Hao Dong Assistant Professor

+86 (0)10 6275-6561


Room 106-2, Courtyard No.5, Jingyuan

Embodied AI, Robotics, Computer Vision


Dr. Hao Dong joined Peking University in August 2019 and is currently an assistant professor at Center on Frontiers of Computing Studies, PKU. He obtained a Ph.D. degree from Imperial College London under the supervision of Yike Guo in Fall 2019. His research involves robotics, reinforcement learning and computer vision with the goal of reducing the data required for learning intelligent systems. He is passionate about popularizing artificial intelligence technologies and established TensorLayer, a deep learning and reinforcement learning library for scientists and engineers, which won the Best Open Source Software Award at ACM Multimedia 2017. Before Ph.D., he received a MSc specialist degree with distinction from Imperial, and a first-class BEng degree from the University of Central Lancashire. He founded a start-up for digital healthcare with Yike Guo between 2012 and 2014.



Deep Reinforcement Learning: Fundamentals, Research and Applications
Hao Dong, Zihan Ding, Shanghang Zhang Eds.

Springer Nature 2020 ISBN 978-981-15-4094-3
[Homepage(及免费中文在线)] [Springer] [Broadview] [繁体版本] [京东]

■ Machine Learning System: Design and Implementation
Luo Mai, Hao Dong Eds. Springer Nature 2023 ISBN coming soon.
机器学习系统:设计与实现 麦络、董豪 等著
清华大学出版社 Tsinghua University Press 2023 ISBN 978-7-302-63007-4
[OpenMLsys Organisation] [免费中文在线] [京东]

■ 深度学习:一起玩转TensorLayer(Deep Learning using TensorLayer)
Hao Dong, Yike Guo, Guang Yang et al
电子工业出版社 Publishing House of Electronics Industry 2018 ISBN: 9787121326226
[Amazon] [京东] [Broadview] [Code] [Organisation] [Documentation]


Recent Selected Papers

■ ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation
Xiaoqi Li, Mingxu Zhang, Yiran Geng, Haoran Geng, Yuxing Long, Yan Shen, Renrui Zhang, Jiaming Liu, Hao Dong
arXiv 2023
[Paper] [Website]

■ Distilling Functional Rearrangement Priors from Large Models
Yiming Zeng*, Mingdong Wu*, Long Yang, Jiyao Zhang, Hao Ding, Hui Cheng, Hao Dong
arXiv 2023
[Paper] [Website]

■ RGBManip: Monocular Image-based Robotic Manipulation through Active Object Pose Estimation
Boshi An, Yiran geng, Kai Chen, Xiaoqi Li, Qi Dou, Hao Dong
arXiv 2023
[Paper] [Website]

■ ImageManip: Image-based Robotic Manipulation with Affordance-guided Next View Selection
Xiaoqi Li, Yanzi Wang, Yan Shen, Haoran Lu, Qianxu Wang, Ponomarenko Iaroslav, Boshi An, Jiaming Liu, Hao Dong
arXiv 2023
[Paper] [Website]

■ Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions
Yuxing Long, Xiaoqi Li, Wenzhe Cai, Hao Dong
arXiv 2023
[Paper] [Website] [量子位]

■ Bridging Zero-shot Object Navigation and Foundation Models through Pixel-guided Navigation Skill
Wenzhe Cai, Siyuan Huang, Guangran Cheng, Yuxing Long, Peng Gao, Changyin Sun, Hao Dong
arXiv 2023
[Paper] [Website] [Code]

■ RGBGrasp: Image-based Object Grasping by Capturing Multiple Views during Robot Arm Movement with Neural Radiance Field
Chang Liu, Kejian Shi, Kaichen Zhou, Haoxiao Wang, Jiyao Zhang, Hao Dong
arXiv 2023
[Paper] [Website]

Bi-DexHands: Towards Human-Level Bimanual Dexterous Manipulation
Yuanpei Chen, Yiran Geng, Fangwei Zhong, Jiaming Ji, Jiechuang Jiang, Zongqing Lu, Hao Dong, Yaodong Yang
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 2023
[Paper] [Website] [Code]

Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigation
---The First Demand-driven Navigation Paper
Hongcheng Wang, Andy Guan Hong Chen, Xiaoqi Li, Mingdong Wu, Hao Dong
Neural Information Processing Systems (NeurIPS) 2023
[Paper] [Website] [Video] [Code] [BAAI]

GenPose: Generative Category-level Object Pose Estimation via Diffusion Models
Jiyao Zhang, Mingdong Wu, Hao Dong
Neural Information Processing Systems (NeurIPS) 2023
[Paper] [Website] [Code]

Learning Environment-aware Affordance for 3D Articulated Object Manipulation under Occlusions
Ruihai Wu, Kai Cheng, Yan Zhao, Chuanruo Ning, Guanqi Zhan, Hao Dong
Neural Information Processing Systems (NeurIPS) 2023
[Paper] [Website] [Code] [AIR学术] [AIR论坛]

GraspGF: Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping
Tianhao Wu, Mingdong Wu, Jiyao Zhang, Yunchong Gan, Hao Dong
Neural Information Processing Systems (NeurIPS) 2023
[Paper] [Website] [Code] [新智元]

Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objects
Chuanruo Ning, Ruihai Wu, Haoran Lu, Kaichun Mo, Hao Dong
Neural Information Processing Systems (NeurIPS) 2023
[Paper] [Website] [Code]

 Learning Gradient Fields for Scalable and Generalizable Irregular Packing
Tianyang Xue, Mingdong Wu, Lin Lu, Haoxuan Wang, Hao Dong, Baoquan Chen
SIGGRAPH Asia 2023
[Paper] [Website] [Code]

 DefoAfford: Learning Foresightful Dense Visual Affordance for Deformable Object Manipulation
Ruihai Wu, Chuanruo Ning, Hao Dong
International Conference on Computer Vision (ICCV) 2023
[Paper] [Website] [Code] [将门创投] [AIR学术] [AIR论坛]

Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assembly
Ruihai Wu, Chenrui Tie, Yushi Du, Yan Zhao, Hao Dong
International Conference on Computer Vision (ICCV) 2023
[Paper] [Website] [Code]

Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable Visual-Audio Navigation
Hongcheng Wang, Yuxuan Wang, Fangwei Zhong, Mingdong Wu, Jianwei Zhang, Yizhou Wang, Hao Dong
IEEE Robotics and Automation Letters (RAL) 2023
[Paper] [Website] [Code] [CFCS]

SGTAPose: Robot Structure Prior Guided Temporal Attention for Camera-to-Robot Pose Estimation from Image Sequence
Yang Tian, Jiyao Zhang, Zekai Yin, Hao Dong
Conference on Computer Vision and Pattern Recognition (CVPR) 2023
[Paper] [Website] [Code]

GFPose: Learning Gradient Field for Multi-Hypothesis 3D Human Pose Estimation
Hai Ci, Mingdong Wu, Wentao Zhu, Xiaoxuan Ma, Hao Dong, Fangwei Zhong, Yizhou Wang
Conference on Computer Vision and Pattern Recognition (CVPR) 2023
[Paper] [Website] [Code] [CFCS]

PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observations
Haoran Geng, Ziming Li, Yiran Geng, Jiayi Chen, Hao Dong, He Wang
Conference on Computer Vision and Pattern Recognition (CVPR) 2023
[Paper] [Website] [Code]

RLAfford: End-to-End Affordance Learning for Robotic Manipulation
Yiran Geng, Boshi An, Haoran Geng, Yuanpei Chen, Yaodong Yang, Hao Dong
International Conference on Robotics and Automation (ICRA) 2023
[Paper] [Website] [Code] [CFCS] [AIR学术] [AIR论坛]

DualAfford: Learning Collaborative Visual Affordance for Dual-gripper Object Manipulation
Yan Zhao, Ruihai Wu, Zhehuan Chen, Yourong Zhang, Qingnan Fan, Kaichun Mo, Hao Dong
International Conference on Learning Representations (ICLR) 2023
[Paper] [Website] [Code] [AIR学术] [AIR论坛]

Intelligent Indoor Metasurface Robotics
---Journal Cover Paper: A New Robot Concept for God's Eye View and Privacy
Hanting Zhao, Shengguo Hu, Hongrui Zhang, Zhuo Wang, Hao Dong, Philipp del Hougne, Tie Jun Cui, Lianlin Li
National Science Review (NSR) 2022
[Paper] [Journal Cover] [中国科学杂志社]

■ TarGF: Learning Target Gradient Field for Object Rearrangement
Mingdong Wu, Fangwei Zhong, Yulong Xia, Hao Dong
Neural Information Processing Systems (NeurIPS) 2022
[Paper] [Website] [Code]

 Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning
Yuanpei Chen, Tianhao Wu, Shengjie Wang, Xidong Feng, Jiechuang Jiang, Stephen Marcus McAleer, Hao Dong, Zongqing Lu, Song-Chun Zhu, Yaodong Yang
Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks 2022
[Paper] [Website] [Code]

AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions
Yian Wang*, Ruihai Wu*, Kaichun Mo*, Jiaqi Ke, Qingnan Fan, Leonidas Guibas, Hao Dong
European Conference on Computer Vision (ECCV) 2022
[Paper] [Website] [Code] [CFCS] [AIR学术] [AIR论坛]

DREDS: Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects
Qiyu Dai*, Jiyao Zhang*, Qiwei Li, Tianhao Wu, Hao Dong, Ziyuan Liu, Ping Tan, He Wang
European Conference on Computer Vision (ECCV) 2022
[Paper] [Website] [Code]

VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D Articulated Objects
Ruihai Wu, Yan Zhao, Kaichun Mo, Zizheng Guo, Yian Wang, Tianhao Wu, Qingnan Fan, Xuelin Chen, Leonidas Guibas, Hao Dong
International Conference on Learning Representations (ICLR) 2022
[Paper] [Code] [Website] [Youtube] [Bilibili] [CFCS] [AIR学术] [AIR论坛]

DMotion: Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos
---The First Attempt to Learn the Forward Model Unsupervisedly via Motion Disentanglement
Haoqi Yuan, Ruihai Wu, Andrew Zhao, Haipeng Zhang, Zihan Ding, Hao Dong
International Conference on Intelligent Robots and Systems (IROS) 2021
[Paper] [Website] [Code] [CFCS]

Generative 3D Part Assembly via Dynamic Graph Learning
---The First Attempt to Assemble 3D Part without External Guidance
Jialei Huang*, Guanqi Zhan*, Qingnan Fan, Kaichun Mo, Lin Shao, Baoquan Chen, Leonidas Guibas, Hao Dong
Neural Information Processing Systems (NeurIPS) 2020
[Paper] [Code] [Website] ( [机器之心]/ [AI科技评论] )

Research Lab



PKU-Agibot Lab