Xinting Liao
Papers
1
Total Citations
1
H-Index
1
About
Xinting Liao is a rising researcher at the intersection of robotics, physics-informed machine learning, and deformable object manipulation. Their work focuses on the challenging problem of predicting and controlling the shape of deformable linear objects (DLOs)—such as cables, wires, and fibers—which are critical in applications ranging from manufacturing to medical robotics. Liao’s most-cited paper, "Physics-Informed Graph Learning for Shape Prediction in Robot Manipulate of Deformable Linear Objects" (2025), introduces a novel framework that integrates physical laws with graph neural networks to model the complex, nonlinear deformation behaviors of DLOs. This approach addresses a long-standing challenge in robotics: enabling accurate, real-time shape prediction for flexible objects, which is essential for tasks like automated assembly and surgical assistance. While still early in their career, with 1 citation on this key work, Liao’s contributions are already shaping the future of soft robotics and intelligent manipulation. Their innovative fusion of physics-based modeling and data-driven learning promises to unlock new capabilities in autonomous systems, making them a researcher to watch in the evolving field of deformable object robotics.
Research Focus
Key Achievements
Top Papers
- 1