Xiaofan Zhu
Papers
2
Total Citations
7
H-Index
2
About
Xiaofan Zhu is a researcher at the intersection of human-robot interaction and intuitive interface design, with a primary focus on developing sketch-based systems for robotic manipulation. Zhu’s major contribution lies in bridging the gap between novice users and complex robot task planning through affordance-driven interfaces. In their most cited work, "Sketching Affordances for Human-in-the-loop Robotic Manipulation Tasks" (2019, 5 citations), Zhu pioneered methods for extracting task-relevant geometries from 3D point clouds using simple sketches, enabling users to generate affordance files for constrained object manipulation. This approach, further refined in "A Sketch-Based System for Human-Guided Constrained Object Manipulation" (2019, 2 citations), democratizes robot programming by allowing even non-experts to guide robots through sketch-based task planning. Zhu’s work directly addresses the challenge of making robotic systems accessible and adaptable in real-world settings, emphasizing human-in-the-loop control. By reducing the technical barriers to robot interaction, Zhu’s contributions have implications for manufacturing, assistive robotics, and collaborative automation, where intuitive human guidance is critical for safe and efficient task execution.
Research Focus
Key Achievements
Top Papers
- 1Sketching Affordances for Human-in-the-loop Robotic Manipulation Tasks5 citations · 2019
- 2A Sketch-Based System for Human-Guided Constrained Object Manipulation2 citations · 2019