Multistep Ahead Prediction of Vehicle Lateral Dynamics Based on Echo State Model

Multistep Ahead Prediction of Vehicle Lateral Dynamics Based on Echo State Model
复制标题

基于回波状态模型的车辆横向动力学多步提前预测

DOI:
10.1109/jsen.2022.3208076
复制
发表时间:
2023-01
影响因子:
4.3
通讯作者:
Xiaoxia Xiong
Xiaoxia Xiong
中科院分区:
综合性期刊2区
文献类型:
--
作者:
Chenglong Teng;Yingfeng Cai;Xiaoqiang Sun;Xiaodong Sun;Hai Wang;Long Chen;Xiaoxia Xiong

文献摘要

参考文献

被引文献

相似文献

横向动力学对于高级自动驾驶至关重要,多步预测可以显著提高车辆安全性。然而,由于准确预测的困难,动力学预测方法很少公布。与传统的时间序列预测方法不同,本文提出了一种新的隐式参数动态系统预测方法。具体来说,我们构建了一个回声状态模型(ESM),将一个合理的数据组织和一个有效的神经网络结构。我们观察到的衰减信息属性(FIP)的动态车辆参数和使用时间数据来构建等效状态的隐式参数。最后,设计并训练了一个门控递归单元(GRU)神经网络来完成车辆动力学系统的复杂映射。它的性能进行了比较,几个基准网络。所提出的方法能够在干燥和湿滑的道路条件下进行高精度的四步预测,这意味着自动驾驶汽车的一些安全和舒适的驾驶应用的潜力增加。
Lateral dynamics are critical for high-level autonomous driving, and multistep forecasting can significantly improve vehicle safety. However, the dynamics prediction method is rarely announced due to the difficulty of accurate prediction. In contrast to conventional time-series prediction, this article proposes a novel method for predicting a dynamical system with implicit parameters. Specifically, we construct an echo state model (ESM) incorporating a rational data organization and an efficient neural network structure. We observe the fading information property (FIP) of dynamic vehicle parameters and use temporal data to construct equivalent states for implicit parameters. Finally, a gated recurrent unit (GRU) neural network is designed and trained to accomplish the complex mapping of a vehicle dynamical system. Its performance is compared to that of several benchmark networks. The proposed method is capable of performing four-step-ahead prediction with high accuracy in both dry and slippery road conditions, implying the increased potential for some safe and comfortable driving applications of autonomous vehicles.
DOI: 10.1109/tvt.2019.2933229
发表时间: 2019-08
影响因子: 6.8
作者:
A. Tahouni;M. Mirzaei;Behrouz Najjari
通讯作者: A. Tahouni;M. Mirzaei;Behrouz Najjari
DOI: 10.1504/ijvd.1996.061978
发表时间: 2014-08
影响因子: 0.5
作者:
A. Ghazizadeh;A. Fahim;M. El-Gindy
通讯作者: A. Ghazizadeh;A. Fahim;M. El-Gindy
DOI: --
发表时间: 2012
期刊: --
影响因子: --
作者:
Manjunath Gandhi;P. Tiňo;H. Jaeger
通讯作者: Manjunath Gandhi;P. Tiňo;H. Jaeger
基于运动预测和模型预测控制的自动驾驶车辆轨迹规划和安全评估
DOI: 10.1109/tvt.2019.2930684
发表时间: 2019-07
影响因子: 6.8
作者:
Wang Yijing;Liu Zhengxuan;Zuo Zhiqiang;Li Zheng;Wang Li;Luo Xiaoyuan
通讯作者: Luo Xiaoyuan
DOI: --
发表时间: 2001
影响因子: 3.7
作者:
H. Jaeger
通讯作者: H. Jaeger