GSGFormer: Generative Social Graph Transformer for Multimodal Pedestrian Trajectory Prediction

2023/12/07 by Zhongchang Luo, Luo, Zhongchang, Marion Robin +3 · 1 citation
Engineering · #Artificial Intelligence (cs.AI) #Autonomous Vehicle Technology and Safety #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Traffic Prediction and Management Techniques #Traffic and Road Safety

paper · pdf · doi:10.48550/arxiv.2312.04479

openalex publication_date 2023/12/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Pedestrian trajectory prediction, vital for selfdriving cars and socially-aware robots, is complicated due to intricate interactions between pedestrians, their environment, and other Vulnerable Road Users. This paper presents GSGFormer, an innovative generative model adept at predicting pedestrian trajectories by considering these complex interactions and offering a plethora of potential modal behaviors. We incorporate a heterogeneous graph neural network to capture interactions between pedestrians, semantic maps, and potential destinations. The Transformer module extracts temporal features, while our novel CVAE-Residual-GMM module promotes diverse behavioral modality generation. Through evaluations on multiple public datasets, GSGFormer not only outperforms leading methods with ample data but also remains competitive when data is limited.

Cited by

• Metamorphic Testing of Multimodal Human Trajectory Prediction

Related

• Attention-aware Social Graph Transformer Networks for Stochastic Trajectory Prediction
• ForceFormer: Exploring Social Force and Transformer for Pedestrian Trajectory Prediction
• Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
• Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction
• PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning