Sibo Qiao

China University of Petroleum, East China, Tianjin Polytechnic University

Papers

Total Citations

H-Index

About

Sibo Qiao is a researcher advancing the frontiers of robotic manipulation and reinforcement learning. His work primarily spans cross-domain policy adaptation and high-performance robotic grasping. In his influential 2023 paper, "Cross-domain policy adaptation with dynamics alignment," Qiao introduced a novel framework that enables robots to transfer learned policies across environments with differing dynamics—a critical step toward generalizable, real-world deployment. This work has garnered 7 citations, signaling its growing impact on the field of transfer learning in robotics. More recently, in 2025, Qiao proposed "High-performance grasp pose detection via point cloud serialization attention," a method that leverages attention mechanisms on point cloud data to achieve precise and efficient grasp pose detection. This contribution promises to enhance the reliability of robotic systems in unstructured settings. Through these efforts, Qiao is helping to bridge the gap between simulated training and physical robot performance, making autonomous manipulation more robust and adaptable.