崔允端 Yunduan Cui
Email Address: yd.cui[at]siat.ac.cn
副研究员 Associate Professor
中国科学院深圳先进技术研究院
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences (SIAT)
奖励 Awards
2025 IEEE RCAR 最佳论文入围奖
Best Paper Finalist of IEEE RCAR 2025
2024 第二十六届高交会优秀科研成果创新奖
Outstanding Research Findings of the 26th China Hi-Tech Fair
2021 深圳市海外高层次B类人才
Shenzhen Overseas High-Caliber Personnel (level B)
2020 中国科学院人才择优计划B类人才
The Hundred Talents Plan of the Chinese Academy of Sciences
2021 日本计测自动控制学会IROS青年作者奖
SICE International Young Authors Award (IROS)
2018 日本神经网络学会优秀论文奖
Japanese Neural Network Society Best Paper Award
2018 日本奈良先端科学技术大学院大学最优秀学生奖
Nara Institute of Science and Technology Best Student Award
2016 IEEE 国际人形机器人会议最优秀发表论文奖
Best Oral Paper Award of IEEE-RAS International Conference on Humanoid Robots
2016 Apr - 2017 Sep, 日本文部省全额奖学金
Japanese Government Scholarship (MEXT)
关于我 About Me
课题组以强化学习的工程应用为研究方向，面向复杂环境下的机器人、无人系统以及工业自动化系统研发稳健抵抗扰动、学习效率高的强化学习算法。 主要研究方向包括但不限于概率模型驱动的强化学习、具有高采样效率的无模型强化学习、分治大规模系统的多智能体强化学习。课题组诚挚欢迎本科同学报考推免研究生，在读研究生同学客座访问，博士毕业生申请博士后，请将简历发送至 yd.cui[at]siat.ac.cn
My group focuses on the engineering applications of reinforcement learning, specifically developing robust and efficient control algorithms for unmanned ships, unmanned vehicles, robots, and large-scale industrial automation systems operating in complex environments. I welcome undergraduate students, visiting students and postdoctoral researcher. Please send your resume to yd.cui[at]siat.ac.cn
工作和教育经历 Experiences & Education
2020 Apr - present,
副研究员 Associate Professor
中国科学院深圳先进技术研究院
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China.
2017 Oct - 2020 Mar,
博士后研究员 Post-doc Researcher
日本奈良先端科学技术大学院大学
Nara Institute of Science and Technology, Japan.
2014 Oct - 2017 Sep,
计算机科学博士 Ph. D in Computer Science
日本奈良先端科学技术大学院大学
Nara Institute of Science and Technology, Japan.
2012 Sep -2014 Sep,
计算机科学硕士 MEng in Computer Science
日本同志社大学
Doshisha University, Japan.
2008 Aug - 2012 Jul,
电子信息工程学士 BSc in Electronic Engineering
西安电子科技大学
Xidian University, China.
学术服务 Professional Memberships & Activities
Membership：
电气电子工程师学会 IEEE, 中国自动化学会 CAA, 中国计算机学会 CCF, 中国人工智能学会 CAAI
Editor:
Guest Editor, Special issue “Deformable object manipulation”, Frontiers in Neurorobotics
Guest Editor, Special issue “Embodied AI”, IEEE Robotics & Automation Magazine (RAM)
Associate Editor, IEEE International Conference on Robotics and Biomimetics (ROBIO) 2023
Associate Editor, IEEE International Conference on Robotics and Automation (ICRA) 2024
Associate Editor, IEEE International Conference on Robotics and Automation (ICRA) 2025
Associate Editor, IEEE International Conference on Robotics and Automation (ICRA) 2026
Committee：
IEEE International Conference on Advanced Robotics and Mechatronics (ICARM) 2019
承担项目 Research Fundings
- 国家自然科学基金青年项目 2022-2024
- 中国科学院人才择优项目 2021-2023
- 企业横向研究项目（华为）2023-2024
- 企业横向研究项目（中控技术）2024-
- 企业横向研究项目（兆威机电）2024-
团队成员 Team Members
博士1年级 D1
黄文俊 Wenjun Huang Google Scholar
硕士3年级 M3
江颖卓 Yingzhuo Jiang
孙明宇 Mingyu Sun
王惠琳 Huilin Wang
穆迪 Mohammad Mohammadi
硕士2年级 M3
刘光玉 Guangyu Liu
林荣墩 Rongdun Lin
硕士1年级 M1
谢岷烨 Minye Xie
梁旭 Xu Liang
毕业生 Alumni Students:
尚致违 Zhiwei Shang Google Scholar, Personal Page [PhD candidate at The Chinese University of Hong Kong Shenzhen]
李任行 Renxing Li [PhD candidate at Southern University of Science and Technology]
缪晨阳 Chenyang Miao Google Scholar, Personal Page [PhD candidate at Xi'an Jiaotong University]
主要论文 Selected Papers
- [J20] Mingrong Gong, Zhengkun Yi, Yidong Chen, Huiyun Li, and Yunduan Cui. “Reducing the Value Function Over-estimation by Kullback-Leibler Divergence Regularized Distributional Actor-Critic.” Applied Intelligence, 2025.(Corresponding Author)
- [J19] Wenjun Huang, Yunduan Cui, Huiyun Li, and Xinyu Wu. “Practical Reinforcement Learning using Time-efficient Model-based Policy Optimization.” IEEE Transactions on Automation Science and Engineering, 2025. (Corresponding Author)
- [J18] Wenjun Huang, Yunduan Cui, Huiyun Li, and Xinyu Wu. “Effective Probabilistic Neural Networks Model for Model-based Reinforcement Learning USV.” IEEE Transactions on Automation Science and Engineering, 2025. (Corresponding Author)
- [J17] Chenyang Miao, Yunduan Cui, Huiyun Li, and Xinyu Wu. “Efficient multi-agent reinforcement learning HVAC power consumption optimization.” Energy Reports, 2024. (Corresponding Author)
- [J16] Shangde Li, Wenjun Huang, Chenyang Miao, Kun Xu, Yidong Chen, Tianfu Sun, and Yunduan Cui. “Efficient Robot Manipulation via Reinforcement Learning with Dynamic Movement Primitives-Based Policy.” Applied Sciences, 2024. (Corresponding Author)
- [J15] Lei Xia, Yunduan Cui, Zhengkun Yi, Huiyun Li, and Xinyu Wu. “Estimating Lyapunov Region of Attraction for Robust Model-Based Reinforcement Learning USV.” IEEE Transactions on Automation Science and Engineering, 2024. (Corresponding Author)
- [J14] Wenjun Huang, Yunduan Cui, Huiyun Li, and Xinyu Wu. “Practical probabilistic model-based reinforcement learning by integrating dropout uncertainty and trajectory sampling.” IEEE Transactions on Neural Networks and Learning Systems, 2024. (Corresponding Author)
- [J13] Chenyang Miao, Yunduan Cui, Huiyun Li, and Xinyu Wu. “Effective multi-agent deep reinforcement learning control with relative entropy regularization.” IEEE Transactions on Automation Science and Engineering, 2024. (Corresponding Author)
- [J12] Zhiwei Shang, Renxing Li, Chunhua Zheng, Huiyun Li, and Yunduan Cui. “Relative Entropy Regularized Sample-Efficient Reinforcement Learning With Continuous Actions.” IEEE Transactions on Neural Networks and Learning Systems, 2023. (Corresponding Author)
- [J11] Renxing Li, Zhiwei Shang, Chunhua Zheng, Huiyun Li, Qing Liang, and Yunduan Cui. “Efficient Distributional Reinforcement Learning with Kullback-Leibler Divergence Regularization.” Applied Intelligence, 2023. (Corresponding Author)
- [J10] Yunduan Cui, Kun Xu, Chunhua Zheng, Jia Liu, Lei Peng, and Huiyun Li. “Flexible Unmanned Surface Vehicles Control using Probabilistic Model-based Reinforcement Learning with Hierarchical Gaussian Distribution.” Ocean Engineering, 2023.
- [J9] Jincheng Wang, Lei Xia, Lei Peng, Huiyun Li, and Yunduan Cui. “Efficient Uncertainty Propagation in Model-Based Reinforcement Learning Unmanned Surface Vehicle Using Unscented Kalman Filter.” Drones, 2023. (Corresponding Author)
- [J8] Yunduan Cui, Wenbo Shi, Huan Yang, Cuiping Shao, Lei Peng, and Huiyun Li. “Probabilistic Model-Based Reinforcement Learning Unmanned Surface Vehicles Using Local Update Sparse Spectrum Approximation.” IEEE Transactions on Industrial Informatics, 2023.
- [J7] Yunduan Cui, Lei Peng, and Huiyun Li. “Filtered Probabilistic Model Predictive Control-based Reinforcement Learning for Unmanned Surface Vehicles.” IEEE Transactions on Industrial Informatics, 2022.
- [J6] Yunduan Cui, Osaki Shigeki, and Takamitsu Matsubara. “Autonomous Boat Driving System using Sample-efficient Model Predictive Control-based Reinforcement Learning Approach.” Journal of Field Robotics, 2021.
- [J5] Yunduan Cui, Junichiro Ooga, Akihito Ogawa, and Takamitsu Matsubara. “Probabilistic Active Filtering with Gaussian Processes for Occluded Object Search in Clutter.” Applied Intelligence, 2020.
- [J4] Lingwei Zhu, Yunduan Cui, Go Takami, Hiroaki Kanokogi, and Takamitsu Matsubara. “Scalable Reinforcement Learning for Plant-wide Control of Vinyl Acetate Monomer Process.” Control Engineering Practice, 2020. (co-first author)