Xiao Song

Beihang University

Papers

2

Total Citations

39

H-Index

2

About

Xiao Song is a leading researcher in pedestrian trajectory prediction, a field critical for autonomous driving, service robotics, and assistive navigation. Their work centers on modeling complex spatio-temporal interactions and addressing the inherent uncertainty of pedestrian motion. In their highly cited 2022 paper (37 citations), Song introduced a novel Spatio-Temporal Interaction Aware and Trajectory Distribution Aware Graph Convolution Network, which simultaneously captures how pedestrians influence each other over time and predicts multiple plausible future paths. This dual-awareness approach marked a significant advance over single-trajectory models. More recently, in 2023, Song expanded into multimodal perception with a Convolutional Transformer Network that fuses depth maps and 3D pose data from first-person video to predict pedestrian locations. By integrating graph-based reasoning with transformer architectures, Song is pushing the boundaries of safe, human-aware navigation. Their work has immediate implications for reducing accidents in autonomous systems and improving mobility for visually impaired individuals, establishing Song as a key innovator in intelligent transportation and human-robot interaction.

Research Focus

Key Achievements

2
H-Index
2
Papers
39
Total Citations
20
Avg Citations/Paper
🏆 Most Cited Paper
Spatio-Temporal Interaction Aware and Trajectory Distribution Aware Graph Convolution Network for Pedestrian Multimodal Trajectory Prediction
37 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 5
🏛 Institutions: Beihang University

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago