Papers
3
Total Citations
13
H-Index
2
About
Xinzhou Xu is a rising researcher at the forefront of surgical robotics and medical AI, whose work bridges the critical gap between intelligent perception and dexterous robotic control. His primary research areas span semantic segmentation for surgical instruments, motion estimation for cable-driven manipulators, and kinematics modelling for continuum robots. Xu’s major contributions include pioneering a structural similarity-based partial activation network that enables accurate cross-scene segmentation of surgical instruments—a vital capability for guiding robots in unknown operating environments. He has also advanced motion control for cable-driven end-effectors by integrating parallel 1D-convolution with recurrent neural networks and attention mechanisms, effectively addressing the nonlinear challenges inherent in these systems. His most cited work (2024, 8 citations) on cross-scene segmentation directly tackles the real-world problem of insufficient training data in novel surgical scenes. Additionally, Xu has developed a transformer-based segmented learning approach for modelling the complex kinematics of cable-driven parallel continuum robots, offering a data-driven alternative to traditional theoretical models. With all his highly cited papers published in 2024, Xu demonstrates exceptional momentum and is quickly establishing himself as a key innovator in intelligent surgical systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3