Quantification Method of Driving Risks for Networked Autonomous Vehicles Based on Molecular Potential Fields

Connected autonomous vehicles (CAVs) face constraints from multiple traffic elements, such as the vehicle, road, and environmental factors. Accurately quantifying the vehicle’s operational status and driving risk level in complex traffic scenarios is crucial for enhancing the efficiency and safety o...

Full description

Saved in:
Bibliographic Details
Main Authors: Yicheng Chen, Dayi Qu, Tao Wang, Shanning Cui, Dedong Shao
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/3/1306
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850199481713164288
author Yicheng Chen
Dayi Qu
Tao Wang
Shanning Cui
Dedong Shao
author_facet Yicheng Chen
Dayi Qu
Tao Wang
Shanning Cui
Dedong Shao
author_sort Yicheng Chen
collection DOAJ
description Connected autonomous vehicles (CAVs) face constraints from multiple traffic elements, such as the vehicle, road, and environmental factors. Accurately quantifying the vehicle’s operational status and driving risk level in complex traffic scenarios is crucial for enhancing the efficiency and safety of connected autonomous driving. To continuously and dynamically quantify the driving risks faced by CAVs in the road environment—arising from the front, rear, and lateral directions—this study focused s on the self-driving particle characteristics that enable CAVs to perceive their surrounding environment and make driving decisions. The vehicle-to-vehicle interaction behavior was analogized to the inter-molecular interaction relationship, and a molecular Morse potential model was applied, coupled with the vehicle dynamics theory. This approach considers the safety margin and the specificity of driving styles. A multi-layer decoder–encoder long short-term memory (LSTM) network was employed to predict vehicle trajectories and establish a risk quantification model for vehicle-to-vehicle interaction behavior. Using SUMO software (win64-1.11.0), three typical driving behavior scenarios—car-following, lane-changing, and yielding—were modeled. A comparative analysis was conducted between the risk field quantification method and existing risk quantification indicators such as post-encroachment time (PET), deceleration rate to avoid crash (DRAC), modified time to collision (MTTC), and safety potential fields (SPFs). The evaluation results demonstrate that the risk field quantification method has the advantage of continuously quantifying risk, addressing the limitations of traditional risk indicators, which may yield discontinuous results when conflict points disappear. Furthermore, when the half-life parameter is reasonably set, the method exhibits more stable evaluation performance. This research provides a theoretical basis for the dynamic equilibrium control of driving risks in connected autonomous vehicle fleets within mixed-traffic environments, offering insights and references for collision avoidance design.
format Article
id doaj-art-2b4efe5a63844a8ca191d827861dfd77
institution OA Journals
issn 2076-3417
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-2b4efe5a63844a8ca191d827861dfd772025-08-20T02:12:37ZengMDPI AGApplied Sciences2076-34172025-01-01153130610.3390/app15031306Quantification Method of Driving Risks for Networked Autonomous Vehicles Based on Molecular Potential FieldsYicheng Chen0Dayi Qu1Tao Wang2Shanning Cui3Dedong Shao4College of Civil Engineering, Qingdao University of Technology, Qingdao 266520, ChinaCollege of Civil Engineering, Qingdao University of Technology, Qingdao 266520, ChinaCollege of Civil Engineering, Qingdao University of Technology, Qingdao 266520, ChinaCollege of Civil Engineering, Qingdao University of Technology, Qingdao 266520, ChinaCollege of Civil Engineering, Qingdao University of Technology, Qingdao 266520, ChinaConnected autonomous vehicles (CAVs) face constraints from multiple traffic elements, such as the vehicle, road, and environmental factors. Accurately quantifying the vehicle’s operational status and driving risk level in complex traffic scenarios is crucial for enhancing the efficiency and safety of connected autonomous driving. To continuously and dynamically quantify the driving risks faced by CAVs in the road environment—arising from the front, rear, and lateral directions—this study focused s on the self-driving particle characteristics that enable CAVs to perceive their surrounding environment and make driving decisions. The vehicle-to-vehicle interaction behavior was analogized to the inter-molecular interaction relationship, and a molecular Morse potential model was applied, coupled with the vehicle dynamics theory. This approach considers the safety margin and the specificity of driving styles. A multi-layer decoder–encoder long short-term memory (LSTM) network was employed to predict vehicle trajectories and establish a risk quantification model for vehicle-to-vehicle interaction behavior. Using SUMO software (win64-1.11.0), three typical driving behavior scenarios—car-following, lane-changing, and yielding—were modeled. A comparative analysis was conducted between the risk field quantification method and existing risk quantification indicators such as post-encroachment time (PET), deceleration rate to avoid crash (DRAC), modified time to collision (MTTC), and safety potential fields (SPFs). The evaluation results demonstrate that the risk field quantification method has the advantage of continuously quantifying risk, addressing the limitations of traditional risk indicators, which may yield discontinuous results when conflict points disappear. Furthermore, when the half-life parameter is reasonably set, the method exhibits more stable evaluation performance. This research provides a theoretical basis for the dynamic equilibrium control of driving risks in connected autonomous vehicle fleets within mixed-traffic environments, offering insights and references for collision avoidance design.https://www.mdpi.com/2076-3417/15/3/1306vehicle-to-vehicle interactionrisk quantificationmolecular potential fieldsnetworked autonomous vehiclesdeep learning
spellingShingle Yicheng Chen
Dayi Qu
Tao Wang
Shanning Cui
Dedong Shao
Quantification Method of Driving Risks for Networked Autonomous Vehicles Based on Molecular Potential Fields
Applied Sciences
vehicle-to-vehicle interaction
risk quantification
molecular potential fields
networked autonomous vehicles
deep learning
title Quantification Method of Driving Risks for Networked Autonomous Vehicles Based on Molecular Potential Fields
title_full Quantification Method of Driving Risks for Networked Autonomous Vehicles Based on Molecular Potential Fields
title_fullStr Quantification Method of Driving Risks for Networked Autonomous Vehicles Based on Molecular Potential Fields
title_full_unstemmed Quantification Method of Driving Risks for Networked Autonomous Vehicles Based on Molecular Potential Fields
title_short Quantification Method of Driving Risks for Networked Autonomous Vehicles Based on Molecular Potential Fields
title_sort quantification method of driving risks for networked autonomous vehicles based on molecular potential fields
topic vehicle-to-vehicle interaction
risk quantification
molecular potential fields
networked autonomous vehicles
deep learning
url https://www.mdpi.com/2076-3417/15/3/1306
work_keys_str_mv AT yichengchen quantificationmethodofdrivingrisksfornetworkedautonomousvehiclesbasedonmolecularpotentialfields
AT dayiqu quantificationmethodofdrivingrisksfornetworkedautonomousvehiclesbasedonmolecularpotentialfields
AT taowang quantificationmethodofdrivingrisksfornetworkedautonomousvehiclesbasedonmolecularpotentialfields
AT shanningcui quantificationmethodofdrivingrisksfornetworkedautonomousvehiclesbasedonmolecularpotentialfields
AT dedongshao quantificationmethodofdrivingrisksfornetworkedautonomousvehiclesbasedonmolecularpotentialfields