Review of pedestrian trajectory prediction based on graph neural networks

Abstract

Accurately predicting pedestrian trajectories is crucial for the development of autonomous driving, robot navigation, and intelligent surveillance systems. However, this task remains extremely challenging due to the complexity of social interactions between pedestrians. Graph neural networks (GNNs) have been widely adopted in pedestrian trajectory prediction tasks due to their powerful interaction modeling capabilities and scalability. The GNN-based trajectory prediction methods construct different graph structures and then utilize graph convolution and its variants to capture pedestrian interaction features, thereby improving model prediction performance. To systematically review the research progress in this direction, this paper proposes a new classification method that divides the existing GNN-based methods into five types: conventional graph-based methods, sparse graph-based methods, multi-graph-based methods, heterogeneous graph-based methods, and higher-order graph-based methods. This paper systematically analyzes the modeling strategies, advantages, and disadvantages of each type of method to provide further guidance for subsequent researchers. In addition, we evaluate the prediction performance and inference time of these methods on public datasets and then discuss the current challenges and potential future directions of GNN-based trajectory prediction methods. A summary of related papers and codes is publicly available at https://github.com/Chenwangxing/Review-of-PTP-Based-on-GNNs.