VideoGAN-based Trajectory Proposal for Automated Vehicles

TL;DR

This paper introduces a VideoGAN approach trained on bird's-eye view traffic videos to generate realistic, statistically accurate vehicle trajectories for automated driving, emphasizing fast training and inference.

Contribution

It proposes a novel pipeline using VideoGAN on BEV traffic videos to generate and extract realistic vehicle trajectories efficiently.

Findings

Achieved realistic trajectory generation with distributional alignment to real data.

Training completed within 100 GPU hours with inference under 20 ms.

Demonstrated physical realism of trajectories on Waymo dataset.

Abstract

Being able to generate realistic trajectory options is at the core of increasing the degree of automation of road vehicles. While model-driven, rule-based, and classical learning-based methods are widely used to tackle these tasks at present, they can struggle to effectively capture the complex, multimodal distributions of future trajectories. In this paper we investigate whether a generative adversarial network (GAN) trained on videos of bird's-eye view (BEV) traffic scenarios can generate statistically accurate trajectories that correctly capture spatial relationships between the agents. To this end, we propose a pipeline that uses low-resolution BEV occupancy grid videos as training data for a video generative model. From the generated videos of traffic scenarios we extract abstract trajectory data using single-frame object detection and frame-to-frame object matching. We particularly choose a GAN architecture for the fast training and inference times with respect to diffusion models. We obtain our best results within 100 GPU hours of training, with inference times under 20\,ms. We demonstrate the physical realism of the proposed trajectories in terms of distribution alignment of spatial and dynamic parameters with respect to the ground truth videos from the Waymo Open Motion Dataset.