Home
Shiyu Zhao
Associate Professor
Director of the WINDY Lab, Associate Head of Department
Department of Artificial Intelligence, School of Engineering
Westlake University, Hangzhou, China
Email: zhaoshiyu[AT]westlake.edu.cn
Welcome to my homepage! More information about my research group (WINDY Lab) can be found at https://shiyuzhao.westlake.edu.cn
Bio: Shiyu Zhao is currently an Associate Professor in the Department of Artificial Intelligence in the School of Engineering at Westlake University. He is the founder and director of the Intelligent Unmanned Systems Laboratory (WINDY Lab). His research interests lie in the theories of estimation, control, and reinforcement learning and their applications to intelligent robotic systems especially multi-robot systems and micro aerial vehicles. He was selected as one of the World's Top 2% Scientists by Stanford University, and simultaneously entered both the "Career-long impact" and "Single-year impact" ranks (his rank is top 0.2%=250/113,906 in the subfield). He is currently an Associate Editor for the journals of IEEE Robotics and Automation Letters, International Journal of Robust and Nonlinear Control, and Unmanned Systems. He used to serve as Associate Editors for quite a few international conferences such as IEEE ICRA, IROS, CDC, ACC, ICCA, and ICUAS, and a member of the IEEE Control Systems Society Conference Editorial Board Committee. He was the UK Regional Chair of ICCA2018 and Program Chair of ICCA2019. His new textbook "Mathematical Foundations of Reinforcement Learning" is jointly published by Tsinghua University Press and Springer Nature Press. The textbook as received 3,500+ stars on GitHub and the open course has recieved 1,000,000 views over the Internet.
Shiyu Zhao received his BE and ME degrees from Beijing University of Aeronautics and Astronautics in 2006 and 2009, respectively. He got his PhD degree in Electrical Engineering from the National University of Singapore in 2014. He was a postdoc researcher at the Technion - Israel Institute of Technology and University of California, Riverside from 2014 to 2016. In 2016, he became a Lecturer in Aerospace Systems in the Department of Automatic Control at the University of Sheffield, UK. He joined Westlake University in 2019.
Highlight:
(Sep 2024) World's Top 2% Scientists: I was selected as one of the World's Top 2% Scientists by Stanford University. I simultaneously entered both the "Career-long impact" and "Single-year impact" ranks. My rank is top 0.2%=250/113,906 in the subfield.
(Jul 2024) English open course: My English open course on reinforcement learning is online now! You are welcome to check our YouTube channel or GitHub homepage. The Chinese version of the open course has received 1,000,000 views over the Internet has received very good feedback from the readers.
(May 2024) IEEE-TRO paper: Our latest work "Keypoint-Guided Efficient Pose Estimation and Domain Adaptation for Micro Aerial Vehicles" has been accepted for publication by IEEE Transactions on Robotics. More details can be found on my publication page.
(Mar 2024) Our GitHub: Most of the code of our research work can be found in our GitHub page! Welcome to check https://github.com/WestlakeIntelligentRobotics
(Feb 2024) IEEE-TASE paper: Our research work "Domain adaptive detection of MAVs: A benchmark and noise suppression network" has been accepted for publication by IEEE Transactions on Automation Science and Engineering. The paper will be online soon.
(Jan 2024) Multiple papers: We got three research articles accepted for publication lately by IEEE Transactions on Automation Science and Engineering, IEEE Transactions on Intelligent Transportation Systems, and New Journal of Physics, respectively.
(Jan 2024) My RL course: a student from the UC Davis emailed me and would like to share the notes he made when he studied my RL textbook. You are welcome to visit: link
(Jan 2024) IJRR paper: Our recent work about vision-based target motion estimation has been officially accepted by the International Journal of Robotics Research.
(Nov 2023) Our first LLM work: Our first research work about large language models is online. arXiv link Paper website
(Sep 2023) Source code available: The source code of our Nature Communications work on robotic swarms is uploaded online: GitHub
(Sep 2023) AE for IEEE-RAL: I recently became an Associate Editor for IEEE Robotics and Automation Letters. This journal has a very efficient and high-standard reviewing process. High-quality robotics-related submissions are welcome.
(Sep 2023) 1000+ stars: My textbook "Mathematical foundation of reinforcement learning" has received more than 1000 stars in GitHub.
(Aug 2023) Textbook major update: The second version of the draft of my textbook "Mathematical foundation of reinforcement learning" is online now!! Compared to the first version, which was online one year ago, the second version has been improved in various ways. It is almost the same as the printed version. See the GitHub page for details.
(Jun 2023) Nature Communications: Our recent research work entitled "Mean-shift exploration in shape assembly of robot swarms" has been published by Nature Communications: https://www.nature.com/articles/s41467-023-39251-5 (June, 2023)
(Dec 2022) Lecture videos: My new lecture videos and slides on the course "Mathematical Foundations of Reinforcement Learning" are online now. For the videos (in Chinese), please check: https://space.bilibili.com/2044042934
(Aug 2022) Textbook: My new textbook (draft) entitled "Mathematical Foundations of Reinforcement Learning" is online now. The GitHub homepage of this book is here. This book aims to provide a mathematical but friendly introduction to the fundamental concepts, basic problems, and classical algorithms in reinforcement learning.
Media channels: Our YouTube and Bilibili video channels are open! Welcome to check our videos out.