Pub Date : 2023-12-01DOI: 10.26599/JICV.2023.9210018
Quan Yuan;Haixu Shi;Ashton Tan Yu Xuan;Ming Gao;Qing Xu;Jianqiang Wang
In autonomous driving, target tracking is essential to environmental perception. The study of target tracking algorithms can improve the accuracy of an autonomous driving vehicle's perception, which is of great significance in ensuring the safety of autonomous driving and promoting the landing of technical applications. This study focuses on the fusion tracking algorithm based on visible and infrared images. The proposed approach utilizes a feature-level image fusion method, dividing the tracking process into two components: image fusion and target tracking. An unsupervised network, Visible and Infrared image Fusion Network (VIF-net), is employed for visible and infrared image fusion in the image fusion part. In the target tracking part, Siamese Region Proposal Network (SiamRPN), based on deep learning, tracks the target with fused images. The fusion tracking algorithm is trained and evaluated on the visible infrared image dataset RGBT234. Experimental results demonstrate that the algorithm outperforms training networks solely based on visible images, proving that the fusion of visible and infrared images in the target tracking algorithm can improve the accuracy of the target tracking even if it is like tracking-based visual images. This improvement is also attributed to the algorithm's ability to extract infrared image features, augmenting the target tracking accuracy.
{"title":"Enhanced Target Tracking Algorithm for Autonomous Driving Based on Visible and Infrared Image Fusion","authors":"Quan Yuan;Haixu Shi;Ashton Tan Yu Xuan;Ming Gao;Qing Xu;Jianqiang Wang","doi":"10.26599/JICV.2023.9210018","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210018","url":null,"abstract":"In autonomous driving, target tracking is essential to environmental perception. The study of target tracking algorithms can improve the accuracy of an autonomous driving vehicle's perception, which is of great significance in ensuring the safety of autonomous driving and promoting the landing of technical applications. This study focuses on the fusion tracking algorithm based on visible and infrared images. The proposed approach utilizes a feature-level image fusion method, dividing the tracking process into two components: image fusion and target tracking. An unsupervised network, Visible and Infrared image Fusion Network (VIF-net), is employed for visible and infrared image fusion in the image fusion part. In the target tracking part, Siamese Region Proposal Network (SiamRPN), based on deep learning, tracks the target with fused images. The fusion tracking algorithm is trained and evaluated on the visible infrared image dataset RGBT234. Experimental results demonstrate that the algorithm outperforms training networks solely based on visible images, proving that the fusion of visible and infrared images in the target tracking algorithm can improve the accuracy of the target tracking even if it is like tracking-based visual images. This improvement is also attributed to the algorithm's ability to extract infrared image features, augmenting the target tracking accuracy.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"6 4","pages":"237-249"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10409225","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139504499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-01DOI: 10.26599/JICV.2023.9210007
Nalin Kumar Sekar;Vinayak Malaghan;Digvijay S. Pawar
Several past studies showed that Autonomous Vehicles (AVs) can reduce crash risk, stop-and-go traffic, and travel time. To analyze the safety benefits of AVs, most of the researchers proposed algorithms and simulation-based techniques. However, these studies have not assessed the safety benefits of AVs for different vehicle types under heterogeneous conditions. With this opportunity, this study focuses on the benefits of AVs in terms of safety for different penetration rates under heterogeneous conditions. This study considered three driving logics during peak hour conditions to assess the performance of AVs in terms of safety. In VISSIM, default driving behavior models for AVs were adopted to consider cautious and all-knowing driving logic and the third driving logic (Atkins) was modeled in VISSIM using parameters adopted from the previous studies. To this end, using VISSIM, the travel time output results were obtained. Also, using Surrogate Safety Assessment Model (SSAM), conflicts were extracted from output trajectory files (VISSIM). The results suggest that “cautious driving logic” reduced travel time and crash risk significantly when compared to the other two driving logics during peak hour conditions. Furthermore, the statistical analysis clearly demonstrated that “cautious driving logic” differs significantly from the other two driving logics. When Market Penetration Rates (MPR) were 50% or greater, the “cautious driving logic” significantly outperforms the other two driving logics. The results highlight that adopting “cautious driving logic” at an expressway may significantly increase safety at higher AV penetration rates (above 50%).
{"title":"Micro-Simulation Insights into the Safety and Operational Benefits of Autonomous Vehicles","authors":"Nalin Kumar Sekar;Vinayak Malaghan;Digvijay S. Pawar","doi":"10.26599/JICV.2023.9210007","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210007","url":null,"abstract":"Several past studies showed that Autonomous Vehicles (AVs) can reduce crash risk, stop-and-go traffic, and travel time. To analyze the safety benefits of AVs, most of the researchers proposed algorithms and simulation-based techniques. However, these studies have not assessed the safety benefits of AVs for different vehicle types under heterogeneous conditions. With this opportunity, this study focuses on the benefits of AVs in terms of safety for different penetration rates under heterogeneous conditions. This study considered three driving logics during peak hour conditions to assess the performance of AVs in terms of safety. In VISSIM, default driving behavior models for AVs were adopted to consider cautious and all-knowing driving logic and the third driving logic (Atkins) was modeled in VISSIM using parameters adopted from the previous studies. To this end, using VISSIM, the travel time output results were obtained. Also, using Surrogate Safety Assessment Model (SSAM), conflicts were extracted from output trajectory files (VISSIM). The results suggest that “cautious driving logic” reduced travel time and crash risk significantly when compared to the other two driving logics during peak hour conditions. Furthermore, the statistical analysis clearly demonstrated that “cautious driving logic” differs significantly from the other two driving logics. When Market Penetration Rates (MPR) were 50% or greater, the “cautious driving logic” significantly outperforms the other two driving logics. The results highlight that adopting “cautious driving logic” at an expressway may significantly increase safety at higher AV penetration rates (above 50%).","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"6 4","pages":"202-210"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10409209","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139504429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-01DOI: 10.26599/JICV.2023.9210017
Yuxiang Guo;Itsuo Kumazawa;Chuyo Kaku
The moving vehicles present different scales in the image due to the perspective effect of different viewpoint distances. The premise of advanced driver assistance system (ADAS) system for safety surveillance and safe driving is early identification of vehicle targets in front of the ego vehicle. The recognition of the same vehicle at different scales requires feature learning with scale invariance. Unlike existing feature vector methods, the normalized PCA eigenvalues calculated from feature maps are used to extract scale-invariant features. This study proposed a convolutional neural network (CNN) structure embedded with the module of multi-pooling-PCA for scale variant object recognition. The validation of the proposed network structure is verified by scale variant vehicle image dataset. Compared with scale invariant network algorithms of Scale-invariant feature transform (SIFT) and FSAF as well as miscellaneous networks, the proposed network can achieve the best recognition accuracy tested by the vehicle scale variant dataset. To testify the practicality of this modified network, the testing of public dataset ImageNet is done and the comparable results proved its effectiveness in general purpose of applications.
{"title":"Scale Variant Vehicle Object Recognition by CNN Module of Multi-Pooling-PCA Process","authors":"Yuxiang Guo;Itsuo Kumazawa;Chuyo Kaku","doi":"10.26599/JICV.2023.9210017","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210017","url":null,"abstract":"The moving vehicles present different scales in the image due to the perspective effect of different viewpoint distances. The premise of advanced driver assistance system (ADAS) system for safety surveillance and safe driving is early identification of vehicle targets in front of the ego vehicle. The recognition of the same vehicle at different scales requires feature learning with scale invariance. Unlike existing feature vector methods, the normalized PCA eigenvalues calculated from feature maps are used to extract scale-invariant features. This study proposed a convolutional neural network (CNN) structure embedded with the module of multi-pooling-PCA for scale variant object recognition. The validation of the proposed network structure is verified by scale variant vehicle image dataset. Compared with scale invariant network algorithms of Scale-invariant feature transform (SIFT) and FSAF as well as miscellaneous networks, the proposed network can achieve the best recognition accuracy tested by the vehicle scale variant dataset. To testify the practicality of this modified network, the testing of public dataset ImageNet is done and the comparable results proved its effectiveness in general purpose of applications.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"6 4","pages":"227-236"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10409228","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139504505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-01DOI: 10.26599/JICV.2023.9210015
Sailesh Acharya
With the likely future of autonomous vehicles (AVs) as private, ride-hailing, and pooled vehicles, it is important to consider all forms of AVs when estimating the impacts of automation on travel behavior. To aid this, this study jointly models the public interest in three forms of AVs (owning, ride-hailing, and using pooled services) and compares the interests in owning versus ride-hailing AVs using a combination of structural equation modeling and multivariate ordered probit modeling frameworks. Using the 2019 California Vehicle Survey data, we estimate the impacts of several exogenous and latent variables on all forms of AV adoption. We find that the individual, household, travel-related, and built-environment factors are related to different forms of AV adoption directly and indirectly through attitudes toward human and automated driving. We also report that human and automated driving sentiments have the highest impact on interest in owning an AV compared to interest in ride-hailing and using pooled AVs. We discuss several policy implications by calculating the pseudo-elasticity effects of exogenous variables and the sensitivities of the impacts on latent variables on different forms of AV adoption. For example, public interest in owning private AVs can be increased by more than 7% by making them familiar with autonomous technology.
{"title":"Private or On-Demand Autonomous Vehicles? Modeling Public Interest Using a Multivariate Model","authors":"Sailesh Acharya","doi":"10.26599/JICV.2023.9210015","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210015","url":null,"abstract":"With the likely future of autonomous vehicles (AVs) as private, ride-hailing, and pooled vehicles, it is important to consider all forms of AVs when estimating the impacts of automation on travel behavior. To aid this, this study jointly models the public interest in three forms of AVs (owning, ride-hailing, and using pooled services) and compares the interests in owning versus ride-hailing AVs using a combination of structural equation modeling and multivariate ordered probit modeling frameworks. Using the 2019 California Vehicle Survey data, we estimate the impacts of several exogenous and latent variables on all forms of AV adoption. We find that the individual, household, travel-related, and built-environment factors are related to different forms of AV adoption directly and indirectly through attitudes toward human and automated driving. We also report that human and automated driving sentiments have the highest impact on interest in owning an AV compared to interest in ride-hailing and using pooled AVs. We discuss several policy implications by calculating the pseudo-elasticity effects of exogenous variables and the sensitivities of the impacts on latent variables on different forms of AV adoption. For example, public interest in owning private AVs can be increased by more than 7% by making them familiar with autonomous technology.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"6 4","pages":"211-226"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10409208","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139504427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-01DOI: 10.26599/JICV.2023.9210021
Wenfeng Lin;Xiaowei Hu;Jian Wang
Reinforcement learning (RL) can free automated vehicles (AVs) from the car-following constraints and provide more possible explorations for mixed behavior. This study uses deep RL as AVs' longitudinal control and designs a multi-level objectives framework for AVs' trajectory decision-making based on multi-agent DRL. The saturated signalized intersection is taken as the research object to seek the upper limit of traffic efficiency and realize the specific target control. The simulation results demonstrate the convergence of the proposed framework in complex scenarios. When prioritizing throughputs as the primary objective and emissions as the secondary objective, both indicators exhibit a linear growth pattern with increasing market penetration rate (MPR). Compared with MPR is 0%, the throughputs can be increased by 69.2% when MPR is 100%. Compared with linear adaptive cruise control (LACC) under the same MPR, the emissions can also be reduced by up to 78.8%. Under the control of the fixed throughputs, compared with LACC, the emission benefits grow nearly linearly as MPR increases, it can reach 79.4% at 80% MPR. This study employs experimental results to analyze the behavioral changes of mixed flow and the mechanism of mixed autonomy to improve traffic efficiency. The proposed method is flexible and serves as a valuable tool for exploring and studying the behavior of mixed flow behavior and the patterns of mixed autonomy.
{"title":"Multi-Level Objective Control of AVs at a Saturated Signalized Intersection with Multi-Agent Deep Reinforcement Learning Approach","authors":"Wenfeng Lin;Xiaowei Hu;Jian Wang","doi":"10.26599/JICV.2023.9210021","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210021","url":null,"abstract":"Reinforcement learning (RL) can free automated vehicles (AVs) from the car-following constraints and provide more possible explorations for mixed behavior. This study uses deep RL as AVs' longitudinal control and designs a multi-level objectives framework for AVs' trajectory decision-making based on multi-agent DRL. The saturated signalized intersection is taken as the research object to seek the upper limit of traffic efficiency and realize the specific target control. The simulation results demonstrate the convergence of the proposed framework in complex scenarios. When prioritizing throughputs as the primary objective and emissions as the secondary objective, both indicators exhibit a linear growth pattern with increasing market penetration rate (MPR). Compared with MPR is 0%, the throughputs can be increased by 69.2% when MPR is 100%. Compared with linear adaptive cruise control (LACC) under the same MPR, the emissions can also be reduced by up to 78.8%. Under the control of the fixed throughputs, compared with LACC, the emission benefits grow nearly linearly as MPR increases, it can reach 79.4% at 80% MPR. This study employs experimental results to analyze the behavioral changes of mixed flow and the mechanism of mixed autonomy to improve traffic efficiency. The proposed method is flexible and serves as a valuable tool for exploring and studying the behavior of mixed flow behavior and the patterns of mixed autonomy.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"6 4","pages":"250-263"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10409224","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139504514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-01DOI: 10.26599/JICV.2023.9210023
Lan Yang;Jiaqi Yuan;Xiangmo Zhao;Shan Fang;Zeyu He;Jiahao Zhan;Zhiqiang Hu;Xia Li
With the increasing level of automation of autonomous vehicles, it is important to conduct comprehensive and extensive testing before releasing autonomous vehicles into the market. Traditional public road and closed-field testing failed to meet the requirements of high testing efficiency and scenario coverage. Therefore, scenario-based autonomous vehicle simulation testing has emerged. Many scenarios form the basis of simulation testing. Generating additional scenarios from an existing scenario library is a significant problem. Taking the scenarios of a proceeding vehicle cutting into an adjacent lane on highways as an example, based on an autoencoder and a generative adversarial network (GAN), a method that combines Transformer to capture the features of a long-time series, called SceGAN, is proposed to model and generate scenarios of autonomous vehicles on highways. An evaluation system is established to analyze the reliability of SceGAN using discriminative and predictive scores and further evaluate the effect of scenario generation in terms of similarity and coverage. Experiments showed that compared with TimeGAN and AEGAN, SceGAN is superior in data fidelity and availability, and their similarity increased by 27.22% and 21.39%, respectively. The coverage increased from 79.84% to 93.98% as generated scenarios increased from 2,547 to 50,000, indicating that the proposed method has a strong generalization capability for generating multiple trajectories, providing a basis for generating test scenarios and promoting autonomous vehicle testing.
{"title":"SceGAN: A Method for Generating Autonomous Vehicle Cut-In Scenarios on Highways Based on Deep Learning","authors":"Lan Yang;Jiaqi Yuan;Xiangmo Zhao;Shan Fang;Zeyu He;Jiahao Zhan;Zhiqiang Hu;Xia Li","doi":"10.26599/JICV.2023.9210023","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210023","url":null,"abstract":"With the increasing level of automation of autonomous vehicles, it is important to conduct comprehensive and extensive testing before releasing autonomous vehicles into the market. Traditional public road and closed-field testing failed to meet the requirements of high testing efficiency and scenario coverage. Therefore, scenario-based autonomous vehicle simulation testing has emerged. Many scenarios form the basis of simulation testing. Generating additional scenarios from an existing scenario library is a significant problem. Taking the scenarios of a proceeding vehicle cutting into an adjacent lane on highways as an example, based on an autoencoder and a generative adversarial network (GAN), a method that combines Transformer to capture the features of a long-time series, called SceGAN, is proposed to model and generate scenarios of autonomous vehicles on highways. An evaluation system is established to analyze the reliability of SceGAN using discriminative and predictive scores and further evaluate the effect of scenario generation in terms of similarity and coverage. Experiments showed that compared with TimeGAN and AEGAN, SceGAN is superior in data fidelity and availability, and their similarity increased by 27.22% and 21.39%, respectively. The coverage increased from 79.84% to 93.98% as generated scenarios increased from 2,547 to 50,000, indicating that the proposed method has a strong generalization capability for generating multiple trajectories, providing a basis for generating test scenarios and promoting autonomous vehicle testing.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"6 4","pages":"264-274"},"PeriodicalIF":0.0,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10409210","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139504506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-01DOI: 10.26599/JICV.2023.9210022
Lan Yang;Zeyu He;Xiangmo Zhao;Shan Fang;Jiaqi Yuan;Yixu He;Shijie Li;Songyan Liu
Real-time and accurate traffic light status recognition can provide reliable data support for autonomous vehicle decision-making and control systems. To address potential problems such as the minor component of traffic lights in the perceptual domain of visual sensors and the complexity of recognition scenarios, we propose an end-to-end traffic light status recognition method, ResNeSt50-CBAM-DINO (RC-DINO). First, we performed data cleaning on the Tsinghua-Tencent traffic lights (TTTL) and fused it with the Shanghai Jiao Tong University's traffic light dataset (S2TLD) to form a Chinese urban traffic light dataset (CUTLD). Second, we combined residual network with split-attention module-50 (ResNeSt50) and the convolutional block attention module (CBAM) to extract more significant traffic light features. Finally, the proposed RC-DINO and mainstream recognition algorithms were trained and analyzed using CUTLD. The experimental results show that, compared to the original DINO, RC-DINO improved the average precision (AP), AP at intersection over union (IOU) = 0.5 (AP 50 ), AP for small objects (APs), average recall (AR), and balanced F score (F1-Score) by 3.1 %, 1.6%, 3.4%, 0.9%, and 0.9%, respectively, and had a certain capability to recognize the partially covered traffic light status. The above results indicate that the proposed RC-DINO improved recognition performance and robustness, making it more suitable for traffic light status recognition tasks.
{"title":"A Deep Learning Method for Traffic Light Status Recognition","authors":"Lan Yang;Zeyu He;Xiangmo Zhao;Shan Fang;Jiaqi Yuan;Yixu He;Shijie Li;Songyan Liu","doi":"10.26599/JICV.2023.9210022","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210022","url":null,"abstract":"Real-time and accurate traffic light status recognition can provide reliable data support for autonomous vehicle decision-making and control systems. To address potential problems such as the minor component of traffic lights in the perceptual domain of visual sensors and the complexity of recognition scenarios, we propose an end-to-end traffic light status recognition method, ResNeSt50-CBAM-DINO (RC-DINO). First, we performed data cleaning on the Tsinghua-Tencent traffic lights (TTTL) and fused it with the Shanghai Jiao Tong University's traffic light dataset (S2TLD) to form a Chinese urban traffic light dataset (CUTLD). Second, we combined residual network with split-attention module-50 (ResNeSt50) and the convolutional block attention module (CBAM) to extract more significant traffic light features. Finally, the proposed RC-DINO and mainstream recognition algorithms were trained and analyzed using CUTLD. The experimental results show that, compared to the original DINO, RC-DINO improved the average precision (AP), AP at intersection over union (IOU) = 0.5 (AP\u0000<inf>50</inf>\u0000), AP for small objects (APs), average recall (AR), and balanced F score (F1-Score) by 3.1 %, 1.6%, 3.4%, 0.9%, and 0.9%, respectively, and had a certain capability to recognize the partially covered traffic light status. The above results indicate that the proposed RC-DINO improved recognition performance and robustness, making it more suitable for traffic light status recognition tasks.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"6 3","pages":"173-182"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10379588","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139081196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-01DOI: 10.26599/JICV.2023.9210016
Lipeng Cao;Yugong Luo;Yongsheng Wang;Jian Chen;Yansong He
On highways, vehicles that swerve out of their lane due to sideslip can pose a serious threat to the safety of autonomous vehicles. To ensure their safety, predicting the sideslip trajectories of such vehicles is crucial. However, the scarcity of data on vehicle sideslip scenarios makes it challenging to apply data-driven methods for prediction. Hence, this study uses a physical model-based approach to predict vehicle sideslip trajectories. Nevertheless, the traditional physical model-based method relies on constant input assumption, making its long-term prediction accuracy poor. To address this challenge, this study presents the time-series analysis and interacting multiple model-based (IMM) sideslip trajectory prediction (TSIMMSTP) method, which encompasses time-series analysis and multi-physical model fusion, for the prediction of vehicle sideslip trajectories. Firstly, we use the proposed adaptive quadratic exponential smoothing method with damping (AQESD) in the time-series analysis module to predict the input state sequence required by kinematic models. Then, we employ an IMM approach to fuse the prediction results of various physical models. The implementation of these two methods allows us to significantly enhance the long-term predictive accuracy and reduce the uncertainty of sideslip trajectories. The proposed method is evaluated through numerical simulations in vehicle sideslip scenarios, and the results clearly demonstrate that it improves the long-term prediction accuracy and reduces the uncertainty compared to other model-based methods.
{"title":"Vehicle Sideslip Trajectory Prediction Based on Time-Series Analysis and Multi-Physical Model Fusion","authors":"Lipeng Cao;Yugong Luo;Yongsheng Wang;Jian Chen;Yansong He","doi":"10.26599/JICV.2023.9210016","DOIUrl":"10.26599/JICV.2023.9210016","url":null,"abstract":"On highways, vehicles that swerve out of their lane due to sideslip can pose a serious threat to the safety of autonomous vehicles. To ensure their safety, predicting the sideslip trajectories of such vehicles is crucial. However, the scarcity of data on vehicle sideslip scenarios makes it challenging to apply data-driven methods for prediction. Hence, this study uses a physical model-based approach to predict vehicle sideslip trajectories. Nevertheless, the traditional physical model-based method relies on constant input assumption, making its long-term prediction accuracy poor. To address this challenge, this study presents the time-series analysis and interacting multiple model-based (IMM) sideslip trajectory prediction (TSIMMSTP) method, which encompasses time-series analysis and multi-physical model fusion, for the prediction of vehicle sideslip trajectories. Firstly, we use the proposed adaptive quadratic exponential smoothing method with damping (AQESD) in the time-series analysis module to predict the input state sequence required by kinematic models. Then, we employ an IMM approach to fuse the prediction results of various physical models. The implementation of these two methods allows us to significantly enhance the long-term predictive accuracy and reduce the uncertainty of sideslip trajectories. The proposed method is evaluated through numerical simulations in vehicle sideslip scenarios, and the results clearly demonstrate that it improves the long-term prediction accuracy and reduces the uncertainty compared to other model-based methods.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"6 3","pages":"161-172"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10310059","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135503821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-01DOI: 10.26599/JICV.2023.9210009
Benjamin Acar;Marius Sterling
The application of machine learning techniques, particularly in the context of autonomous driving solutions, has grown exponentially in recent years. As such, the collection of high-quality datasets has become a prerequisite for training new models. However, concerns about privacy and data usage have led to a growing demand for decentralized methods that can be learned without the need for pre-collected data. Federated learning (FL) offers a potential solution to this problem by enabling individual clients to contribute to the learning process by sending model updates rather than training data. While Federated Learning has proven successful in many cases, new challenges have emerged, especially in terms of network availability during training. Since a global instance is responsible for collecting updates from local clients, there is a risk of network downtime if the global server fails. In this study, we propose a novel and crucial concept that addresses this issue by adding redundancy to our network. Rather than deploying a single global model, we deploy a multitude of global models and utilize consensus algorithms to synchronize and keep these replicas updated. By utilizing these replicas, even if the global instance fails, the network remains available. As a result, our solution enables the development of reliable Federated Learning systems, particularly in system architectures suitable for infrastructure-enhanced autonomous driving. Consequently, our findings enable the more effective realization of use cases in the context of cooperative, connected, and automated mobility.
{"title":"Ensuring Federated Learning Reliability for Infrastructure-Enhanced Autonomous Driving","authors":"Benjamin Acar;Marius Sterling","doi":"10.26599/JICV.2023.9210009","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210009","url":null,"abstract":"The application of machine learning techniques, particularly in the context of autonomous driving solutions, has grown exponentially in recent years. As such, the collection of high-quality datasets has become a prerequisite for training new models. However, concerns about privacy and data usage have led to a growing demand for decentralized methods that can be learned without the need for pre-collected data. Federated learning (FL) offers a potential solution to this problem by enabling individual clients to contribute to the learning process by sending model updates rather than training data. While Federated Learning has proven successful in many cases, new challenges have emerged, especially in terms of network availability during training. Since a global instance is responsible for collecting updates from local clients, there is a risk of network downtime if the global server fails. In this study, we propose a novel and crucial concept that addresses this issue by adding redundancy to our network. Rather than deploying a single global model, we deploy a multitude of global models and utilize consensus algorithms to synchronize and keep these replicas updated. By utilizing these replicas, even if the global instance fails, the network remains available. As a result, our solution enables the development of reliable Federated Learning systems, particularly in system architectures suitable for infrastructure-enhanced autonomous driving. Consequently, our findings enable the more effective realization of use cases in the context of cooperative, connected, and automated mobility.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"6 3","pages":"125-135"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10379565","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139081239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-01DOI: 10.26599/JICV.2023.9210024
Kunjun Wang;Ye Xiao;Yixu He
Driven by technological innovation and digital evolution, the current automotive industry is standing at the cusp of a transformative era (Liu et al., 2023). As urban centers continue to expand and intensify the demands on transportation networks, the need for solutions to alleviate congestion, boost traffic efficiency, and enhance road safety becomes increasingly urgent. On this occasion, intelligent and connected vehicles, integrating vehicles, infrastructure, and cloud computing, promise a smarter mode of passenger transportation and pave the way for a more interconnected and responsive urban transit ecosystem (Cao et al., 2023). Therefore, traditional passenger buses are on the verge of significant transformation in terms of their functional technologies and operational models. This will bring about a host of benefits such as higher efficiency, better passenger experiences, and safer road environments. This paper provides a comprehensive outlook on intelligent and connected passenger buses (ICPBs), delving into the integrated vehicle-road-cloud platform and highlighting the key technologies that will shape the future bus system. As illustrated in Fig. 1, it showcases the key perspectives on the future of ICPBs.
{"title":"Charting the Future: Intelligent and Connected Vehicles Reshaping the Bus System","authors":"Kunjun Wang;Ye Xiao;Yixu He","doi":"10.26599/JICV.2023.9210024","DOIUrl":"10.26599/JICV.2023.9210024","url":null,"abstract":"Driven by technological innovation and digital evolution, the current automotive industry is standing at the cusp of a transformative era (Liu et al., 2023). As urban centers continue to expand and intensify the demands on transportation networks, the need for solutions to alleviate congestion, boost traffic efficiency, and enhance road safety becomes increasingly urgent. On this occasion, intelligent and connected vehicles, integrating vehicles, infrastructure, and cloud computing, promise a smarter mode of passenger transportation and pave the way for a more interconnected and responsive urban transit ecosystem (Cao et al., 2023). Therefore, traditional passenger buses are on the verge of significant transformation in terms of their functional technologies and operational models. This will bring about a host of benefits such as higher efficiency, better passenger experiences, and safer road environments. This paper provides a comprehensive outlook on intelligent and connected passenger buses (ICPBs), delving into the integrated vehicle-road-cloud platform and highlighting the key technologies that will shape the future bus system. As illustrated in Fig. 1, it showcases the key perspectives on the future of ICPBs.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"6 3","pages":"113-115"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10310061","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135504037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：