Xinghao Zhu
Papers
1
Total Citations
62
H-Index
1
About
Xinghao Zhu is a robotics researcher whose work sits at the intersection of robot learning, deformable object manipulation, and neural network-based modeling. His most recognized contribution, "Offline-Online Learning of Deformation Model for Cable Manipulation With Graph Neural Networks" (2022), has garnered 62 citations and exemplifies his focus on equipping robots with the ability to handle flexible, real-world objects such as cables and wires — challenges with direct relevance to manufacturing automation and medical robotics. In this work, Zhu proposes a hybrid offline-online learning framework that leverages Graph Neural Networks to accurately predict the deformation dynamics of deformable linear objects, enabling more robust and adaptive robotic control. By combining the generalization power of offline training with the adaptability of online learning, his approach bridges a critical gap between simulation and real-world deployment. Zhu's research addresses one of manipulation robotics' most enduring challenges — the unpredictability of non-rigid objects — and his early citation impact signals growing recognition within the robotics community. His contributions are particularly valuable for researchers and engineers working on intelligent, dexterous robotic systems in complex, unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1