Papers
3
Total Citations
16
H-Index
3
About
Zeyuan Xu is a researcher advancing the frontiers of intelligent control, nonlinear systems, and autonomous navigation. Their work is distinguished by a focus on integrating machine learning with robust control theory to address real-world challenges in data privacy, system uncertainty, and computational efficiency. A key contribution is the development of a personalized federated learning-based distributed model predictive control (PFL-DMPC) method, which preserves data privacy while achieving superior control performance for nonlinear networked systems—a paper that has already garnered 7 citations since its 2025 publication. Xu has also made significant strides in robust control for Markov jump nonlinear systems, tackling the complexities of incomplete transition probabilities and uncertain packet dropouts using fuzzy-model-based approaches (6 citations). In the domain of autonomous navigation, Xu introduced RWKV-VIO, an end-to-end deep network for visual-inertial odometry that offers an efficient, low-drift alternative to traditional LSTM and Transformer-based methods (3 citations). This work addresses critical bottlenecks in temporal modeling for robotics. Collectively, Xu’s research demonstrates a powerful synergy between theoretical rigor and practical deployment, making notable contributions to the fields of networked control systems and embodied AI.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3