Behavior Encoder Transformer BETR: A Transformer Encoder for Predicting Agent Behavior
Elhusseni, M., Maher, Y., Elsayed, E., Abdelkader, M. (2025). Behavior Encoder Transformer BETR: A Transformer Encoder for Predicting Agent Behavior. EKB Journal Management System, 29(2), 71-79. doi: 10.21608/pserj.2025.338938.1381
Mahmoud a Elhusseni; Yara Maher; Emad Elsayed; Mohamed F. Abdelkader. "Behavior Encoder Transformer BETR: A Transformer Encoder for Predicting Agent Behavior". EKB Journal Management System, 29, 2, 2025, 71-79. doi: 10.21608/pserj.2025.338938.1381
Elhusseni, M., Maher, Y., Elsayed, E., Abdelkader, M. (2025). 'Behavior Encoder Transformer BETR: A Transformer Encoder for Predicting Agent Behavior', EKB Journal Management System, 29(2), pp. 71-79. doi: 10.21608/pserj.2025.338938.1381
Elhusseni, M., Maher, Y., Elsayed, E., Abdelkader, M. Behavior Encoder Transformer BETR: A Transformer Encoder for Predicting Agent Behavior. EKB Journal Management System, 2025; 29(2): 71-79. doi: 10.21608/pserj.2025.338938.1381

Behavior Encoder Transformer BETR: A Transformer Encoder for Predicting Agent Behavior

Port-Said Engineering Research Journal
Article 7, Volume 29, Issue 2, June 2025, Page 71-79  XML PDF (846.88 K)
Document Type: Original Article
DOI: 10.21608/pserj.2025.338938.1381
View on SCiNiTO View on SCiNiTO
Authors
Mahmoud a Elhusseni email orcid 1; Yara Maher2; Emad Elsayedorcid 3; Mohamed F. Abdelkaderorcid 4
1Electrical Communication Engineering, Port Said University.
2Electrical Communication and Electronics, Faculty of Engineering, Port Said University
3Computer and Control Engineering, Port Said University
4Electrical Engineering Department, Faculty of Engineering, Port Said University, Port Said, Egypt.
Abstract
Anticipating the future behavior of road users stands as one of the most formidable challenges in the

realm of autonomous driving. Achieving a comprehensive understanding of the dynamic driving environment requires an autonomous vehicle to accurately predict the motion of other traffic participants within the scene. As the complexity of motion prediction tasks increases, capturing

intricate spatial relationships, temporal dependencies, and nuanced interactions between agents and map elements becomes crucial. Our proposed hierarchical architecture strategically incorporates transformers, effectively modeling both local and global representations to extract multi-

scale features. Leveraging the potency of transformers, BETR adeptly captures and encodes intricate patterns of agent interactions, spatial dependencies, and temporal dynamics. Demonstrating superior performance in predicting agent behavior compared to conventional methods, BETR proves its efficacy through extensive experiments. Its capacity to adapt to diverse scenarios establishes BETR

as a robust and versatile solution for the intricate task of agent behavior prediction.
Keywords
Transformers; Encoders; Motion Prediction; Vector Representations
Statistics
Article View: 75
PDF Download: 15