This page in Swedish

Yufei Zhu

Yufei Zhu Position: Doctoral Student School/office: School of Science and Technology

Email: eXVmZWkuemh1O29ydS5zZQ==

Phone: +46 19 301005

Room: T1227

Yufei Zhu

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

Publications

Articles in journals |  Conference papers | 

Articles in journals

Conference papers