Graph Neural Networks for Modelling Traffic Participant Interaction
This work addresses traffic prediction for autonomous driving systems by improving accuracy in interactive scenarios, though it is incremental as it adapts existing GNN methods.
The paper tackled traffic prediction by modeling traffic scenes as graphs of interacting vehicles and applying Graph Neural Networks (GNNs), resulting in a 30% reduction in prediction error in high-interaction scenarios compared to non-interaction models.
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.