Research on Risk Quantification Methods for Connected Autonomous Vehicles Based on CNN-LSTM

Quantifying and predicting driving risks for connected autonomous vehicles (CAVs) is critical to ensuring the safe operation of traffic in complex environments. This study first establishes a car-following model for CAVs based on molecular force fields. Subsequently, using a convolutional neural net...

Full description

Saved in:
Bibliographic Details
Main Authors: Kedong Wang, Dayi Qu, Dedong Shao, Liangshuai Wei, Zhi Zhang
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/23/11204
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846124433779982336
author Kedong Wang
Dayi Qu
Dedong Shao
Liangshuai Wei
Zhi Zhang
author_facet Kedong Wang
Dayi Qu
Dedong Shao
Liangshuai Wei
Zhi Zhang
author_sort Kedong Wang
collection DOAJ
description Quantifying and predicting driving risks for connected autonomous vehicles (CAVs) is critical to ensuring the safe operation of traffic in complex environments. This study first establishes a car-following model for CAVs based on molecular force fields. Subsequently, using a convolutional neural network and long short-term Memory (CNN-LSTM) deep-learning model, the future trajectory of the target vehicle is predicted. Risk is quantified by employing models that assess both the collision probability and collision severity, with deep-learning techniques applied for risk classification. Finally, the High-D dataset is used to predict the vehicle trajectory, from which the speed and acceleration of a target vehicle are derived to forecast driving risks. The results indicate that the CNN-LSTM model, when compared with standalone CNN and LSTM models, demonstrates a superior generalization performance, a higher sensitivity to risk changes, and an accuracy rate exceeding 86% for medium- and high-risk predictions. This improved accuracy and efficacy contribute to enhancing the overall safety of connected vehicle platoons.
format Article
id doaj-art-607edfa7da1e40a98f77a4f0a79a6839
institution Kabale University
issn 2076-3417
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-607edfa7da1e40a98f77a4f0a79a68392024-12-13T16:23:09ZengMDPI AGApplied Sciences2076-34172024-12-0114231120410.3390/app142311204Research on Risk Quantification Methods for Connected Autonomous Vehicles Based on CNN-LSTMKedong Wang0Dayi Qu1Dedong Shao2Liangshuai Wei3Zhi Zhang4School of Intelligent Manufacturing, Qingdao Huanghai University, Qingdao 266427, ChinaSchool of Mechanical and Automotive Engineering, Qingdao University of Technology, Qingdao 266520, ChinaSchool of Civil Engineering, Qingdao University of Technology, Qingdao 266520, ChinaSchool of Mechanical and Automotive Engineering, Qingdao University of Technology, Qingdao 266520, ChinaSchool of Mechanical and Automotive Engineering, Qingdao University of Technology, Qingdao 266520, ChinaQuantifying and predicting driving risks for connected autonomous vehicles (CAVs) is critical to ensuring the safe operation of traffic in complex environments. This study first establishes a car-following model for CAVs based on molecular force fields. Subsequently, using a convolutional neural network and long short-term Memory (CNN-LSTM) deep-learning model, the future trajectory of the target vehicle is predicted. Risk is quantified by employing models that assess both the collision probability and collision severity, with deep-learning techniques applied for risk classification. Finally, the High-D dataset is used to predict the vehicle trajectory, from which the speed and acceleration of a target vehicle are derived to forecast driving risks. The results indicate that the CNN-LSTM model, when compared with standalone CNN and LSTM models, demonstrates a superior generalization performance, a higher sensitivity to risk changes, and an accuracy rate exceeding 86% for medium- and high-risk predictions. This improved accuracy and efficacy contribute to enhancing the overall safety of connected vehicle platoons.https://www.mdpi.com/2076-3417/14/23/11204traffic safetydeep learningrisk quantificationrisk prediction
spellingShingle Kedong Wang
Dayi Qu
Dedong Shao
Liangshuai Wei
Zhi Zhang
Research on Risk Quantification Methods for Connected Autonomous Vehicles Based on CNN-LSTM
Applied Sciences
traffic safety
deep learning
risk quantification
risk prediction
title Research on Risk Quantification Methods for Connected Autonomous Vehicles Based on CNN-LSTM
title_full Research on Risk Quantification Methods for Connected Autonomous Vehicles Based on CNN-LSTM
title_fullStr Research on Risk Quantification Methods for Connected Autonomous Vehicles Based on CNN-LSTM
title_full_unstemmed Research on Risk Quantification Methods for Connected Autonomous Vehicles Based on CNN-LSTM
title_short Research on Risk Quantification Methods for Connected Autonomous Vehicles Based on CNN-LSTM
title_sort research on risk quantification methods for connected autonomous vehicles based on cnn lstm
topic traffic safety
deep learning
risk quantification
risk prediction
url https://www.mdpi.com/2076-3417/14/23/11204
work_keys_str_mv AT kedongwang researchonriskquantificationmethodsforconnectedautonomousvehiclesbasedoncnnlstm
AT dayiqu researchonriskquantificationmethodsforconnectedautonomousvehiclesbasedoncnnlstm
AT dedongshao researchonriskquantificationmethodsforconnectedautonomousvehiclesbasedoncnnlstm
AT liangshuaiwei researchonriskquantificationmethodsforconnectedautonomousvehiclesbasedoncnnlstm
AT zhizhang researchonriskquantificationmethodsforconnectedautonomousvehiclesbasedoncnnlstm