SIAT: Pedestrian trajectory prediction via social interaction-aware transformer

Abstract Pedestrian trajectory prediction is crucial for mitigating collision risks in intelligent transportation and surveillance systems. Despite recent advances, accurately capturing and modeling complex social interactions among pedestrians remains a challenge. This paper introduces the Social I...

Full description

Saved in:
Bibliographic Details
Main Authors: Chengdong Wang, Jianming Wang, Wenbo Gao, Lei Guo
Format: Article
Language:English
Published: Springer 2025-06-01
Series:Complex & Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1007/s40747-025-01944-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849388675842965504
author Chengdong Wang
Jianming Wang
Wenbo Gao
Lei Guo
author_facet Chengdong Wang
Jianming Wang
Wenbo Gao
Lei Guo
author_sort Chengdong Wang
collection DOAJ
description Abstract Pedestrian trajectory prediction is crucial for mitigating collision risks in intelligent transportation and surveillance systems. Despite recent advances, accurately capturing and modeling complex social interactions among pedestrians remains a challenge. This paper introduces the Social Interaction-Aware Transformer (SIAT), a novel approach that leverages a Transformer encoder to process pedestrian embedding features and a Graph Convolutional Network (GCN) to construct a social graph for extracting spatial interaction features. The future pedestrian trajectory is predicted using a Transformer decoder that integrates both pedestrian embeddings and social graph features. Extensive experiments on the ETH/UCY and Stanford Drone datasets demonstrate that SIAT significantly outperforms state-of-the-art methods in terms of accuracy and robustness, particularly in densely populated environments. SIAT’s contributions include improved precision through temporal and spatial processing, deep contextual understanding of pedestrian dynamics, and robustness across various settings. The novel model framework establishes a new benchmark for mixed models in trajectory prediction.
format Article
id doaj-art-b6a80c6664604d1cbd209a3c0bb9a9f4
institution Kabale University
issn 2199-4536
2198-6053
language English
publishDate 2025-06-01
publisher Springer
record_format Article
series Complex & Intelligent Systems
spelling doaj-art-b6a80c6664604d1cbd209a3c0bb9a9f42025-08-20T03:42:11ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-06-0111811410.1007/s40747-025-01944-3SIAT: Pedestrian trajectory prediction via social interaction-aware transformerChengdong Wang0Jianming Wang1Wenbo Gao2Lei Guo3School of Computer and Software Engineering, Anhui Institute of Information TechnologySchool of Computer and Software Engineering, Anhui Institute of Information TechnologySchool of Computer and Software Engineering, Anhui Institute of Information TechnologyYunnan Key Laboratory of Computer Technology Applications, Faculty of Information Engineering and Automation, Kunming University of Science and TechnologyAbstract Pedestrian trajectory prediction is crucial for mitigating collision risks in intelligent transportation and surveillance systems. Despite recent advances, accurately capturing and modeling complex social interactions among pedestrians remains a challenge. This paper introduces the Social Interaction-Aware Transformer (SIAT), a novel approach that leverages a Transformer encoder to process pedestrian embedding features and a Graph Convolutional Network (GCN) to construct a social graph for extracting spatial interaction features. The future pedestrian trajectory is predicted using a Transformer decoder that integrates both pedestrian embeddings and social graph features. Extensive experiments on the ETH/UCY and Stanford Drone datasets demonstrate that SIAT significantly outperforms state-of-the-art methods in terms of accuracy and robustness, particularly in densely populated environments. SIAT’s contributions include improved precision through temporal and spatial processing, deep contextual understanding of pedestrian dynamics, and robustness across various settings. The novel model framework establishes a new benchmark for mixed models in trajectory prediction.https://doi.org/10.1007/s40747-025-01944-3Pedestrian trajectory predictionSocial InteractionTransformerGCN
spellingShingle Chengdong Wang
Jianming Wang
Wenbo Gao
Lei Guo
SIAT: Pedestrian trajectory prediction via social interaction-aware transformer
Complex & Intelligent Systems
Pedestrian trajectory prediction
Social Interaction
Transformer
GCN
title SIAT: Pedestrian trajectory prediction via social interaction-aware transformer
title_full SIAT: Pedestrian trajectory prediction via social interaction-aware transformer
title_fullStr SIAT: Pedestrian trajectory prediction via social interaction-aware transformer
title_full_unstemmed SIAT: Pedestrian trajectory prediction via social interaction-aware transformer
title_short SIAT: Pedestrian trajectory prediction via social interaction-aware transformer
title_sort siat pedestrian trajectory prediction via social interaction aware transformer
topic Pedestrian trajectory prediction
Social Interaction
Transformer
GCN
url https://doi.org/10.1007/s40747-025-01944-3
work_keys_str_mv AT chengdongwang siatpedestriantrajectorypredictionviasocialinteractionawaretransformer
AT jianmingwang siatpedestriantrajectorypredictionviasocialinteractionawaretransformer
AT wenbogao siatpedestriantrajectorypredictionviasocialinteractionawaretransformer
AT leiguo siatpedestriantrajectorypredictionviasocialinteractionawaretransformer