This work introduces the multidimensional Graph Fourier Transformation Neural Network (GFTNN) for long-term trajectory predictions on highways. Similar to Graph Neural Networks (GNNs), the GFTNN is a novel network architecture that operates on graph structures. While several GNNs lack discriminative power due to suboptimal aggregation schemes, the proposed model aggregates scenario properties through a powerful operation: the multidimensional Graph Fourier Transformation (GFT). The spatio-temporal vehicle interaction graph of a scenario is converted into a spectral scenario representation using the GFT. This beneficial representation is input to the prediction framework composed of a neural network and a descriptive decoder. Even though the proposed GFTNN does not include any recurrent element, it outperforms state-of-the-art models in the task of highway trajectory prediction. For experiments and evaluation, the publicly available datasets highD and NGSIM are used
@article{arxiv.2305.07416,
title = {A Multidimensional Graph Fourier Transformation Neural Network for Vehicle Trajectory Prediction},
author = {Marion Neumeier and Andreas Tollkühn and Michael Botsch and Wolfgang Utschick},
journal= {arXiv preprint arXiv:2305.07416},
year = {2023}
}
Comments
Accepted as a conference paper in ITSC 2022, Macau, China