期刊
NEUROCOMPUTING
卷 428, 期 -, 页码 332-339出版社
ELSEVIER
DOI: 10.1016/j.neucom.2020.03.120
关键词
Trajectory generation; Generation model; Variational AutoEncoder (VAE); Long Short-Term Memory (LSTM)
资金
- National Natrual Science Foundation of China [61872258, 6177 2356, 61876117, 61802273]
- Australia Research Council [DP180100212]
- State Key Labroratory of Software Architecture [SKL-SAOP1801]
- Blockshine corporation
This paper focuses on trajectory generation problem and proposes two advanced solutions, TrajGAN and TrajVAE, which utilize LSTM, GAN, and VAE frameworks to model and generate trajectories. The accuracy and stability of the methods are validated through multiple trajectory similarity metrics in several experiments.
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. (C) 2020 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据