Trajectory Prediction Model of Attention Network Based on Space-Time Graph

DOI

10.2991/978-94-6463-821-9_89How to use a DOI?

Keywords

Autonomous Driving; Artificial Intelligence; Trajectory Prediction; Stgamt Model

Abstract

The recent development of autonomous driving has been obvious to all showcasing its potential to revolutionize the transportation industry. Central to this transformation is artificial intelligence (AI), which serves as the driving force behind the development of safe, efficient, and reliable autonomous systems. While traditional five classical models have laid the groundwork for autonomous operations, they struggle to address the dynamic and complex challenges posed by real-world driving environments. As the focus shifts from low-level automation, such as toward highly automated or fully autonomous driving systems, the need for innovative and precise modeling approaches has grown exponentially. To address these challenges, researchers have increasingly turned to advanced trajectory prediction models, a critical component for anticipating the behavior of surrounding vehicles, cyclists, and pedestrians. STGAMT (Spatio-Temporal Graph Attention Motion Transformer) trajectory prediction model represents a significant breakthrough. By leveraging cutting-edge AI techniques, STGAMT enhances the ability to predict motion trajectories with unparalleled accuracy, thereby improving the safety, reliability, and overall performance of autonomous vehicles in complex traffic scenarios.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Haoran Song
PY  - 2025
DA  - 2025/08/31
TI  - Trajectory Prediction Model of Attention Network Based on Space-Time Graph
BT  - Proceedings of the 2025 2nd International Conference on Mechanics, Electronics Engineering and Automation (ICMEEA 2025)
PB  - Atlantis Press
SP  - 931
EP  - 938
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-821-9_89
DO  - 10.2991/978-94-6463-821-9_89
ID  - Song2025
ER  -