Hongxing Liu
Papers
3
Total Citations
32
H-Index
3
About
Hongxing Liu is a researcher at the forefront of robotic manipulation and computer vision, with a focus on enabling intelligent, context-aware interaction between robots and their environments. His primary research areas include 6D object pose estimation, visual reasoning, and graph-based scene understanding for robotics. Liu’s most impactful contribution is the development of a Graph-Based Visual Manipulation Relationship Reasoning Network, which allows robots to reason about object relationships in cluttered, object-stacking scenes. This work, published in 2021 with 23 citations, addresses the critical challenge of determining a stable and logical manipulation order, moving beyond simple pick-and-place tasks to more advanced, context-driven robotic behavior. His earlier work on low-quality rendering-driven 6D object pose estimation from single RGB images, with 5 citations, explores practical, data-efficient methods for pose estimation, a key enabler for applications in robotic manipulation and virtual reality. By integrating graph neural networks with visual reasoning, Liu’s research provides a foundational framework for robots to understand and navigate complex, unstructured environments, marking a significant step toward more autonomous and intelligent robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3