Abstract
Multi-vehicle trajectories generated from existing and real-time data provide valuable resources for autonomous vehicle development and testing. This paper introduces a multi-vehicle trajectory generator (MTG) that extracts the interpretable representations of driving encounters. The generator’s encoder has a bi-directional GRU module, and multiple branches of its decoder generate the sequences separately. A new disentanglement metric developed for model analyses and comparisons reveals the robustness of the deep generative models and the dependency among the latent codes. Experiments demonstrate that the proposed trajectory generator outperforms $\beta$-VAE and InfoGAN in terms of traffic rationality and disentanglement. Based on the results, we conclude that the generator will provide additional valuable data to the engineers and researchers who develop simulation scenarios for autonomous vehicle development and testing.
Abstract (translated by Google)
URL
http://arxiv.org/abs/1809.05680