Xiaofang Zhou

Hong Kong University of Science and Technology

Papers

Total Citations

H-Index

About

Xiaofang Zhou is a leading researcher at the intersection of artificial intelligence, robotics, and spatial computing, with a primary focus on enabling intelligent agents to perceive, navigate, and reason within complex, real-world environments. Her most impactful work centers on **Embodied AI**, where she pioneered the construction of scene-driven multimodal knowledge graphs. This groundbreaking approach, detailed in her 2024 paper (38 citations), allows robots to move beyond simple object recognition to understand the rich, contextual relationships within a scene—a critical step for autonomous decision-making. Complementing this, Zhou has made significant contributions to **autonomous navigation** in unstructured terrains. Her PUTN framework (2022, 3 citations) introduces a novel plane-fitting method that allows ground robots to traverse rough, uneven outdoor landscapes, directly addressing a key limitation of traditional 2D navigation systems. With a career spanning foundational algorithms for surface pathfinding (2005, 8 citations) to cutting-edge AI for embodied agents, Zhou’s work is defining how robots can intelligently interact with and serve humans in the physical world.