Prediction and Interpretation of Vehicle Trajectories in the Graph Spectral Domain
This work addresses the problem of accurate trajectory prediction for autonomous vehicles and traffic management, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles vehicle trajectory prediction by transforming traffic scenarios into the graph spectral domain using a Graph Fourier Transformation, and introduces GFTNNv2, a deep learning network that achieves up to 25% performance gain over state-of-the-art methods on highD and NGSIM datasets.
This work provides a comprehensive analysis and interpretation of the graph spectral representation of traffic scenarios. Based on a spatio-temporal vehicle interaction graph, an observed traffic scenario can be transformed into the graph spectral domain by means of the multidimensional Graph Fourier Transformation. Since these spectral scenario representations have shown to successfully incorporate the complex and interactive nature of traffic scenarios, the beneficial feature representation is employed for the purpose of predicting vehicle trajectories. This work introduces GFTNNv2, a deep learning network predicting vehicle trajectories in the graph spectral domain. Evaluation of the GFTNNv2 on the publicly available datasets highD and NGSIM shows a performance gain of up to 25% in comparison to state-of-the-art prediction approaches.