# Graph Neural Networks for Modelling Traffic Participant Interaction

## TL;DR

This paper demonstrates that Graph Neural Networks effectively model interactions between traffic participants, significantly improving traffic prediction accuracy by capturing complex vehicle interactions.

## Contribution

It introduces adaptations of GNN architectures for traffic scene modeling and shows their effectiveness in reducing prediction errors in interactive scenarios.

## Key findings

- Prediction error decreases by 30% with GNNs in interactive scenarios.
- GNNs effectively model vehicle interactions in traffic scenes.
- Interaction modeling improves traffic prediction accuracy.

## Abstract

By interpreting a traffic scene as a graph of interacting vehicles, we gain a flexible abstract representation which allows us to apply Graph Neural Network (GNN) models for traffic prediction. These naturally take interaction between traffic participants into account while being computationally efficient and providing large model capacity. We evaluate two state-of-the art GNN architectures and introduce several adaptations for our specific scenario. We show that prediction error in scenarios with much interaction decreases by 30% compared to a model that does not take interactions into account. This suggests that interaction is important, and shows that we can model it using graphs. This makes GNNs a worthwhile addition to traffic prediction systems.