Name
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. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/IVS.2019.8814066 | 2019 IEEE Intelligent Vehicles Symposium (IV) |
Keywords | Field | DocType |
traffic scene,interacting vehicles,flexible abstract representation,traffic participants,traffic prediction systems,graph neural network models,GNN architecture,traffic participant interaction | Graph,Mean squared prediction error,Graph neural networks,Artificial intelligence,Traffic scene,Traffic prediction,Machine learning,Mathematics | Journal |
Volume | ISSN | ISBN |
abs/1903.01254 | 1931-0587 | 978-1-7281-0561-1 |
Citations | PageRank | References |
4 | 0.43 | 10 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Frederik Diehl | 1 | 8 | 2.24 |
| thomas brunner | 2 | 14 | 2.61 |
| Michael Truong-Le | 3 | 11 | 1.54 |
| Alois Knoll Knoll | 4 | 1700 | 271.32 |