Geometric Graph Neural Network Modeling of Human Interactions in Crowded Environments

TL;DR

This paper introduces a geometric GNN model that incorporates psychological domain knowledge to improve the prediction of human trajectories in crowded environments by defining interaction neighborhoods based on pedestrians' view, motion, and proximity.

Contribution

It presents a novel GNN architecture that models pedestrian interactions using domain-informed graph construction, outperforming prior complete graph approaches.

Findings

Improved trajectory prediction accuracy over baseline models.

Effective modeling of pedestrian interactions using domain knowledge.

Reduced displacement errors in multiple datasets.

Abstract

Modeling human trajectories in crowded environments is challenging due to the complex nature of pedestrian behavior and interactions. This paper proposes a geometric graph neural network (GNN) architecture that integrates domain knowledge from psychological studies to model pedestrian interactions and predict future trajectories. Unlike prior studies using complete graphs, we define interaction neighborhoods using pedestrians' field of view, motion direction, and distance-based kernel functions to construct graph representations of crowds. Evaluations across multiple datasets demonstrate improved prediction accuracy through reduced average and final displacement error metrics. Our findings underscore the importance of integrating domain knowledge with data-driven approaches for effective modeling of human interactions in crowds.