Yifu Tian

Hi there 👋

I'm Yifu Tian. I go by Joseph. I'm now working at Shanghai Jiao Tong University as a visiting student under the supervision of Prof. Tong Qin. I will join George Washington University in Fall 2026 as a Ph.D. student under the supervision of Prof. Chuchu Chen.

I received my B.Eng. in Electrical Computer Engineering from The Chinese University of Hong Kong in 2025.

Previously:

I was a visiting student at ICT@CAS.
I worked as a research assistant at AIRS.
I was also a visiting scholar at UIUC, Thomas M. Siebel Center for CS.
After graduating from CUHK-Shenzhen, I worked as a research assistant in FAST Lab@Zhejiang University.

Email / Google Scholar / GitHub / LinkedIn / Bilibili

Yifu (Joseph) Tian
Visiting Student@ SJTU
Incoming PhD student@ GWU
Email: josepht@gwmail.gwu.edu

News

March, 2026: I started my internship at Shanghai Jiao Tong University.
June, 2025: I received B.Eng. in Electrical Computer Engineering from The Chinese University of Hong Kong.

Publications

Topological Motion Planning Diffusion: Generative Tangle-Free Path Planning for Tethered Robots in Obstacle-Rich Environments
Yifu Tian, Xinhang Xu, Thien-Minh Nguyen, Muqing Cao
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026(Under Review)
Paper / Video / Code /
In extreme environments, tethered robots require continuous navigation while avoiding cable entanglement. Traditional planners struggle in these lifelong planning scenarios due to topological unawareness, while topology-augmented graphsearch methods face computational bottlenecks in obstaclerich environments where the number of candidate topological classes increases. To address these challenges, we propose Topological Motion Planning Diffusion (TMPD), a novel generative planning framework that integrates lifelong topological memory. Benchmarking in obstacle-rich simulated environments demonstrates that TMPD achieves a collision-free reach of 100% and a tangle-free rate of 97.0%, outperforming traditional topological search and purely kinematic diffusion baselines in both geometric smoothness and computational efficiency. Simulation with AGX-Dynamics for unity further validates the practicality of the proposed approach.

Education