Huaxia Xia
Papers
2
Total Citations
232
H-Index
2
About
Huaxia Xia is a researcher specializing in autonomous systems, social robot navigation, and human motion prediction, with a particular focus on developing intelligent models that enable machines to understand and anticipate human behavior in complex environments. His work centers on spatio-temporal deep learning, graph neural networks, and attention mechanisms applied to pedestrian trajectory forecasting — a critical challenge in building safe autonomous robots and vehicles. Xia's most recognized contribution is AST-GNN (2021), an attention-based spatio-temporal graph neural network designed to model interaction-aware pedestrian trajectory prediction. This work has accumulated an impressive 196 citations, reflecting its significant influence on the autonomous navigation and computer vision communities. Complementing this, his Tra2Tra framework introduces a trajectory-to-trajectory prediction paradigm using global social spatial-temporal attention, further advancing the field's ability to handle the subtle, complex interactions found in crowded real-world scenes. Through these contributions, Xia has helped push the boundaries of how robots perceive and predict human movement, addressing one of the most nuanced challenges in collision-free path planning. His research is particularly valuable for students and practitioners working at the intersection of deep learning, robotics, and human-computer interaction.
Research Focus
Key Achievements
Top Papers
- 1
- 2