Xiaoyi Qu

Beijing Academy of Artificial Intelligence, Chinese Academy of Sciences

Papers

Total Citations

H-Index

About

Xiaoyi Qu is a robotics researcher whose work bridges learning, perception, and control for complex manipulation and mobile navigation. Her primary research areas include learning from demonstration (LfD), reinforcement learning for motion planning, and sensor-based robotic assembly. A key contribution is her development of task-parameterized dynamic movement primitives integrated with reinforcement learning, enabling mobile robots to adapt online to unstructured environments and varying obstacle shapes—a significant advance over traditional offline LfD methods. Her work on designing robot systems for reorienting and assembling irregular parts (including screws, washers, and nuts) addresses critical challenges in manufacturing, particularly precise orientation using vision and force sensors. With each of her most-cited papers accumulating 2 citations in their first year, Qu’s research is gaining recognition for its practical impact on adaptive motion planning and flexible automation. Her contributions are particularly valuable for students and researchers interested in combining learning algorithms with real-world robotic dexterity and assembly tasks.