
Pai Zheng,
Jiaming Qi†,
Chengxi Li,
Hoi-Yin Lee,
Anqing Duan,
Liang Lu,
Zhongxuan Li,
Luyin Hu,
David Navarro-Alarcon
IEEE Robotics and Automation Letters (RA-L), 2021
*, †: equal contribution, corresponding author
| arXiv |
project page |
We present a sim-to-real learning-based approach for real-world humanoid locomotion.
To the best of our knowledge, this is the first demonstration of a fully learning-based method for real-world full-sized humanoid locomotion.
|
Awards
|
- Track 3 champion, Zhuhai International Dexterous Manipulation Challenge, 2024
- IEEE R10 Outstanding Volunteer Award, 2023
- Outstanding Young Researcher, National Engineering Research Center, 2022
- IEEE MGA Young Professional Achievement Award, 2022
- Best Artificial Intelligence Application Award,Hong Kong AI Open Competition, 2022
- Hong Kong Innovation and Technology Commission
Research Talent Hub (RTH-ITF),2022
- IEEE Young Professional, 2022
- Outstanding Employee Award, Tencent, 2018
- Outstanding Graduate, Tongji University, 2017
- National Scholarship, Ministry of Education, China, 2016
|
Service
|
 |
Teaching Faculty, Perceptual Robotics (ME41006) (20-21 spring)
Teaching Faculty, Reinforcement Learning for Robotics (21-22 fall)
|
Contact
Centre for Transformative Garment Production (TransGP)
Units 1215-1220, 12/F, Building 19W,
SPX1, Hong Kong Science Park,
Pak Shek Kok, N.T.,
Hong Kong, SAR.
|
Website design: ✩ ✩
✩
Avatar photo: generated in July 2024 by an AI app Miaoya Camera.
|
|