GSGFormer: Generative Social Graph Transformer for Multimodal Pedestrian Trajectory Prediction
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
GUIDE-CoT: Goal-driven and User-Informed Dynamic Estimation for Pedestrian Trajectory using Chain-of-Thought
SceneAware: Scene-Constrained Pedestrian Trajectory Prediction with LLM-Guided Walkability
Towards Predicting Any Human Trajectory In Context
SocialMOIF: Multi-Order Intention Fusion for Pedestrian Trajectory Prediction
Equi-Euler GraphNet: An Equivariant, Temporal-Dynamics Informed Graph Neural Network for Dual Force and Trajectory Prediction in Multi-Body Systems
Learning Velocity and Acceleration: Self-Supervised Motion Consistency for Pedestrian Trajectory Prediction
토론
이 논문과 연결된 포럼 글이 아직 없습니다.