Fangtai Guo
Papers
2
Total Citations
17
H-Index
2
About
Fangtai Guo is a rising researcher in computer vision and robotics, whose work centers on bridging the gap between structured knowledge and real-world perception. His primary research areas include 6D object pose estimation, robotic grasping, and human-robot interaction, with a particular focus on enabling machines to understand and manipulate objects without relying on exact CAD models. Guo’s most significant contribution is the development of KGNet (Knowledge-Guided Networks), a novel framework for category-level 6D object pose and size estimation. This work, published in 2023 and already garnering 15 citations, addresses a critical limitation in robotic manipulation by leveraging prior knowledge to generalize across object instances, moving beyond the traditional dependence on precise 3D models. Additionally, his 2025 paper on referring expression comprehension in semi-structured human-robot interaction explores how robots can interpret natural language commands in dynamic environments, further advancing intuitive human-robot collaboration. Guo’s research is particularly impactful for applications in automation, assistive robotics, and industrial manipulation, where adaptability and robustness are paramount. His work represents an important step toward more intelligent, context-aware robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2