Papers
1
Total Citations
2
H-Index
1
About
Qiao Liang is a rising researcher in robotics and computer vision, whose work centers on self-supervised learning for articulated object understanding—a critical challenge for enabling robots to interact with real-world environments. His most cited paper, "SM<sup>3</sup>: Self-supervised Multi-task Modeling with Multi-view 2D Images for Articulated Objects" (2024, 2 citations), tackles the problem of reconstructing objects and estimating their movable joint structures without reliance on expensive annotated datasets. By leveraging multi-view 2D images in a self-supervised framework, Liang’s approach breaks free from the constraints of supervised methods that are limited to predefined object categories, offering a scalable path for robots to perceive and manipulate diverse articulated objects like doors, drawers, and tools. Though early in his career, this work demonstrates his commitment to reducing data dependency in robotics, a key bottleneck for real-world deployment. His research promises to advance autonomous systems in household and industrial settings, where adaptability to novel objects is essential.
Research Focus
Key Achievements
Top Papers
- 1