Pub Date : 2023-09-01DOI: 10.1109/MITS.2023.3263890
Keno Garlichs, Maximilian Huber, Lars C. Wolf
Collective perception is one of the key ideas of vehicular networking and allows the exchange of data about perceived objects. However, unlike autonomous driving systems, human drivers cannot screen large numbers of objects to judge their dangerousness. An assistance system in the vehicle, therefore, must do this job. This article shows a concept for a human–machine interface that could be used to warn the driver in case such a system detects an actually dangerous object. A user study in a driving simulator was performed to evaluate its potential to prevent accidents. Eye-tracking glasses were used to analyze the driver’s gaze during different types of situations. Furthermore, the participants’ subjective experience was evaluated with a questionnaire. Results show that drivers trust the system and brake earlier and with more control due to the warnings, and ultimately, the majority of accidents could be avoided thanks to the warnings.
{"title":"How Human Drivers Can Benefit From Collective Perception: A User Study","authors":"Keno Garlichs, Maximilian Huber, Lars C. Wolf","doi":"10.1109/MITS.2023.3263890","DOIUrl":"https://doi.org/10.1109/MITS.2023.3263890","url":null,"abstract":"Collective perception is one of the key ideas of vehicular networking and allows the exchange of data about perceived objects. However, unlike autonomous driving systems, human drivers cannot screen large numbers of objects to judge their dangerousness. An assistance system in the vehicle, therefore, must do this job. This article shows a concept for a human–machine interface that could be used to warn the driver in case such a system detects an actually dangerous object. A user study in a driving simulator was performed to evaluate its potential to prevent accidents. Eye-tracking glasses were used to analyze the driver’s gaze during different types of situations. Furthermore, the participants’ subjective experience was evaluated with a questionnaire. Results show that drivers trust the system and brake earlier and with more control due to the warnings, and ultimately, the majority of accidents could be avoided thanks to the warnings.","PeriodicalId":48826,"journal":{"name":"IEEE Intelligent Transportation Systems Magazine","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44254352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-01DOI: 10.1109/mits.2023.3295394
Yisheng Lv
{"title":"Infrastructure Perception and Control Laboratory [ITS Research Lab]","authors":"Yisheng Lv","doi":"10.1109/mits.2023.3295394","DOIUrl":"https://doi.org/10.1109/mits.2023.3295394","url":null,"abstract":"","PeriodicalId":48826,"journal":{"name":"IEEE Intelligent Transportation Systems Magazine","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62345856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Autonomous driving (AD), including single-vehicle intelligent AD and vehicle–infrastructure cooperative AD, has become a current research hot spot in academia and industry, and multi-sensor fusion is a fundamental task for AD system perception. However, the multi-sensor fusion process faces the problem of differences in the type and dimensionality of sensory data acquired using different sensors (cameras, lidar, millimeter-wave radar, and so on) as well as differences in the performance of environmental perception caused by using different fusion strategies. In this article, we study multiple papers on multi-sensor fusion in the field of AD and address the problem that the category division in current multi-sensor fusion perception is not detailed and clear enough and is more subjective, which makes the classification strategies differ significantly among similar algorithms. We innovatively propose a multi-sensor fusion taxonomy, which divides the fusion perception classification strategies into two categories—symmetric fusion and asymmetric fusion—and seven subcategories of strategy combinations, such as data, features, and results. In addition, the reliability of current AD perception is limited by its insufficient environment perception capability and the robustness of data-driven methods in dealing with extreme situations (e.g., blind areas). This article also summarizes the innovative applications of multi-sensor fusion classification strategies in AD cooperative perception.
{"title":"Multi-Sensor Fusion and Cooperative Perception for Autonomous Driving: A Review","authors":"Chao Xiang, Chen Feng, Xiaopo Xie, Botian Shi, Hao Lu, Yisheng Lv, Mingchuan Yang, Zhendong Niu","doi":"10.1109/MITS.2023.3283864","DOIUrl":"https://doi.org/10.1109/MITS.2023.3283864","url":null,"abstract":"Autonomous driving (AD), including single-vehicle intelligent AD and vehicle–infrastructure cooperative AD, has become a current research hot spot in academia and industry, and multi-sensor fusion is a fundamental task for AD system perception. However, the multi-sensor fusion process faces the problem of differences in the type and dimensionality of sensory data acquired using different sensors (cameras, lidar, millimeter-wave radar, and so on) as well as differences in the performance of environmental perception caused by using different fusion strategies. In this article, we study multiple papers on multi-sensor fusion in the field of AD and address the problem that the category division in current multi-sensor fusion perception is not detailed and clear enough and is more subjective, which makes the classification strategies differ significantly among similar algorithms. We innovatively propose a multi-sensor fusion taxonomy, which divides the fusion perception classification strategies into two categories—symmetric fusion and asymmetric fusion—and seven subcategories of strategy combinations, such as data, features, and results. In addition, the reliability of current AD perception is limited by its insufficient environment perception capability and the robustness of data-driven methods in dealing with extreme situations (e.g., blind areas). This article also summarizes the innovative applications of multi-sensor fusion classification strategies in AD cooperative perception.","PeriodicalId":48826,"journal":{"name":"IEEE Intelligent Transportation Systems Magazine","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42207262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-01DOI: 10.1109/MITS.2023.3265309
Hongliang Guo, Wenda Sheng, Chen Gao, Yaochu Jin
This article studies reliable shortest path (RSP) problems in stochastic transportation networks. The term reliability in the RSP literature has many definitions, e.g., 1) maximal stochastic on-time arrival probability, 2) minimal travel time with a high-confidence constraint, 3) minimal mean and standard deviation combination, and 4) minimal expected disutility. To the best of our knowledge, almost all state-of-the-art RSP solutions are designed to target one specific RSP objective, and it is very difficult, if not impossible, to adapt them to other RSP objectives. To bridge the gap, this article develops a distributional reinforcement learning (DRL)-based algorithm, namely, DRL-Router, which serves as a universal solution to the four aforementioned RSP problems. DRL-Router employs the DRL method to approximate the full travel time distribution of a given routing policy and then makes improvements with respect to the user-defined RSP objective through a generalized policy iteration scheme. DRL-Router is 1) universal, i.e., it is applicable to a variety of RSP objectives; 2) model free, i.e., it does not rely on well calibrated travel time distribution models; 3) it is adaptive with navigation objective changes; and 4) fast, i.e., it performs real-time decision making. Extensive experimental results and comparisons with baseline algorithms in various transportation networks justify both the accuracy and efficiency of DRL-Router.
{"title":"DRL Router: Distributional Reinforcement Learning-Based Router for Reliable Shortest Path Problems","authors":"Hongliang Guo, Wenda Sheng, Chen Gao, Yaochu Jin","doi":"10.1109/MITS.2023.3265309","DOIUrl":"https://doi.org/10.1109/MITS.2023.3265309","url":null,"abstract":"This article studies reliable shortest path (RSP) problems in stochastic transportation networks. The term reliability in the RSP literature has many definitions, e.g., 1) maximal stochastic on-time arrival probability, 2) minimal travel time with a high-confidence constraint, 3) minimal mean and standard deviation combination, and 4) minimal expected disutility. To the best of our knowledge, almost all state-of-the-art RSP solutions are designed to target one specific RSP objective, and it is very difficult, if not impossible, to adapt them to other RSP objectives. To bridge the gap, this article develops a distributional reinforcement learning (DRL)-based algorithm, namely, DRL-Router, which serves as a universal solution to the four aforementioned RSP problems. DRL-Router employs the DRL method to approximate the full travel time distribution of a given routing policy and then makes improvements with respect to the user-defined RSP objective through a generalized policy iteration scheme. DRL-Router is 1) universal, i.e., it is applicable to a variety of RSP objectives; 2) model free, i.e., it does not rely on well calibrated travel time distribution models; 3) it is adaptive with navigation objective changes; and 4) fast, i.e., it performs real-time decision making. Extensive experimental results and comparisons with baseline algorithms in various transportation networks justify both the accuracy and efficiency of DRL-Router.","PeriodicalId":48826,"journal":{"name":"IEEE Intelligent Transportation Systems Magazine","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42937979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-01DOI: 10.1109/MITS.2023.3272501
Zhuolin Deng, Ming-cheng Cai, Chen Xiong
Autonomous transportation systems (ATSs) focus on traffic services and have become more capable of handling stochastic traffic scenarios. The preliminary work for designing and constructing ATS management and control systems is to develop an instructive and systematic architecture. However, the construction process of a conventional traffic system generally follows a function- and demand-oriented way. Thus, few studies have addressed architecture integrity evaluation and verification. In this work, we propose a collaboration mechanism-based approach to ATS architecture integrity evaluation. First, to provide a clear description of ATSs, ATS theory was systematically introduced through the generation, definition, and property of its basic elements, and then the relations between each element were analyzed based on the concept of microservices. Second, a collaboration mechanism on physical architecture was proposed to realize the adaptive construction of the architecture. Additionally, to fulfill the evaluation of architecture integrity, a contrast scheme combined with system function and information flow (IF) was determined, and accordingly, two independent ways were determined to obtain both the reference and calculated results. Finally, the scenario of automatic vehicles passing through an intersection was illustrated to demonstrate the feasibility of this static simulation evaluation method for the scenario architecture, and achieved a 100% function integrity rate and 93.3% IF integrity rate. A successful application in the case study shows that the proposed method could be extended to more general traffic scenarios.
{"title":"An Architecture Integrity Simulation Evaluation Method for an Autonomous Transportation System Based on an Information-Triggered Collaboration Mechanism","authors":"Zhuolin Deng, Ming-cheng Cai, Chen Xiong","doi":"10.1109/MITS.2023.3272501","DOIUrl":"https://doi.org/10.1109/MITS.2023.3272501","url":null,"abstract":"Autonomous transportation systems (ATSs) focus on traffic services and have become more capable of handling stochastic traffic scenarios. The preliminary work for designing and constructing ATS management and control systems is to develop an instructive and systematic architecture. However, the construction process of a conventional traffic system generally follows a function- and demand-oriented way. Thus, few studies have addressed architecture integrity evaluation and verification. In this work, we propose a collaboration mechanism-based approach to ATS architecture integrity evaluation. First, to provide a clear description of ATSs, ATS theory was systematically introduced through the generation, definition, and property of its basic elements, and then the relations between each element were analyzed based on the concept of microservices. Second, a collaboration mechanism on physical architecture was proposed to realize the adaptive construction of the architecture. Additionally, to fulfill the evaluation of architecture integrity, a contrast scheme combined with system function and information flow (IF) was determined, and accordingly, two independent ways were determined to obtain both the reference and calculated results. Finally, the scenario of automatic vehicles passing through an intersection was illustrated to demonstrate the feasibility of this static simulation evaluation method for the scenario architecture, and achieved a 100% function integrity rate and 93.3% IF integrity rate. A successful application in the case study shows that the proposed method could be extended to more general traffic scenarios.","PeriodicalId":48826,"journal":{"name":"IEEE Intelligent Transportation Systems Magazine","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46330686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The short-term passenger flow prediction of the urban rail transit (URT) system is of great significance for traffic operation and management. Emerging deep learning-based models provide effective methods to improve prediction accuracy. However, most of the existing models mainly predict the passenger flow on general weekdays and weekends. Only a few studies focus on predicting the passenger flow on holidays, which is a significantly challenging task for traffic management because of its suddenness and irregularity. To this end, we take passenger flow prediction in the URT system during the New Year’s Day holiday as an example to study passenger flow prediction on holidays in depth. We propose a deep learning-based model, Spatial–Temporal Attention Fusion Network (STAFN), for short-term passenger flow prediction in the URT system during New Year’s Day, which includes a novel multigraph attention network (MGATN), convolution–attention (conv–attention) block, and feature fusion block. The MGATN is applied to extract the complex spatial dependencies of passenger flow dynamically, and the conv–attention block is applied to extract the temporal dependencies of passenger flow from global and local perspectives. Moreover, in addition to historical passenger flow data, social media data, which have proved that they can effectively reflect the evolution trend of passenger flow during events, are fused into the feature fusion block of STAFN. STAFN is tested on two large-scale URT automatic fare collection system datasets from Nanning, China, on New Year’s Day, and the prediction performance of the model is compared with that of several basic and advanced prediction models. The results demonstrate better robustness and advantages of STAFN among benchmark methods, which can provide overwhelming support for practical applications of short-term passenger flow prediction on New Year’s Day.
{"title":"Spatiotemporal Attention Fusion Network for Short-Term Passenger Flow Prediction on New Year’s Day Holiday in Urban Rail Transit System","authors":"Shuxin Zhang, Jinlei Zhang, Lixing Yang, Jiateng Yin, Ziyou Gao","doi":"10.1109/MITS.2023.3265808","DOIUrl":"https://doi.org/10.1109/MITS.2023.3265808","url":null,"abstract":"The short-term passenger flow prediction of the urban rail transit (URT) system is of great significance for traffic operation and management. Emerging deep learning-based models provide effective methods to improve prediction accuracy. However, most of the existing models mainly predict the passenger flow on general weekdays and weekends. Only a few studies focus on predicting the passenger flow on holidays, which is a significantly challenging task for traffic management because of its suddenness and irregularity. To this end, we take passenger flow prediction in the URT system during the New Year’s Day holiday as an example to study passenger flow prediction on holidays in depth. We propose a deep learning-based model, Spatial–Temporal Attention Fusion Network (STAFN), for short-term passenger flow prediction in the URT system during New Year’s Day, which includes a novel multigraph attention network (MGATN), convolution–attention (conv–attention) block, and feature fusion block. The MGATN is applied to extract the complex spatial dependencies of passenger flow dynamically, and the conv–attention block is applied to extract the temporal dependencies of passenger flow from global and local perspectives. Moreover, in addition to historical passenger flow data, social media data, which have proved that they can effectively reflect the evolution trend of passenger flow during events, are fused into the feature fusion block of STAFN. STAFN is tested on two large-scale URT automatic fare collection system datasets from Nanning, China, on New Year’s Day, and the prediction performance of the model is compared with that of several basic and advanced prediction models. The results demonstrate better robustness and advantages of STAFN among benchmark methods, which can provide overwhelming support for practical applications of short-term passenger flow prediction on New Year’s Day.","PeriodicalId":48826,"journal":{"name":"IEEE Intelligent Transportation Systems Magazine","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43928911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-01DOI: 10.1109/mits.2023.3295396
Fei-Yue Wang
{"title":"The Story of IEEE ICVES: The Dark Days Before China's Boom in New Energy Vehicles [History and Perspectives]","authors":"Fei-Yue Wang","doi":"10.1109/mits.2023.3295396","DOIUrl":"https://doi.org/10.1109/mits.2023.3295396","url":null,"abstract":"","PeriodicalId":48826,"journal":{"name":"IEEE Intelligent Transportation Systems Magazine","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62345908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-01DOI: 10.1109/MITS.2023.3238026
Longpai Pan, Yu Zhou, Q. Meng, Yun Wang
Due to the mixed right-of-way and varying traffic conditions, urban bus operations are often subject to random delays and eventually bus bunching, undermining the schedule reliability. The existing studies have proposed different models to emulate bus bunching and control strategies to mitigate bus bunching, yet few of them considered the effect of the three important traffic factors: intersections with signal coordination, varying traffic volume, and passenger demand. To fill in the research gap, we first define the stop-level frequency of bus bunching events for a bus route in this study. We proceed to present a simulation-based approach to quantify the impact of the three traffic factors on bus bunching. Numerical experiments based on different scenarios are carried out to reveal the cause–effect relationship between these factors and bus bunching events. Contributors to bus bunching are evaluated, and the effect of control delays is examined through statistical measurements. Finally, a real-world case study based on bus route 51 in Singapore is performed, and some insights are provided to alleviate the bus bunching phenomenon.
{"title":"Impact Analysis of Traffic Factors on Urban Bus Bunching","authors":"Longpai Pan, Yu Zhou, Q. Meng, Yun Wang","doi":"10.1109/MITS.2023.3238026","DOIUrl":"https://doi.org/10.1109/MITS.2023.3238026","url":null,"abstract":"Due to the mixed right-of-way and varying traffic conditions, urban bus operations are often subject to random delays and eventually bus bunching, undermining the schedule reliability. The existing studies have proposed different models to emulate bus bunching and control strategies to mitigate bus bunching, yet few of them considered the effect of the three important traffic factors: intersections with signal coordination, varying traffic volume, and passenger demand. To fill in the research gap, we first define the stop-level frequency of bus bunching events for a bus route in this study. We proceed to present a simulation-based approach to quantify the impact of the three traffic factors on bus bunching. Numerical experiments based on different scenarios are carried out to reveal the cause–effect relationship between these factors and bus bunching events. Contributors to bus bunching are evaluated, and the effect of control delays is examined through statistical measurements. Finally, a real-world case study based on bus route 51 in Singapore is performed, and some insights are provided to alleviate the bus bunching phenomenon.","PeriodicalId":48826,"journal":{"name":"IEEE Intelligent Transportation Systems Magazine","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46473393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","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：