VideoGAN-based Trajectory Proposal for Automated Vehicles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mariani, Annajoyce, Maag, Kira, Gottschalk, Hanno
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908413374496768
author Mariani, Annajoyce
Maag, Kira
Gottschalk, Hanno
author_facet Mariani, Annajoyce
Maag, Kira
Gottschalk, Hanno
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16209
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VideoGAN-based Trajectory Proposal for Automated Vehicles
Mariani, Annajoyce
Maag, Kira
Gottschalk, Hanno
Computer Vision and Pattern Recognition
Machine Learning
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.
title VideoGAN-based Trajectory Proposal for Automated Vehicles
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2506.16209