Yufei Zhu
Yufei Zhu Position: Doctoral Student School/office: School of Science and TechnologyEmail: eXVmZWkuemh1O29ydS5zZQ==
Phone: +46 19 301005
Room: T1227
About Yufei Zhu
Welcome to my personal page.
I am Yufei Zhu, a final-year doctoral student at the Robot Navigation & Perception Lab, Örebro University in Sweden, under the supervision of Martin Magnusson, with co-supervision by Andrey Rudenko (TUM), Tomasz P. Kucner (Aalto University), and Achim J. Lilienthal (TUM). I am working on the EU horizon 2020 project DARKO and affiliated with Wallenberg AI, Autonomous Systems and Software Program (WASP).
My research focuses on learning probabilistic representations of human motion patterns (maps of dynamics) that encode environment-level spatio-temporal dynamics, enabling long-term human motion prediction and human-aware robot navigation. I advance these representations through implicit neural representations for continuous spatio-temporal motion fields, online adaptation to evolving environments, and integration into generative models such as flow matching, toward controllable multi-modal trajectory generation.
Internships and Research Experience:
- 2026 Mar – 2026 Aug: Visiting PhD Student at UC San Diego, USA. Working on controllable generative models for human motion generation under physical constraints.
- 2025 Jan – 2025 Mar: Research Intern at Miraikan Accessibility Lab, Tokyo, Japan. Worked on robot navigation through dense human crowds, aligning with compatible crowd flows for safe and efficient navigation.
- 2024 Mar – 2024 Sep: Research Intern at Robert Bosch GmbH Corporate Research, Stuttgart, Germany. Worked on online learning of human motion patterns in changing environments.
Research topics:
- Human Motion Prediction
- Spatiotemporal Pattern Learning
- Probabilistic Modeling
- Neural Implicit Representations
- Generative Modeling
Research projects
Active projects
Research groups
Publications
Articles in journals
- Zhu, Y. , Rudenko, A. , Kucner, T. P. , Lilienthal, A. J. & Magnusson, M. (2025). Long-Term Human Motion Prediction Using Spatio-Temporal Maps of Dynamics. IEEE Robotics and Automation Letters, 10 (11), 12229-12236. [BibTeX]
- Schreiter, T. , Almeida, T. R. d. , Zhu, Y. , Gutiérrez Maestro, E. , Morillo-Mendez, L. , Rudenko, A. , Palmieri, L. , Kucner, T. P. & et al. (2025). THÖR-MAGNI: A large-scale indoor motion capture recording of human movement and robot interaction. The international journal of robotics research, 44 (4). [BibTeX]
- Almeida, T. R. d. , Zhu, Y. , Rudenko, A. , Kucner, T. P. , Stork, J. A. , Magnusson, M. & Lilienthal, A. J. (2024). Trajectory Prediction for Heterogeneous Agents: A Performance Analysis on Small and Imbalanced Datasets. IEEE Robotics and Automation Letters, 9 (7), 6576-6583. [BibTeX]
Conference papers
- Zhu, Y. , Rudenko, A. , Palmieri, L. , Heuer, L. , Lilienthal, A. & Magnusson, M. (2025). Fast Online Learning of CLiFF-Maps in Changing Environments. In: Ott, C, IEEE International Conference on Robotics and Automation Proceedings. Paper presented at 2025 IEEE International Conference on Robotics and Automation (ICRA 2025), Atlanta, USA, May 19-23, 2025. (pp. 10424-10431). Institute of Electrical and Electronics Engineers Inc.. [BibTeX]
- Zhu, Y. , Fan, H. , Rudenko, A. , Magnusson, M. , Schaffernicht, E. & Lilienthal, A. (2024). LaCE-LHMP: Airflow Modelling-Inspired Long-Term Human Motion Prediction By Enhancing Laminar Characteristics in Human Flow. In: 2024 IEEE International Conference on Robotics and Automation (ICRA). Paper presented at IEEE International Conference on Robotics and Automation (ICRA 2024), Yokohama, Japan, May 13-17, 2024. (pp. 11281-11288). IEEE. [BibTeX]
- Zhu, Y. , Rudenko, A. , Kucner, T. , Palmieri, L. , Arras, K. , Lilienthal, A. & Magnusson, M. (2023). CLiFF-LHMP: Using Spatial Dynamics Patterns for Long-Term Human Motion Prediction. In: 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 01-05 October 2023, Detroit, MI, USA. Paper presented at 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2023), Detroit, MI, USA, October 1-5, 2023. (pp. 3795-3802). IEEE. [BibTeX]