Papers
2
Total Citations
7
H-Index
2
About
Yonghui Xu is a researcher whose work bridges the critical gap between artificial intelligence and real-world robotic perception. His primary research areas center on transfer learning, domain adaptation, and deep neural networks, with a particular focus on enabling robots to operate intelligently in dynamic, changing environments. Xu’s major contributions lie in developing novel methods that allow robotic systems to adapt existing knowledge to new, unseen conditions—such as shifts in lighting or layout—without requiring complete retraining. His 2020 paper, "Domain Adaptation from Public Dataset to Robotic Perception Based on Deep Neural Network," has garnered 5 citations and addresses the fundamental challenge of how robots can understand their surroundings in a human-like manner by transferring knowledge from public datasets to specific operational contexts. Additionally, his 2018 work, "A Novel Transfer Metric Learning Approach Based on Multi-Group," with 2 citations, advances the field of transfer learning by proposing innovative techniques for moving knowledge from source to target domains. Through these efforts, Xu is helping to create more adaptable, efficient, and intelligent robotic systems that can seamlessly integrate into our daily lives.
Research Focus
Key Achievements
Top Papers
- 1
- 2A Novel Transfer Metric Learning Approach Based on Multi-Group2 citations · 2018