Cargando…
A Physics-Informed Generative Car-Following Model for Connected Autonomous Vehicles
This paper proposes a novel hybrid car-following model: the physics-informed conditional generative adversarial network (PICGAN), designed to enhance multi-step car-following modeling in mixed traffic flow scenarios. This hybrid model leverages the strengths of both physics-based and deep-learning-b...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10378484/ https://www.ncbi.nlm.nih.gov/pubmed/37509998 http://dx.doi.org/10.3390/e25071050 |
_version_ | 1785079778032746496 |
---|---|
author | Ma, Lijing Qu, Shiru Song, Lijun Zhang, Zhiteng Ren, Jie |
author_facet | Ma, Lijing Qu, Shiru Song, Lijun Zhang, Zhiteng Ren, Jie |
author_sort | Ma, Lijing |
collection | PubMed |
description | This paper proposes a novel hybrid car-following model: the physics-informed conditional generative adversarial network (PICGAN), designed to enhance multi-step car-following modeling in mixed traffic flow scenarios. This hybrid model leverages the strengths of both physics-based and deep-learning-based models. By taking advantage of the inherent structure of GAN, the PICGAN eliminates the need for an explicit weighting parameter typically used in the combination of traditional physics-based and data-driven models. The effectiveness of the proposed model is substantiated through case studies using the NGSIM I-80 dataset. These studies demonstrate the model’s superior trajectory reproduction, suggesting its potential as a strong contender to replace conventional models in trajectory prediction tasks. Furthermore, the deployment of PICGAN significantly enhances the stability and efficiency in mixed traffic flow environments. Given its reliable and stable results, the PICGAN framework contributes substantially to the development of efficient longitudinal control strategies for connected autonomous vehicles (CAVs) in real-world mixed traffic conditions. |
format | Online Article Text |
id | pubmed-10378484 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-103784842023-07-29 A Physics-Informed Generative Car-Following Model for Connected Autonomous Vehicles Ma, Lijing Qu, Shiru Song, Lijun Zhang, Zhiteng Ren, Jie Entropy (Basel) Article This paper proposes a novel hybrid car-following model: the physics-informed conditional generative adversarial network (PICGAN), designed to enhance multi-step car-following modeling in mixed traffic flow scenarios. This hybrid model leverages the strengths of both physics-based and deep-learning-based models. By taking advantage of the inherent structure of GAN, the PICGAN eliminates the need for an explicit weighting parameter typically used in the combination of traditional physics-based and data-driven models. The effectiveness of the proposed model is substantiated through case studies using the NGSIM I-80 dataset. These studies demonstrate the model’s superior trajectory reproduction, suggesting its potential as a strong contender to replace conventional models in trajectory prediction tasks. Furthermore, the deployment of PICGAN significantly enhances the stability and efficiency in mixed traffic flow environments. Given its reliable and stable results, the PICGAN framework contributes substantially to the development of efficient longitudinal control strategies for connected autonomous vehicles (CAVs) in real-world mixed traffic conditions. MDPI 2023-07-12 /pmc/articles/PMC10378484/ /pubmed/37509998 http://dx.doi.org/10.3390/e25071050 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Ma, Lijing Qu, Shiru Song, Lijun Zhang, Zhiteng Ren, Jie A Physics-Informed Generative Car-Following Model for Connected Autonomous Vehicles |
title | A Physics-Informed Generative Car-Following Model for Connected Autonomous Vehicles |
title_full | A Physics-Informed Generative Car-Following Model for Connected Autonomous Vehicles |
title_fullStr | A Physics-Informed Generative Car-Following Model for Connected Autonomous Vehicles |
title_full_unstemmed | A Physics-Informed Generative Car-Following Model for Connected Autonomous Vehicles |
title_short | A Physics-Informed Generative Car-Following Model for Connected Autonomous Vehicles |
title_sort | physics-informed generative car-following model for connected autonomous vehicles |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10378484/ https://www.ncbi.nlm.nih.gov/pubmed/37509998 http://dx.doi.org/10.3390/e25071050 |
work_keys_str_mv | AT malijing aphysicsinformedgenerativecarfollowingmodelforconnectedautonomousvehicles AT qushiru aphysicsinformedgenerativecarfollowingmodelforconnectedautonomousvehicles AT songlijun aphysicsinformedgenerativecarfollowingmodelforconnectedautonomousvehicles AT zhangzhiteng aphysicsinformedgenerativecarfollowingmodelforconnectedautonomousvehicles AT renjie aphysicsinformedgenerativecarfollowingmodelforconnectedautonomousvehicles AT malijing physicsinformedgenerativecarfollowingmodelforconnectedautonomousvehicles AT qushiru physicsinformedgenerativecarfollowingmodelforconnectedautonomousvehicles AT songlijun physicsinformedgenerativecarfollowingmodelforconnectedautonomousvehicles AT zhangzhiteng physicsinformedgenerativecarfollowingmodelforconnectedautonomousvehicles AT renjie physicsinformedgenerativecarfollowingmodelforconnectedautonomousvehicles |