TrajVAE: A Variational AutoEncoder model for trajectory generation

Large-scale trajectory dataset is always required for self-driving and many other applications. In this paper, we focus on the trajectory generation problem, which aims to generate qualified trajectory dataset that is indistinguishable from real trajectories, for fulfilling the needs of large-scale...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) Vol. 428; pp. 332 - 339
Main Authors: Chen, Xinyu, Xu, Jiajie, Zhou, Rui, Chen, Wei, Fang, Junhua, Liu, Chengfei
Format: Journal Article
Language:English
Published: Elsevier B.V 07.03.2021
Subjects:
Generation model
Long Short-Term Memory (LSTM)
Trajectory generation
Variational AutoEncoder (VAE)
Trajectory generation
Variational AutoEncoder (VAE)
Long Short-Term Memory (LSTM)
Generation model
ISSN:0925-2312, 1872-8286
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Large-scale trajectory dataset is always required for self-driving and many other applications. In this paper, we focus on the trajectory generation problem, which aims to generate qualified trajectory dataset that is indistinguishable from real trajectories, for fulfilling the needs of large-scale trajectory data by self-driving simulation and traffic analysis tasks in data sparse cities or regions. We propose two advanced solutions, namely TrajGAN and TrajVAE, which utilize LSTM to model the characteristics of trajectories first, and then take advantage of Generative Adversarial Network (GAN) and Variational AutoEncoder (VAE) frameworks respectively to generate trajectories. In order of compare the similarity of existing trajectories in our dataset and the generated trajectories, we utilize multiple trajectory similarity metrics. Through several experiments, we demonstrate that our method is more accurate and stable than the baseline.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2020.03.120