Pub Date : 2025-03-01DOI: 10.26599/JICV.2024.9210051
Changxi Ma;Xiaoyu Huang;Yongpeng Zhao;Tao Wang;Bo Du
The transportation department relies on accurate traffic forecasting for effective decision-making. However, determining relevant parameters for existing traffic flow prediction models poses challenges. To address this issue, this study proposes a hybrid model, sparrow search algorithm-gated recurrent unit-long short-term memory (SSA-GRU-LSTM), which leverages the SSA to optimize the GRUs and LSTM networks. The SSA is employed to identify the optimal parameters for the GRU-LSTM model, mitigating their impact on prediction accuracy. This model integrates the predictive efficiency of the GRU, LSTM's capability in temporal data analysis, and the fast convergence and global search attributes of the SSA. Comprehensive experiments are conducted to validate the proposed method via traffic flow datasets, and the results are compared with those of baseline models. The numerical results demonstrate the superior performance of the SSA-GRU-LSTM model. Compared with the baselines, the proposed model results in reductions in the root mean square error (RMSE) of 4.632%–45.206%, the mean absolute error (MAE) of 2.608%–53.327%, the mean absolute percentage error (MAPE) of 1.324%–13.723%, and an increase in $R^{2}$ of 0.5%–17.5%. Consequently, the SSA-GRU-LSTM model has high prediction accuracy and measurement stability.
{"title":"GRU-LSTM Model Based on the SSA for Short-Term Traffic Flow Prediction","authors":"Changxi Ma;Xiaoyu Huang;Yongpeng Zhao;Tao Wang;Bo Du","doi":"10.26599/JICV.2024.9210051","DOIUrl":"https://doi.org/10.26599/JICV.2024.9210051","url":null,"abstract":"The transportation department relies on accurate traffic forecasting for effective decision-making. However, determining relevant parameters for existing traffic flow prediction models poses challenges. To address this issue, this study proposes a hybrid model, sparrow search algorithm-gated recurrent unit-long short-term memory (SSA-GRU-LSTM), which leverages the SSA to optimize the GRUs and LSTM networks. The SSA is employed to identify the optimal parameters for the GRU-LSTM model, mitigating their impact on prediction accuracy. This model integrates the predictive efficiency of the GRU, LSTM's capability in temporal data analysis, and the fast convergence and global search attributes of the SSA. Comprehensive experiments are conducted to validate the proposed method via traffic flow datasets, and the results are compared with those of baseline models. The numerical results demonstrate the superior performance of the SSA-GRU-LSTM model. Compared with the baselines, the proposed model results in reductions in the root mean square error (RMSE) of 4.632%–45.206%, the mean absolute error (MAE) of 2.608%–53.327%, the mean absolute percentage error (MAPE) of 1.324%–13.723%, and an increase in <tex>$R^{2}$</tex> of 0.5%–17.5%. Consequently, the SSA-GRU-LSTM model has high prediction accuracy and measurement stability.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"8 1","pages":"1-10"},"PeriodicalIF":0.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10960593","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808858","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}
To address existing shortcomings such as short time domains and low interpretability, this study proposes a long-term trajectory prediction model for leading vehicles that considers the impact of traffic flow. Through an analysis of trailing trajectory data from the HighD natural driving dataset, fitting relationships for the following behavior patterns were derived. Building upon the intelligent driver model (IDM), three long-term trajectory prediction models were established: acceleration delta velocity (ADV), space delta velocity intelligent driver model (SDVIDM), and space velocity intelligent driver model (SVIDM). These models were then compared with the IDM model through simulations. The results indicate that when there is one vehicle ahead, under aggressive following conditions, the ADV model outperforms the IDM model, reducing the root mean square errors in acceleration, speed, and position by 79.61%, 91.26%, and 87.82%, respectively. In scenarios with two vehicles ahead and conservative short-distance following, the SDVIDM model exhibits reductions of 83.42%, 92.85%, and 92.25%, while the SVIDM model shows reductions of 82.31%, 92.47%, and 94.02%, respectively, compared to the IDM model.
{"title":"Long-Term Trajectory Prediction Method Based on Highway Vehicle-Following Behavior Patterns","authors":"Zhichao An;Yimin Wu;Fan Zhang;Dong Zhang;Bolin Gao;Suying Zhang;Guang Zhou;Aoning Jia","doi":"10.26599/JICV.2024.9210045","DOIUrl":"https://doi.org/10.26599/JICV.2024.9210045","url":null,"abstract":"To address existing shortcomings such as short time domains and low interpretability, this study proposes a long-term trajectory prediction model for leading vehicles that considers the impact of traffic flow. Through an analysis of trailing trajectory data from the HighD natural driving dataset, fitting relationships for the following behavior patterns were derived. Building upon the intelligent driver model (IDM), three long-term trajectory prediction models were established: acceleration delta velocity (ADV), space delta velocity intelligent driver model (SDVIDM), and space velocity intelligent driver model (SVIDM). These models were then compared with the IDM model through simulations. The results indicate that when there is one vehicle ahead, under aggressive following conditions, the ADV model outperforms the IDM model, reducing the root mean square errors in acceleration, speed, and position by 79.61%, 91.26%, and 87.82%, respectively. In scenarios with two vehicles ahead and conservative short-distance following, the SDVIDM model exhibits reductions of 83.42%, 92.85%, and 92.25%, while the SVIDM model shows reductions of 82.31%, 92.47%, and 94.02%, respectively, compared to the IDM model.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"8 1","pages":"1-11"},"PeriodicalIF":0.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10960598","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808859","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 : 2025-03-01DOI: 10.26599/JICV.2024.9210048
Tanjida Tahmina;Mark Fuchs;Chao Shi
This study scrutinizes the use of virtual reality (VR) in automated driving simulation environments, with a focus on publication year, driving simulator type, virtual reality (VR) technology, and the advantages and drawbacks of VR application in autonomous driving simulations. An analysis of 87 articles from 10 databases reveals a notable uptick in VR-related research for autonomous driving simulations after 2015, demonstrating VR's potential in crafting realistic and secure environments for driving research. The identified challenges include motion sickness in participants, validation of driving scenarios, and simulator discomfort, alongside other obstacles and benefits. This study delineates existing research gaps and proposes research directions, aiming to inform and guide subsequent scholarly work at the intersection of VR and autonomous driving research.
{"title":"Use of Virtual Reality for Automated Driving Simulation","authors":"Tanjida Tahmina;Mark Fuchs;Chao Shi","doi":"10.26599/JICV.2024.9210048","DOIUrl":"https://doi.org/10.26599/JICV.2024.9210048","url":null,"abstract":"This study scrutinizes the use of virtual reality (VR) in automated driving simulation environments, with a focus on publication year, driving simulator type, virtual reality (VR) technology, and the advantages and drawbacks of VR application in autonomous driving simulations. An analysis of 87 articles from 10 databases reveals a notable uptick in VR-related research for autonomous driving simulations after 2015, demonstrating VR's potential in crafting realistic and secure environments for driving research. The identified challenges include motion sickness in participants, validation of driving scenarios, and simulator discomfort, alongside other obstacles and benefits. This study delineates existing research gaps and proposes research directions, aiming to inform and guide subsequent scholarly work at the intersection of VR and autonomous driving research.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"8 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10960597","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808939","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}
This study focuses on predicting the motion states and intentions of HDVs at unsignalized intersections. On the basis of a risk field-driven driving behavior model for uncontrolled intersections, multiple motion hypotheses are formulated to characterize the motion planning process of drivers in multivehicle conflict scenarios. Each motion hypothesis is modeled and expressed separately via the extended Kalman filter (EKF) model. These EKF models were combined to construct an interacting multiple model (IMM) framework. This framework estimates which motion hypothesis the driver is more likely to adopt as a strategy. By integrating the predictions of multiple motion hypotheses, more accurate predictions are obtained. Ultimately, it estimates the driver's travel path and acceptable risk level and predicts the spatiotemporal trajectory of HDVs within a future time window.
{"title":"Trajectory Prediction of Human-Driven Vehicles on the Basis of Risk Field Theory and Interaction Multiple Models","authors":"Zhaojie Wang;Guangquan Lu;Jinghua Wang;Haitian Tan;Renjing Tang","doi":"10.26599/JICV.2024.9210052","DOIUrl":"https://doi.org/10.26599/JICV.2024.9210052","url":null,"abstract":"This study focuses on predicting the motion states and intentions of HDVs at unsignalized intersections. On the basis of a risk field-driven driving behavior model for uncontrolled intersections, multiple motion hypotheses are formulated to characterize the motion planning process of drivers in multivehicle conflict scenarios. Each motion hypothesis is modeled and expressed separately via the extended Kalman filter (EKF) model. These EKF models were combined to construct an interacting multiple model (IMM) framework. This framework estimates which motion hypothesis the driver is more likely to adopt as a strategy. By integrating the predictions of multiple motion hypotheses, more accurate predictions are obtained. Ultimately, it estimates the driver's travel path and acceptable risk level and predicts the spatiotemporal trajectory of HDVs within a future time window.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"8 1","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10960594","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808989","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 : 2024-12-01DOI: 10.26599/JICV.2023.9210044
Jian Chen;Yunfeng Xiang;Yugong Luo;Keqiang Li;Xiaomin Lian
The behaviors of front vehicles are important factors that can influence the driving safety of autonomous vehicles on highways. This situation poses a serious threat to the security of autonomous vehicles, especially when front vehicle sideslip occurs. To address this problem, a decision-making approach can be used to promote the emergency obstacle avoidance capability of autonomous vehicles. First, the front sideslip vehicle trajectory was predicted by the kinematic models Constant Acceleration (CA), Constant Turn Rate and Velocity (CTRV), and Constant Turn Rate and Acceleration (CTRA) based on the front vehicle sideslip identification results. The CTRA prediction approach is chosen by comparing the prediction errors of the three models. To enhance the obstacle avoidance ability of autonomous vehicles, a novel trajectory planning method based on a driving characteristic vector is proposed. Model prediction control (MPC) is used to track the planned trajectory. Finally, the cosimulation platform of Simulink and Carsim was built. The simulation results show that autonomous vehicles can avoid collisions with front sideslip vehicles through the proposed approach, and the proposed trajectory planning approach has better obstacle avoidance ability than does the traditional approach.
{"title":"Decision Making and Control of Autonomous Vehicles Under the Condition of Front Vehicle Sideslip","authors":"Jian Chen;Yunfeng Xiang;Yugong Luo;Keqiang Li;Xiaomin Lian","doi":"10.26599/JICV.2023.9210044","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210044","url":null,"abstract":"The behaviors of front vehicles are important factors that can influence the driving safety of autonomous vehicles on highways. This situation poses a serious threat to the security of autonomous vehicles, especially when front vehicle sideslip occurs. To address this problem, a decision-making approach can be used to promote the emergency obstacle avoidance capability of autonomous vehicles. First, the front sideslip vehicle trajectory was predicted by the kinematic models Constant Acceleration (CA), Constant Turn Rate and Velocity (CTRV), and Constant Turn Rate and Acceleration (CTRA) based on the front vehicle sideslip identification results. The CTRA prediction approach is chosen by comparing the prediction errors of the three models. To enhance the obstacle avoidance ability of autonomous vehicles, a novel trajectory planning method based on a driving characteristic vector is proposed. Model prediction control (MPC) is used to track the planned trajectory. Finally, the cosimulation platform of Simulink and Carsim was built. The simulation results show that autonomous vehicles can avoid collisions with front sideslip vehicles through the proposed approach, and the proposed trajectory planning approach has better obstacle avoidance ability than does the traditional approach.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"7 4","pages":"248-257"},"PeriodicalIF":0.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10823098","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918489","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 : 2024-12-01DOI: 10.26599/JICV.2023.9210042
Chen Tu;Liang Wang;Jaehyuck Lim;Inhi Kim
The advancement of technology has propelled autonomous driving into the public spotlight over the past decade, establishing it as a strategic focal point for technological competition among countries (Lin et al., 2023b). For instance, the U.S. Department of Transportation released a series of influential documents outlining top-level designs for autonomous driving, ranging from the ‘Federal Autonomous Vehicle Policy Guide’ in 2016 to the ‘Ensuring the U.S. Leadership in Automated Driving: Autonomous Vehicle 4.0’ in 2020. In 2016, Japan formulated a roadmap to promote the adoption of autonomous driving, culminating in the launch of its inaugural L4-level autonomous vehicle public road operation service in 2023. Moreover, the development of autonomous driving in Europe is primarily concentrated in countries such as Germany, France, UK, and Sweden. These countries boast robust automotive industry foundations in the field of autonomous driving, accompanied by advanced systems and frameworks in terms of regulations and standards.
{"title":"Advancements and Prospects in Multisensor Fusion for Autonomous Driving","authors":"Chen Tu;Liang Wang;Jaehyuck Lim;Inhi Kim","doi":"10.26599/JICV.2023.9210042","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210042","url":null,"abstract":"The advancement of technology has propelled autonomous driving into the public spotlight over the past decade, establishing it as a strategic focal point for technological competition among countries (Lin et al., 2023b). For instance, the U.S. Department of Transportation released a series of influential documents outlining top-level designs for autonomous driving, ranging from the ‘Federal Autonomous Vehicle Policy Guide’ in 2016 to the ‘Ensuring the U.S. Leadership in Automated Driving: Autonomous Vehicle 4.0’ in 2020. In 2016, Japan formulated a roadmap to promote the adoption of autonomous driving, culminating in the launch of its inaugural L4-level autonomous vehicle public road operation service in 2023. Moreover, the development of autonomous driving in Europe is primarily concentrated in countries such as Germany, France, UK, and Sweden. These countries boast robust automotive industry foundations in the field of autonomous driving, accompanied by advanced systems and frameworks in terms of regulations and standards.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"7 4","pages":"245-247"},"PeriodicalIF":0.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10823101","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918293","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 : 2024-12-01DOI: 10.26599/JICV.2023.9210047
Syed Muzammil Abbas Rizvi;Bernhard Friedrich
The macroscopic fundamental diagram (MFD) represents the aggregated traffic states of a road network. However, the uniqueness of an empirically estimated MFD cannot be guaranteed due to the problem of link selection. Instationarity and varying flow patterns make it difficult to select link flows that are representative of the traffic state in the whole network. This study developed a new method for selecting links equipped with loop detectors that represent a particular traffic state of a road network. The method utilizes a metric of heterogeneity characterizing the role of a network link over the time of day. The dispersion metric indicates the heterogeneity in traffic states and the dynamic role of each time interval. It ranks links based on the heterogeneity-weighted saturation level, with the highest-rank links representing the most homogeneous subset of sample links. This study compared classical and proposed dynamic weights using loop detector data from Zurich and London and a simulated network. Sample links were selected based on different saturation levels, and the saturation level was associated with the heterogeneity level to identify the links creating heterogeneity in the road network.
{"title":"Improving the Representation of Traffic States: A Novel Method for Link Selection of Urban Road Networks","authors":"Syed Muzammil Abbas Rizvi;Bernhard Friedrich","doi":"10.26599/JICV.2023.9210047","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210047","url":null,"abstract":"The macroscopic fundamental diagram (MFD) represents the aggregated traffic states of a road network. However, the uniqueness of an empirically estimated MFD cannot be guaranteed due to the problem of link selection. Instationarity and varying flow patterns make it difficult to select link flows that are representative of the traffic state in the whole network. This study developed a new method for selecting links equipped with loop detectors that represent a particular traffic state of a road network. The method utilizes a metric of heterogeneity characterizing the role of a network link over the time of day. The dispersion metric indicates the heterogeneity in traffic states and the dynamic role of each time interval. It ranks links based on the heterogeneity-weighted saturation level, with the highest-rank links representing the most homogeneous subset of sample links. This study compared classical and proposed dynamic weights using loop detector data from Zurich and London and a simulated network. Sample links were selected based on different saturation levels, and the saturation level was associated with the heterogeneity level to identify the links creating heterogeneity in the road network.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"7 4","pages":"266-278"},"PeriodicalIF":0.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10823100","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918520","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 : 2024-12-01DOI: 10.26599/JICV.2023.9210046
Adham Badran;Ahmed El-Geneidy;Luis Miranda-Moreno
The emergence of road users' global positioning system (GPS) trajectory data is attracting increasing research interest in knowledge discovery to improve transport planning-related methods and tools. In fact, the widespread use of GPS-enabled smartphones and the mobile internet has increased the availability and size of such data. With the increase in GPS data coverage and availability, some research has expanded its use to estimate state-wide vehicle-miles travelled, to classify driving maneuvers for road safety assessment, or to estimate environmental performance indicators, such as vehicular fuel consumption and pollution emissions. In computer science, research has used GPS data to infer road network maps. Although the inferred maps provide a correct topology and connectivity, they lack the essential details to be used for transport modeling. Therefore, this work proposes a method to extract network-wide road direction and turning movement rules. In addition, building a road network model under the widely used macroscopic transport modeling software serves as a proof of concept. A sensitivity analysis was carried out to determine the output quality and recommend future improvements. Road segment geometry and directionality were extracted accurately (case study accuracy of 95 % ); however, turning movement rules can be extracted more accurately using a larger GPS vehicle trajectory sample (case study accuracy of 68%).
{"title":"Extracting Networkwide Road Segment Location, Direction, and Turning Movement Rules From Global Positioning System Vehicle Trajectory Data for Macrosimulation","authors":"Adham Badran;Ahmed El-Geneidy;Luis Miranda-Moreno","doi":"10.26599/JICV.2023.9210046","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210046","url":null,"abstract":"The emergence of road users' global positioning system (GPS) trajectory data is attracting increasing research interest in knowledge discovery to improve transport planning-related methods and tools. In fact, the widespread use of GPS-enabled smartphones and the mobile internet has increased the availability and size of such data. With the increase in GPS data coverage and availability, some research has expanded its use to estimate state-wide vehicle-miles travelled, to classify driving maneuvers for road safety assessment, or to estimate environmental performance indicators, such as vehicular fuel consumption and pollution emissions. In computer science, research has used GPS data to infer road network maps. Although the inferred maps provide a correct topology and connectivity, they lack the essential details to be used for transport modeling. Therefore, this work proposes a method to extract network-wide road direction and turning movement rules. In addition, building a road network model under the widely used macroscopic transport modeling software serves as a proof of concept. A sensitivity analysis was carried out to determine the output quality and recommend future improvements. Road segment geometry and directionality were extracted accurately (case study accuracy of 95\u0000<sup>%</sup>\u0000); however, turning movement rules can be extracted more accurately using a larger GPS vehicle trajectory sample (case study accuracy of 68%).","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"7 4","pages":"258-265"},"PeriodicalIF":0.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10823099","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918488","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 : 2024-12-01DOI: 10.26599/JICV.2023.9210050
Katherine Riffle;Edward J. Smaglik;Steven Procaccio;Steven R. Gehrke;Brendan J. Russo;David Hurwitz
This study develops new methods for evaluating detector health via event-based outputs and existing traffic flow theory. In this work, event-based detector data outputs were used to develop empirical vehicle volume-density curves per Greenshields fundamental model. Through integration, these empirical lines were compared with a conceptual volume-density curve for each detector, which was generated with average headway and posted speed limit data. The detector performance and site information were also used to model a predicted volume-density relationship for each detector on the basis of empirical observations, which was then compared with the conceptual line in the same manner as the empirical lines. The outcomes of each comparison were then used to create a database for assessing detector health within the structure of an algorithm. The algorithm is presented and discussed, followed by directions for future research, applications for practice, lessons learned, and limitations of this work.
{"title":"Application of the Traffic Fundamental Diagram to Assess Detector Performance","authors":"Katherine Riffle;Edward J. Smaglik;Steven Procaccio;Steven R. Gehrke;Brendan J. Russo;David Hurwitz","doi":"10.26599/JICV.2023.9210050","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210050","url":null,"abstract":"This study develops new methods for evaluating detector health via event-based outputs and existing traffic flow theory. In this work, event-based detector data outputs were used to develop empirical vehicle volume-density curves per Greenshields fundamental model. Through integration, these empirical lines were compared with a conceptual volume-density curve for each detector, which was generated with average headway and posted speed limit data. The detector performance and site information were also used to model a predicted volume-density relationship for each detector on the basis of empirical observations, which was then compared with the conceptual line in the same manner as the empirical lines. The outcomes of each comparison were then used to create a database for assessing detector health within the structure of an algorithm. The algorithm is presented and discussed, followed by directions for future research, applications for practice, lessons learned, and limitations of this work.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"7 4","pages":"279-291"},"PeriodicalIF":0.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10823097","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918519","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 : 2024-09-26DOI: 10.26599/JICV.2023.9210038
Zhe Zheng;Jian Yuan;Kun An;Nan Zheng;Wanjing Ma
Through and right-turn shared lanes are widely designed to increase the capacity of through traffic, but they can also cause delays for right-turn vehicles. This study presents a dynamic control method for a shared lane that prioritizes right-turn vehicles at the beginning of the cycle and subsequently allows through traffic to queue in the shared lane for saturated discharge. The traffic wave model is employed to reveal the dynamics of the traffic flow under this control and to derive the relationships among major traffic parameters. Constrained by the major relationship, a linear programming approach to minimize the total queue length is developed to determine the proper values of control parameters, including the shared area length, subordinate signal time lag, and shared or exclusive duration. A sensitivity analysis of the control parameters for different arrival rates and flow ratios is performed. Comparisons are conducted among the dynamic shared lane, the fixed exclusive lane, and the fixed shared lane. The results show that the dynamic control method results in a lower delay for both through and total traffic.
{"title":"Coordinated Optimization of Signal Timing for Intersections with Dynamic Shared Through- and Right-Turn Lanes","authors":"Zhe Zheng;Jian Yuan;Kun An;Nan Zheng;Wanjing Ma","doi":"10.26599/JICV.2023.9210038","DOIUrl":"https://doi.org/10.26599/JICV.2023.9210038","url":null,"abstract":"Through and right-turn shared lanes are widely designed to increase the capacity of through traffic, but they can also cause delays for right-turn vehicles. This study presents a dynamic control method for a shared lane that prioritizes right-turn vehicles at the beginning of the cycle and subsequently allows through traffic to queue in the shared lane for saturated discharge. The traffic wave model is employed to reveal the dynamics of the traffic flow under this control and to derive the relationships among major traffic parameters. Constrained by the major relationship, a linear programming approach to minimize the total queue length is developed to determine the proper values of control parameters, including the shared area length, subordinate signal time lag, and shared or exclusive duration. A sensitivity analysis of the control parameters for different arrival rates and flow ratios is performed. Comparisons are conducted among the dynamic shared lane, the fixed exclusive lane, and the fixed shared lane. The results show that the dynamic control method results in a lower delay for both through and total traffic.","PeriodicalId":100793,"journal":{"name":"Journal of Intelligent and Connected Vehicles","volume":"7 3","pages":"219-228"},"PeriodicalIF":0.0,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10695162","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142324273","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：