Haiyuan Gui

China University of Petroleum, East China, Qingdao University of Technology

Papers

Total Citations

H-Index

About

Dr. Haiyuan Gui is a rising researcher at the forefront of robotic manipulation and reinforcement learning, whose work bridges the gap between simulation and real-world dexterity. His primary research areas include cross-domain policy transfer, 6-DoF grasp pose detection, and efficient 3D perception for robotics. Dr. Gui’s most influential contribution, "Cross-domain policy adaptation with dynamics alignment" (2023, 7 citations), introduces a novel framework that enables robotic policies trained in simulation to adapt seamlessly to real-world environments by aligning dynamic discrepancies—a critical step toward robust sim-to-real transfer. In parallel, his work "GraspFast: Multi-stage lightweight 6-DoF grasp pose fast detection with RGB-D image" (2024, 6 citations) has garnered attention for its real-time, computationally efficient approach to grasp detection, making it suitable for resource-constrained robotic platforms. His latest paper, "High–performance grasp pose detection via point cloud serialization attention" (2025, 1 citation), further advances the field by leveraging attention mechanisms to serialize point cloud data, achieving state-of-the-art accuracy in grasp pose estimation. With a growing citation impact and a focus on practical, deployable solutions, Dr. Gui is establishing himself as a key contributor to the next generation of intelligent robotic systems.