Zeng Long

Associate Professor, Doctoral Supervisor, PhD from Hong Kong University of Science and Technology; Leader of the Intelligent Manufacturing and Machine Vision Research Group; Director of Tsinghua Purdue Intelligent Service Robot Technology Joint Research Center; Guangzhou Fuwei Intelligent Technology, co-founder.

The research group has long focused on industrial embodied intelligence technology, especially deep learning theory, methods, and techniques for intelligent manufacturing, and applied them to embodied intelligent industrial robots and service robots, embodied intelligent flexible assembly systems, and intelligent CAD/CAM industrial software. The research group has recently focused on researching and implementing industrial basic models (including assembly process basic models, hand drawn design basic models), deep learning methods for industrial parameterized part point clouds, and embodied intelligence big and small brain technology frameworks for industrial scenarios. Specific technologies include semantic maps, knowledge graphs, embodied intelligence grasping, humanoid perception and decision-making, virtual real fusion simulation technology, 3D reconstruction AIGC、 Defect detection, etc. The research group has published over 80 high-level academic papers in top global conferences and journals such as JMS (Impact Factor 12.2) and RCIM (Impact Factor 9.2), Global Robotics and Computer Vision Summit (ICRA, IROS, RSS, CVPR, ECCV), and Computer Graphics; Hosted over 25 national and corporate projects, including the project leader of the National Key R&D Program Industrial Software, National Natural Science General Project, Youth Project, Guangdong Provincial Natural Science Foundation General Project, Shenzhen Science and Technology Major Project, Technology Attack, Discipline Layout Project, with research funding exceeding 25 million yuan in the past 5 years; Applied for and authorized over 40 invention patents, and successfully completed the industrialization of research achievements in reconfigurable flexible assembly and visual robotic arm grasping, creating significant economic benefits.

【Tip】: The research group is recruiting postdoctoral, doctoral, and master's students from mechanical engineering, computer technology, automation, and other fields on a long-term basis.

Please refer to the Github account jackyzengl for the open source code, public datasets, and team English website of the research group.

(1) September 2007-October 2012, Hong Kong University of Science and Technology，Mechanical Engineering/Computer Aided Design and Manufacturing, PhD

(2) September 2005-June 2007, Zhejiang University，Mechanical Design and Theory, Master

(3) September 2001-June 2005, Dalian University of Technology，Measurement and Control Technology and Instruments, Bachelor

(1) From February 2023 to present, Associate Professor, Institute of Data and Information Shenzhen International Graduate School, Tsinghua University

(2) From December 2020 to February 2023, Associate Professor, Advanced Manufacturing Department, Shenzhen International Graduate School, Tsinghua University

(3) From April 2019 to November 2020, lecturer at the Advanced Manufacturing Department of Tsinghua University Shenzhen International Graduate School

(4) From December 2014 to March 2019, lecturer at the Advanced Manufacturing Department of Tsinghua University Shenzhen Graduate School

(5) Nov. 2012-Nov. 2014, Hong Kong University of Science and Technology，Mechanical Engineering, Associate Researcher

(1) Executive Editorial Board Member of the Journal of Computer Science (ranked 6th in the core Chinese journals of Peking University);

(2) Journal of Computer Integrated Manufacturing Systems (selected for EI Core Database), board member;

(3) Member of the 8th Network Graphics Professional Committee of the Chinese Society of Graphic Sciences;

(4) The ICRA2024 and IROS2024 session chairs of the Global Robotics Technology Summit;

(5) Long term reviewers for top journals and conferences in the fields of robotics, graphics, and intelligent manufacturing, such as ICRA, IROS, CAD, IEEE TASE, RCIM, IJAMT, etc.

Product Design and Development; Advanced Mechanical Engineering Design; Modern CAD Methodology and Technology

The Intelligent Manufacturing and Machine Vision research group has long focused on the study of industrial embodied intelligence, especially deep learning methods for intelligent manufacturing, industrial vertical domain based large models, embodied intelligent robotics, and hand-drawn sketch CAD modeling.

In the field of embodied intelligent robots, the main research focuses on human like perception and decision-making technology for mobile robots in complex dynamic indoor environments, including mobile robot learning platforms, semantic SLAM, embodied intelligence, etc. It is mainly applied in food delivery robots, cleaning robots, etc. At present, we have established a Joint Research Center for Intelligent Service Robot Technology with Purdue Technology, a unicorn enterprise in the field of distribution robots in Shenzhen. We have invested tens of millions of yuan to carry out key research and engineering application research on core technologies related to intelligent service robots.

In the field of intelligent manufacturing, in response to the significant demand and industry pain points of multi variety and small batch product assembly in the era of product personalization, the research team has proposed a cross category reconfigurable flexible assembly production line deformation design theory and technical system, widely using knowledge graphs, deep learning, virtual debugging, digital twins and other methods to achieve the flexibility, numerical control and intelligence of product assembly production lines. At present, the technology has been successfully industrialized for Guangzhou Fuwei Intelligent Technology Co., Ltd. and has been successfully applied in large state-owned enterprises.

In the field of CAD industrial software, hand drawn sketch engineering product assembly modeling technology has been proposed to address the gap between conceptual design and detailed design. This includes research tasks such as hand drawn sketch understanding, part creation, and complex product assembly based on deep learning, data mining, and other methods. Our team has independently developed the 3D modeling core iDesignCAD with the continuous support of National Natural Science Youth and general projects. At present, with the support of the national key research and development program Industrial Software, we plan to develop a large-scale multimodal dataset of hand drawn sketches, laying the data foundation for deep learning methods for hand drawn sketches, and developing hand drawn sketch CAD industrial software, laying the foundation for the industrial application of hand drawn sketch CAD industrial software.

Based on their in-depth understanding of product design and development, the research team mostly focuses on the industry pain points of intelligent manufacturing and robotics enterprises. The research team has always adhered to the concept of down-to-earth, mutual benefit, and common growth, and established long-term, sustainable and healthy cooperative relationships with partner enterprises. At present, more than 25 projects have been completed and are under research, with a total of over 25 million in the past 5 years.

Please refer to the Github account jackyzengl for the open source code, public datasets, and team English website of the research group.

[1] Zijie Zheng#, Zeshun Li#, Yunpeng Wang#, Qinghongbing Xie, Long Zeng*, Demonstrating DVS: Dynamic Virtual-Real Simulation Platform for Mobile Robotic Tasks, Robotics: Science and Systems 2025.

[2] Haodong Xiang†, Xinghui Li†, Kai Cheng†, Xiansong Lai, Wanting Zhang, Zhichao Liao, Long Zeng*, Xueping Liu*, GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstruction, Accepted by 2025 IEEE ICRA.

[3] Yan Chen, Di Huang, Zhichao Liao, Xi Cheng, Xinghui Li, Long Zeng*, Training-Free Point Cloud Recognition Based on Geometric and Semantic Information Fusion, 2024 International Conference on Acoustics, Speech and Signal Processing (CCF-B).

[4] Ente Lin, xujie zhang, Fuwei Zhao, Yuxuan Luo, Xin Dong, Long ZENG*, Xiaodan Liang, DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder, AAAI Conference on Artificial Intelligence 2024 (CCF-A).

[5] Fuhao Li, Long Zeng*, Dual-Alignment Domain Adaptation for Pedestrian Trajectory Prediction, IEEE Robotics Automation Letters (JCR Q1, IF4.6), 2024.

[6] Xi Cheng, Pingfa Feng, Long Zeng*, Approaching optimum sampling by sectional error equivalence, Measurement (JCR Q1, IF5.2), 2024.

[7] Zhaobo Xu, Chaoran Zhang, Song Hu, Pingfa Feng, Long Zeng*, Reconfigurable Flexible Assembly Model and Its Implementation for Cross-Category Products, Journal of Manufacturing Systems (JCR Q1, IF 12.2), 2024.

[8] Zhichao Liao, Di Huang, Pingfa Feng, Long Zeng*, Freehand Sketch Generation from Mechanical Components, ACM International Conference on Multimedia, 2024.

[9] Yihan Xie, Weijie Lv, Xinyu Zhang, YiHong Chen, Long Zeng*, ParametricNet+: A 6DoF Pose Estimation Network with Sparse Keypoint Recovery for Parametric Shapes in Stacked Scenarios, IEEE International Conference on Intelligent Robots and Systems, 2024.

[10] Xinghui Jing, Xin Xiong, Fuhao Li, Tao Zhang, Long Zeng*, A Two-Stage Reinforcement Learning Approach for Robot Navigation in Long-range Indoor Dense Crowd Environments, IEEE International Conference on Intelligent Robots and Systems, 2024.

[11] Dingtao huang, Ente Lin, Lipeng Chen, lifu Liu, Long Zeng*, SD-Net: Symmetric-Aware Keypoint Prediction and Domain Adaptation for 6D Pose Estimation In Bin-picking Scenarios, IEEE International Conference on Intelligent Robots and Systems, 2024.

[12] Zhe Ni, Xiaoxin Deng, Cong Tai, Xinyue Zhu, Qinghongbing Xie, Weihang Huang, Xiang Wu, Long Zeng*, GRID: Scene-Graph-based Instruction-driven Robotic Task Planning, 2024 IEEE International Conference on Intelligent Robots and Systems.

[13] Xinghui Li, Yuchen ji, Xiansong Lai, Wanting Zhang and Long Zeng*. Fine-detailed Neural Indoor Scene Reconstruction Using Multi-level Importance Sampling and Multi-view Consistency, 2024 IEEE International Conference on Image Processing (ICIP, CCF-B).

[14] Yi-Fan Tang, Cong Tai, Fang-Xin Chen, Wanting Zhang, Tao Zhang, Yongjin Liu, Long Zeng*, Mobile Robot Oriented Large-Scale Indoor Dataset for Dynamic Scene Understanding, IEEE International Conference Robotic and Automation, 2024（顶会，开源地址：jackyzengl.github.io/THUD-Robotic-Dataset.github.io/）.

[15] Fang-xing Chen, Yifan Tang, Cong Tai, Xue-ping Liu, Xiang Wu, Tao Zhang, and Long Zeng∗, FusedNet: End-to-end Mobile Robot Relocalization in Dynamic Large-scale Scene, IEEE Robotics and Automation Letters, 2024.

[16] XiaoMing Zhu, Shuo Wang, JunYu Su, Fei Liu*, Long Zeng*, High-speed and accurate cascade detection method for chip surface defects, IEEE Transactions on Instrumentation & Measurement (SCI 1区), 2023.

[17] Fei Liu, XiaoMing Zhu, PingFa Feng, Long Zeng*, Anomaly Detection via Progressive Reconstruction and Hierarchical Feature Fusion, Sensors (JCR Q2, IF3.9), MDPI, 2023.

[18] Shuo Wang, Weijie Lv, Xinyuan Zhao, Xinyu, Zhang, Junyu Su, Long Zeng*, Refined-mask guided multi-stream blending network, Multimedia Tools and Applications (SCI 2区), 2023.

[19] L. Zhao, W. J. Lv, X. Y. Zhang, L. Zeng*, Domain Adaptation on Point Clouds for 6D Pose Estimation in Bin-picking Scenarios, 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2023).

[20] X.H. L., Y. K. Ding, J. Guo, X.S. Lai, S. H. Ren, W. S. Feng, L. Zeng*, Edge-aware Neural Implicit Surface Reconstruction, International Conference on Multimedia and Expo (CCF-B), 2023.H. Zhang, H. Z. Liang, L. Cong, J. Z. Lyu, L. Zeng∗, P. F. Feng, and J. W. Zhang, Reinforcement Learning Based Pushing and Grasping Objects from Ungraspable Poses, IEEE International Conference Robotic and Automation (ICRA2023).

[21] L. C. Xiao, Z. B. Xu, L. Zeng*, X. P. Liu, Assembly language design and development for reconfigurable flexible assembly line, Robotics and Computer-Integrated Manufacturing (SCI 1区, IF5.1), 2022.

[22] Z. Sun, P. F. Feng, L. Zeng*, S. Q. Zhang, X. Cheng, Adaptive Machining Scheme for a Multi-Hole Part with Multi-Position Accuracy Tolerances, Journal of Advanced Manufacturing Technology (SCI 2区), 2022

[23] S. Wang, H. Y. Wang, F. Yang, F. Liu, L. Zeng*, Attention-based deep learning for chip-surface-defect detection, Journal of Advanced Manufacturing Technology (SCI 2区), 2022.

[24] L. Zeng, W. J. Lv, Z. K.Dong, Y. J. Liu, PPR-Net++, Accurate 6-D Pose Estimation in Stacked Scenarios, IEEE Transactions on Automation Science and Engineering (JCR 1区), 2021, 1(1): 1-13.

[25] F. Yang（学生）, k. Wu, S. Y. Zhang, G. N. Jiang, Y. Liu, F. Zheng, W. Zhang, C. J. Wang and L. Zeng, Class-Aware Contrastive Semi-Supervised Learning, 2022 IEEE Computer Vision and Pattern Recognition (CVPR2022, CCF-A).

[26] L. Zeng, W. J. Lv, X. Y. Zhang, Y. J. Liu, ParametricNet: 6DoF Pose Estimation Network for Parametric Shapes in Stacked Scenarios, IEEE International Conference Robotic and Automation (ICRA 2021).

[27] S. M. Li, L. Zeng*, Pingfa Feng, Dingwen Yu, An accurate probe pre-travel error compensation model for five-axis OMI system, Precision Engineering (SCI 1区, IF3.1), 2020, vol. 62, pp. 256-264.

[28] Y. M. Li, L. Zeng*, K. Tang, C. Xie, Orientation-point relation-based inspection path planning method for 5-axis OMI system, Robotics and Computer-Integrated Manufacturing (SCI 1区, IF5.1), 2020, vol. 51, pp. 1-17.

[29] Y. M. Li, L. Zeng*, K. Tang, S. M. Li, A dynamic pre-travel error prediction model for the kinematic touch trigger probe, Measurement (SCI 1区, IF3.4), 2019.

[30] Z. K. Dong, S. C. Liu, T. Zhou, H. Cheng, L. Zeng*, X. Y. Yu, H. D. Liu, PPR-Net: Point-wise Pose Regression Network for Instance Segmentation and 6D Pose Estimation in Bin-picking Scenarios, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (顶会，同年获得IROS2019位姿估计挑战赛双料冠军).

[31] Y. M. Li, L. Zeng*, K. Tang, C. Xie, Orientation-point relation based inspection path planning method for 5-axis OMI system, Robotics and Computer-Integrated Manufacturing (SCI 1区, IF4.4), 2019.

[32] L. Zeng*, Z.-k. Dong, J. Y. Yu, J. Hong, H. Y. Wang, Sketch-based Retrieval and Instantiation of Parametric Parts [J], Computer Aided Design (SCI 1区), 2019, 113(82-95).

[33] S. M. Li, L. Zeng*, P. F. Feng Y. M. , Li, C. Xu, Y. Ma, Error Compensation using 3D error map for OMI with touch trigger probe, Journal of Advanced Manufacturing Technology (SCI 2区, IF2.5), 2019.

[34] B. Li, P. F. Feng, L. Zeng*, et al. Path planning method for on-machine inspection of aerospace structures based on adjacent feature graph [J]. Robotics and Computer-Integrated Manufacturing (SCI 1区, IF4.4), 2018, 54:17-34.

[35] S. L. Mi, X. Y. Wu, L. Zeng*. Optimal build orientation based on material changes for FGM parts [J]. International Journal of Advanced Manufacturing Technology (JCR 2区, IF2.5), 2017, 94(3):1-14.

[36] Y. F. Xu（学生）, T. Fan, M. Xu, L. Zeng. SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters, ECCV 2018 (全球计算机视觉三大会议之一，谷歌学术引用数>800次).

[37] L. Zeng*, Y. J. Liu, S. H. Lee, and M. M. F. Yuen. Q-Complex: Efficient Non-Manifold Boundary Representation with Inclusion Topology, Computer-Aided Design (JCR 1区，IF3.1), Vol. 44, No. 11, pp.1115-1126, 2012.

[38] L. Zeng*, L. M. L. Lai, D. Qi, Y. H. Lai, M. M. F. Yuen. Efficient Slicing Procedure based on Adaptive Layer Depth Normal Image, Computer-Aided Design (JCR 1区，IF3.1), Vol.43, No. 12, pp.1577-1586, 2011.

At present, a total of 42 patents have been applied for, including 21 authorized invention patents, mainly distributed in reconfigurable flexible assembly, visual grasping, defect detection, and flexible assembly.

1. Eight invention patents related to reconfigurable flexible assembly and visual grasping have been transferred to Guangzhou Fuwei Intelligent Technology Co., Ltd. as industrial achievements.