Zewen Yang

AI Researcher ｜ Robotic Control Engineer

prof_pic_zewen.jpg

I am a Senior Research Scientist at Agile Robots in Munich, working on agentic frameworks and world models for robotic manipulation.

Previously, I was a postdoctoral researcher at the Munich Institute of Robotics and Machine Intelligence (MIRMI), supervised by Prof. Sami Haddadin and Dr. Hamid Sadeghian. Before that, in the aftermath of the pandemic, I joined the Robert Koch Institute as a postdoctoral researcher, working on AI for public health research. I did my Ph.D. research in Control Science & Engineering at the Technical University of Munich and Harbin Engineering University, where I was supervised by Prof. Sandra Hirche and Prof. Zheping Yan and worked closely with Dr. Stefan Sosnowski.

My work lies at the intersection of Machine Learning and Robotics, driven by a strong interest in machine intelligence and the emerging technologies that make everyday life better and work more efficient. I enjoy moving between building methods that hold up in the real world and exploring the deeper scientific questions behind them. I also care deeply about education and research, and find it especially rewarding to work alongside passionate people and ambitious students, growing together with them.

I am always glad to connect with others who share these interests, whether for collaboration, projects, research, or simply a good conversation. Feel free to reach out.

News

Aug 05, 2026 Our paper Whom to Trust? Selective Online Learning in Multi-Agent Systems with Prior-Aware Gaussian Process Regression, the extended journal version of our AAMAS conference paper, has been accepted to JAAMAS! ✨
Jun 17, 2026 Two of our papers have been accepted to IROS 2026! 🚀
May 15, 2026 Our paper RCM Constraint-Consistent Dynamic Control in Surgical Robots has been selected as a finalist for the Best Paper Award in Medical Robotics at ICRA 2026! 🏆 (see the award finalists)
Apr 16, 2026 Our paper Residual Reinforcement Learning for Robot Teleoperation under Stochastic Delays has been accepted to the IFAC World Congress 2026! 🎉
See all news →

Blog

Jun 19, 2026 PPO vs SAC: the two default go-to RL algorithms in continuous control
See all blog →

Selected publications

  1. AAAI
    Streaming Generated Gaussian Process Experts for Online Learning and Control
    Zewen Yang, Dongfa Zhang, Xiaobing Dai, Fengyi Yu, Chi Zhang, Bingkun Huang, Hamid Sadeghian, and Sami Haddadin
    In Proceedings of the AAAI Conference on Artificial Intelligence, Mar 2026
    Oral presentation (acceptance rate 17.6%)
    DOI Code
  2. IEEE/CAA JAS
    Quality or Quantity? Error-Informed Selective Online Learning with Gaussian Processes in Multi-Agent Systems
    Zewen Yang, Xiaobing Dai, Jiajun Cheng, Yulong Huang, and Peng Shi
    IEEE/CAA Journal of Automatica Sinica, 2026
    Impact factor: 18.3, JCR: Q1
    DOI Code
  3. JAAMAS
    Whom to Trust? Selective Online Learning in Multi-Agent Systems with Prior-Aware Gaussian Process Regression
    Zewen Yang, Xiaobing Dai, Akshat Dubey, Yansong Wu, Xiao Chen, Ebebezer Oladimeji, and Sandra Hirche
    Autonomous Agents and Multi-Agent Systems, 2026
    Accepted. Impact factor: 2.4, JCR: Q2
    Code
  4. IROS
    Safe Consensus of Cooperative Manipulation with Hierarchical Event-Triggered Control Barrier Functions
    Simiao Zhuang, Bingkun Huang, and Zewen Yang†
    In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2026
    Oral presentation (acceptance rate 36%)
    arXiv Website
  5. IROS
    Safe-Night VLA: Seeing the Unseen via Thermal-Perceptive Vision-Language-Action Models for Safety-Critical Manipulation
    Dian Yu, Qingchuan Zhou, Bingkun Huang, Majid Khadiv, and Zewen Yang†
    In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2026
    Oral presentation (acceptance rate 36%)
    arXiv
  6. IFAC
    Residual Reinforcement Learning for Robot Teleoperation under Stochastic Delays
    Kaize Deng and Zewen Yang†
    In IFAC World Congress, 2026
    Poster presentation
    arXiv
  7. ICRA
    RCM Constraint-Consistent Dynamic Control in Surgical Robots
    Yu Li, Hamid Sadeghian, Zewen Yang, Valentin Le Mesle, and Sami Haddadin
    In Proceedings of the IEEE International Conference on Robotics and Automation, 2026
    Oral presentation (top 1% in submissions)
    Best Paper Finalist arXiv Website
  8. ICRA
    Contact-Safe Reinforcement Learning with ProMP Reparameterization and Energy Awareness
    Bingkun Huang, Yuhe Gong, Zewen Yang, Tianyu Ren, and Luis Figueredo
    In IEEE International Conference on Robotics and Automation (ICRA), 2026
    Poster presentation (acceptance rate 38.04%)
    DOI
  9. IEEE JSTSP
    Machine Learning based Controller using Gaussian Process Regression in Electric Motors: Interpretability, Safety and Reliability
    Zhenxiao Yin, Xiaobing Dai, Zewen Yang, Dianxun Xiao, Filippo Menolascina, Sandra Hirche, and Hang Zhao
    IEEE Journal of Selected Topics in Signal Processing, 2026
    Impact factor: 13.7, JCR: Q1
    DOI
  10. AAAI
    Asynchronous Distributed Gaussian Process Regression
    Zewen Yang, Xiaobing Dai, and Sandra Hirche
    In Proceedings of the AAAI Conference on Artificial Intelligence, Apr 2025
    Poster presentation (acceptance rate 23.4%)
    DOI Code
  11. EAAI
    Safe event-triggered control of unmanned surface vehicles with Gaussian processes: Resilience in denial of service attacks and uncertain dynamics
    Zewen Yang, Xiaobing Dai, Liang Fang, Jiajia Zhou, and Zheping Yan
    Engineering Applications of Artificial Intelligence, 2025
    Impact factor: 9.0, JCR: Q1
    DOI
  12. IEEE TNNLS
    Cooperative Online Learning for Multiagent System Control via Gaussian Processes With Event-Triggered Mechanism
    Xiaobing Dai, Zewen Yang†, Sihua Zhang, Di-Hua Zhai, Yuanqing Xia, and Sandra Hirche
    IEEE Transactions on Neural Networks and Learning Systems, 2025
    Impact factor: 9.7, JCR: Q1
    DOI
  13. IEEE/ASME TMECH
    Torque-Induced-Overshoot Reduction Inspired Compensator for PMSMs Using Motor-Physics Embedded Gaussian Process Regression
    Zhenxiao Yin, Xiaobing Dai, Zewen Yang, Yang Shen, Fang Li, Dianxun Xiao, and Hang Zhao
    IEEE/ASME Transactions on Mechatronics, 2025
    Impact factor: 6.3, JCR: Q1
    DOI
  14. AAMAS
    Whom to Trust? Elective Learning for Distributed Gaussian Process Regression
    Zewen Yang, Xiaobing Dai, Akshat Dubey, Sandra Hirche, and Georges Hattab
    In Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Auckland, New Zealand, 2024
    Oral presentation (acceptance rate: 23.4%)
    HTML Code
  15. ACC
    Cooperative Learning with Gaussian Processes for Euler-Lagrange Systems Tracking Control Under Switching Topologies
    Zewen Yang, Songbo Dong, Armin Lederer, Xiaobing Dai, Siyu Chen, Stefan Sosnowski, Georges Hattab, and Sandra Hirche
    In 2024 American Control Conference (ACC), 2024
    Oral presentation
    DOI
  16. CCC
    Kernel-based Learning for Safe Control of Discrete-Time Unknown Systems under Incomplete Observations
    Zewen Yang, Xiaobing Dai, Weijie Yang, Bahar Ilgen, Aleksandar Anzel, and Georges Hattab
    In 2024 43rd Chinese Control Conference (CCC), 2024
    Oral presentation
    DOI
  17. EJC
    Decentralized event-triggered online learning for safe consensus control of multi-agent systems with Gaussian process regression
    Xiaobing Dai, Zewen Yang†, Mengtian Xu, Sihua Zhang, Fangzhou Liu, Georges Hattab, and Sandra Hirche
    European Journal of Control, 2024
    Impact Factor: 2.6, JCR: Q2
    DOI
  18. IEEE TAC
    Cooperative Control of Uncertain Multiagent Systems via Distributed Gaussian Processes
    Armin Lederer, Zewen Yang, Junjie Jiao, and Sandra Hirche
    IEEE Transactions on Automatic Control, 2023
    Impact factor: 7.0, JCR: Q1
    DOI
  19. L4DC
    Can Learning Deteriorate Control? Analyzing Computational Delays in Gaussian Process-Based Event-Triggered Online Learning
    Xiaobing Dai, Armin Lederer, Zewen Yang, and Sandra Hirche
    In Proceedings of The 5th Annual Learning for Dynamics and Control Conference, 15–16 jun 2023
    Poster presentation (acceptance rate: 67.6%)
    PDF
  20. IECON
    Learning-based Control for PMSM Using Distributed Gaussian Processes with Optimal Aggregation Strategy
    Zhenxiao Yin*, Xiaobing Dai*, Zewen Yang*, Yang Shen, Georges Hattab, and Hang Zhao
    In IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society, 2023
    Oral presentation
    DOI
  21. CDC
    Distributed Learning Consensus Control for Unknown Nonlinear Multi-Agent Systems based on Gaussian Processes
    Zewen Yang, Stefan Sosnowski, Qingchen Liu, Junjie Jiao, Armin Lederer, and Sandra Hirche
    In 2021 60th IEEE Conference on Decision and Control (CDC), 2021
    Oral presentation
    DOI
  22. OE
    Virtual leader based path tracking control for Multi-UUV considering sampled-data delays and packet losses
    Zheping Yan, Zewen Yang†, Xiaoli Pan, Jiajia Zhou, and Di Wu
    Ocean Engineering, 2020
    Impact factor: 6.3, JCR: Q1
    DOI
    41 Google Scholar citations
  23. OE
    Discrete-time coordinated control of leader-following multiple AUVs under switching topologies and communication delays
    Zheping Yan, Zewen Yang†, Lidong Yue, Lu Wang, Heming Jia, and Jiajia Zhou
    Ocean Engineering, 2019
    Impact factor: 6.3, JCR: Q1
    DOI
    111 Google Scholar citations
  24. OCEANS
    Coordinated Control for Trajectory Tracking of Multiple UUVs with Input Saturation
    Zheping Yan, Zewen Yang†, Anzuo Jiang, Yanbin Teng, Xiangling Liu, and Shilin Wei
    In OCEANS 2019 - Marseille, 2019
    Oral presentation
    DOI
  25. CCC
    Diving Control of Underactuated UUV Based on Backstepping Upper Bound Sliding Mode Method
    Zheping Yan, Zewen Yang†, Gengshi Zhang, Jiajia Zhou, Xiaoli Pan, and Lidong Yue
    In 2019 Chinese Control Conference (CCC), 2019
    Oral presentation
    DOI
  26. IECON
    Discrete-time Path Tracking Control of Multiple UUVs Based on Virtual Leader under Time Varying Delay
    Zheping Yan, Zewen Yang†, Di Wu, Lu Wang, Yi Wu, and Jiyun Li
    In IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society, 2018
    Oral presentation
    DOI
  27. CCC
    Horizontal Trajectory Tracking Control of AUV Using a Two-way Channel High Gain Observer
    Zheping Yan, Zewen Yang†, Jiajia Zhou, Lu Wang, and Heming Jia
    In 2018 37th Chinese Control Conference (CCC), 2018
    Oral presentation
    DOI
See all publications →