Zekai Yin
Papers
2
Total Citations
15
H-Index
2
About
Zekai Yin is a researcher at the forefront of robotic perception, specializing in camera-to-robot pose estimation and spatial reasoning. His work addresses a fundamental challenge in robotics: enabling robots to accurately determine their own pose relative to a camera from a single-view image sequence, a task complicated by self-occlusions and visual ambiguity. Yin’s major contribution is the introduction of a robot structure prior guided temporal attention mechanism, which leverages the known kinematic structure of a robot to inform and constrain pose estimation across successive frames. This approach significantly improves accuracy and robustness in online, real-time settings. His most-cited paper, published in 2023, has already garnered 13 citations, reflecting its immediate impact on the field. By fusing geometric priors with deep temporal attention, Yin’s work bridges the gap between model-based and learning-based methods, offering a practical solution for robots interacting dynamically with their environment. His research is pivotal for applications in autonomous manipulation, human-robot collaboration, and visual servoing, marking him as a rising innovator in embodied AI and robotic vision.
Research Focus
Key Achievements
Top Papers
- 1
- 2