Pub Date : 2026-01-01DOI: 10.1109/TITS.2025.3644205
{"title":"IEEE Intelligent Transportation Systems Society Information","authors":"","doi":"10.1109/TITS.2025.3644205","DOIUrl":"https://doi.org/10.1109/TITS.2025.3644205","url":null,"abstract":"","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 1","pages":"C3-C3"},"PeriodicalIF":8.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11322433","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145877119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-04DOI: 10.1109/TITS.2025.3625574
Liangliang Lou;Yike Wang;Haoxu Wang;Miao Zhou;Hanbing Zhao;Chun Li;Wei He
The management level of Smart Parking Systems (SPS) relies heavily on accurate parking occupancy information, making low-cost, high-precision wireless parking sensors (WPS), powered by batteries, widely used in urban parking lots. However, the performance of magnetometer-based WPS is often disrupted by electromagnetic interference (EMI) from underground high-voltage cables and subways, limiting their reliability in urban environments. This paper proposes an Anti-electromagnetic Interference Parking Detection (AeIPD) method to address this issue. AeIPD combines traditional Received Signal Strength (RSS) features with antenna impedance measurements, utilizing two Bluetooth Low Energy (BLE) transceivers to enhance detection robustness under EMI conditions. Compared to existing methods, AeIPD significantly improves resilience to EMI, providing a more reliable and robust solution for parking detection even in environments with severe interference. This approach offers a cost-effective, scalable solution for large-scale deployment in modern SPS, overcoming the limitations of traditional magnetometer-based systems. Experimental results demonstrate that AeIPD outperforms current parking detection methods, offering a more reliable and robust alternative for smart parking applications.
{"title":"Wireless Channel as a Sensor: An Anti-Electromagnetic Interference Vehicle Detection Method Based on Wireless Sensing Technology","authors":"Liangliang Lou;Yike Wang;Haoxu Wang;Miao Zhou;Hanbing Zhao;Chun Li;Wei He","doi":"10.1109/TITS.2025.3625574","DOIUrl":"https://doi.org/10.1109/TITS.2025.3625574","url":null,"abstract":"The management level of Smart Parking Systems (SPS) relies heavily on accurate parking occupancy information, making low-cost, high-precision wireless parking sensors (WPS), powered by batteries, widely used in urban parking lots. However, the performance of magnetometer-based WPS is often disrupted by electromagnetic interference (EMI) from underground high-voltage cables and subways, limiting their reliability in urban environments. This paper proposes an Anti-electromagnetic Interference Parking Detection (AeIPD) method to address this issue. AeIPD combines traditional Received Signal Strength (RSS) features with antenna impedance measurements, utilizing two Bluetooth Low Energy (BLE) transceivers to enhance detection robustness under EMI conditions. Compared to existing methods, AeIPD significantly improves resilience to EMI, providing a more reliable and robust solution for parking detection even in environments with severe interference. This approach offers a cost-effective, scalable solution for large-scale deployment in modern SPS, overcoming the limitations of traditional magnetometer-based systems. Experimental results demonstrate that AeIPD outperforms current parking detection methods, offering a more reliable and robust alternative for smart parking applications.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 1","pages":"1639-1649"},"PeriodicalIF":8.4,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145877111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2025-12-04DOI: 10.1109/TITS.2025.3633150
Ting Gao;Winnie Daamen;Elvin Isufi;Serge P. Hoogendoorn
In urban centers, cycling is increasingly popular as an eco-friendly transportation mode and a short-distance transport option, driving higher demand for accurate bicycle travel time estimation. Policymakers need to understand bicycle traffic for urban traffic management and sustainable transport promotion, while cyclists benefit from better route planning and improved network efficiency. However, urban bicycle travel time estimation has not received as much attention as car traffic estimation and presents several challenges: 1) Limited availability of structural cycling data, which can be inaccessible due to privacy concerns and/or severely biased by user demographics. 2) The diverse and complex behaviors of cyclists. 3) The lack of strict road constraints for cyclists and frequent rule violations, complicating the model definition of a comprehensive cycling infrastructure network. This paper presents the first study on urban bicycle travel time estimation using GPS tracking data. Leveraging graph-based deep learning’s ability to learn from topological network information, we introduce the Dual Graph-based approach for bicycles (DG4b), which employs two parallel encode-process-decode pipelines: one for a shared undirected road network graph to capture intrinsic road characteristics, and another for a directed trip-specific graph reflecting unique trip features. The outputs are combined to estimate road segment speeds and overall trip travel time. When applied to a real-world dataset from Berlin, our method shows superior accuracy and reliability compared to baseline models, while maintaining low complexity. Our approach provides a novel perspective on integrating bicycling-specific characteristics and aims to inspire more future research in bicycle-related traffic estimation.
{"title":"Bicycle Travel Time Estimation via Dual Graph-Based Neural Networks","authors":"Ting Gao;Winnie Daamen;Elvin Isufi;Serge P. Hoogendoorn","doi":"10.1109/TITS.2025.3633150","DOIUrl":"https://doi.org/10.1109/TITS.2025.3633150","url":null,"abstract":"In urban centers, cycling is increasingly popular as an eco-friendly transportation mode and a short-distance transport option, driving higher demand for accurate bicycle travel time estimation. Policymakers need to understand bicycle traffic for urban traffic management and sustainable transport promotion, while cyclists benefit from better route planning and improved network efficiency. However, urban bicycle travel time estimation has not received as much attention as car traffic estimation and presents several challenges: 1) Limited availability of structural cycling data, which can be inaccessible due to privacy concerns and/or severely biased by user demographics. 2) The diverse and complex behaviors of cyclists. 3) The lack of strict road constraints for cyclists and frequent rule violations, complicating the model definition of a comprehensive cycling infrastructure network. This paper presents the first study on urban bicycle travel time estimation using GPS tracking data. Leveraging graph-based deep learning’s ability to learn from topological network information, we introduce the Dual Graph-based approach for bicycles (DG4b), which employs two parallel encode-process-decode pipelines: one for a shared undirected road network graph to capture intrinsic road characteristics, and another for a directed trip-specific graph reflecting unique trip features. The outputs are combined to estimate road segment speeds and overall trip travel time. When applied to a real-world dataset from Berlin, our method shows superior accuracy and reliability compared to baseline models, while maintaining low complexity. Our approach provides a novel perspective on integrating bicycling-specific characteristics and aims to inspire more future research in bicycle-related traffic estimation.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 1","pages":"1511-1524"},"PeriodicalIF":8.4,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145877114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2025-12-04DOI: 10.1109/TITS.2025.3632039
{"title":"IEEE Intelligent Transportation Systems Society Information","authors":"","doi":"10.1109/TITS.2025.3632039","DOIUrl":"https://doi.org/10.1109/TITS.2025.3632039","url":null,"abstract":"","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 12","pages":"C3-C3"},"PeriodicalIF":8.4,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11278555","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145665794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-04DOI: 10.1109/TITS.2025.3629411
Xuecheng Wang;Linhui Li;Jing Lian;Zhenfeng Wang;Juan Li;Jian Zhao;Qiong Wu;Jun Hu
In highly dynamic and complex autonomous driving environments, accurately predicting agents’ future multimodal trajectories still faces challenges such as modeling diverse social interactions, capturing dynamic intents, and ensuring prediction consistency. To address these issues, this paper proposes a novel trajectory prediction model that integrates a Hierarchical Recursive Interaction Network (HRINet) and a multi-stage goal-guided mechanism (GoalNet), aiming to improve prediction accuracy, stability, and plausibility. Specifically, we design a HRINet with local and global attention mechanisms to recursively model various social interactions, while progressively integrating map semantic information to enhance the model’s understanding of traffic scenes. Meanwhile, inspired by the divide-and-conquer approach, the proposed GoalNet first estimates fine-grained multi-stage goal lane segments along the path. These goals are then used to continuously guide and constrain the trajectory generation process, effectively reducing error accumulation and improving stability. In addition, we construct a dynamic goal candidate area that combines domain knowledge and traffic rules to filter out unreasonable goals, thereby enhancing the plausibility and consistency of the predictions. Experimental results on nuScenes, INTERACTION, and Waymo Open Motion Dataset (WOMD) show that our model achieves state-of-the-art performance in multiple key metrics, maintains a trade-off between prediction accuracy, model complexity, and inference latency, and shows high stability and consistency in predictions.
{"title":"Hierarchical Recursive Interaction and Multi-Stage Goal-Guided Mechanism for Multimodal Trajectory Prediction","authors":"Xuecheng Wang;Linhui Li;Jing Lian;Zhenfeng Wang;Juan Li;Jian Zhao;Qiong Wu;Jun Hu","doi":"10.1109/TITS.2025.3629411","DOIUrl":"https://doi.org/10.1109/TITS.2025.3629411","url":null,"abstract":"In highly dynamic and complex autonomous driving environments, accurately predicting agents’ future multimodal trajectories still faces challenges such as modeling diverse social interactions, capturing dynamic intents, and ensuring prediction consistency. To address these issues, this paper proposes a novel trajectory prediction model that integrates a Hierarchical Recursive Interaction Network (HRINet) and a multi-stage goal-guided mechanism (GoalNet), aiming to improve prediction accuracy, stability, and plausibility. Specifically, we design a HRINet with local and global attention mechanisms to recursively model various social interactions, while progressively integrating map semantic information to enhance the model’s understanding of traffic scenes. Meanwhile, inspired by the divide-and-conquer approach, the proposed GoalNet first estimates fine-grained multi-stage goal lane segments along the path. These goals are then used to continuously guide and constrain the trajectory generation process, effectively reducing error accumulation and improving stability. In addition, we construct a dynamic goal candidate area that combines domain knowledge and traffic rules to filter out unreasonable goals, thereby enhancing the plausibility and consistency of the predictions. Experimental results on nuScenes, INTERACTION, and Waymo Open Motion Dataset (WOMD) show that our model achieves state-of-the-art performance in multiple key metrics, maintains a trade-off between prediction accuracy, model complexity, and inference latency, and shows high stability and consistency in predictions.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 1","pages":"1621-1638"},"PeriodicalIF":8.4,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145877118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2025-12-03DOI: 10.1109/TITS.2025.3634731
Xiang Peng;Yong Zhang;Xiangwang Hu;Weike Lu
This paper proposes a modeling framework for optimizing the mobile battery-swapping system (MBSS) that integrates frontend battery-swapping service with backend charging operation. The service district is partitioned into multiple jurisdictions, each with a charging station and multiple battery-swapping vans (BSVs) and batteries. BSVs carry multiple charged batteries and provide on-demand swapping service for electric vehicles. Once a BSV exhausts charged batteries, it returns to backend charging stations to reload charged batteries for subsequent services. Our modeling framework optimizes the fleet size/capacity/allocation of BSVs and the allocation of batteries and charging racks at stations. To this end, we develop a frontend BSV service model and a backend charging model to present the MBSS performance metrics, and introduce three customized algorithms to solve the MBSS configuration and its performance metrics. The framework is validated by a case study of Xiongan China, showing a promising application of the MBSS in practice.
{"title":"Integrated Design of Mobile Battery-Swapping and Charging Services for Electric Vehicles","authors":"Xiang Peng;Yong Zhang;Xiangwang Hu;Weike Lu","doi":"10.1109/TITS.2025.3634731","DOIUrl":"https://doi.org/10.1109/TITS.2025.3634731","url":null,"abstract":"This paper proposes a modeling framework for optimizing the mobile battery-swapping system (MBSS) that integrates frontend battery-swapping service with backend charging operation. The service district is partitioned into multiple jurisdictions, each with a charging station and multiple battery-swapping vans (BSVs) and batteries. BSVs carry multiple charged batteries and provide on-demand swapping service for electric vehicles. Once a BSV exhausts charged batteries, it returns to backend charging stations to reload charged batteries for subsequent services. Our modeling framework optimizes the fleet size/capacity/allocation of BSVs and the allocation of batteries and charging racks at stations. To this end, we develop a frontend BSV service model and a backend charging model to present the MBSS performance metrics, and introduce three customized algorithms to solve the MBSS configuration and its performance metrics. The framework is validated by a case study of Xiongan China, showing a promising application of the MBSS in practice.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 1","pages":"1525-1537"},"PeriodicalIF":8.4,"publicationDate":"2025-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145877109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2025-12-03DOI: 10.1109/TITS.2025.3627592
Jingyuan Zhou;Longhao Yan;Jinhao Liang;Kaidi Yang
It is recognized that the control of mixed-autonomy platoons comprising connected and automated vehicles (CAVs) and human-driven vehicles (HDVs) can enhance traffic flow. Among existing methods, Multi-Agent Reinforcement Learning (MARL) appears to be a promising control strategy because it can manage complex scenarios in real time. However, current research on MARL-based mixed-autonomy platoon control suffers from several limitations. First, existing MARL approaches address safety by penalizing safety violations in the reward function, thus lacking theoretical safety guarantees due to the limited interpretability of RL. Second, few studies have explored the cooperative safety of multi-CAV platoons, where CAVs can be coordinated to further enhance the system-level safety involving the safety of both CAVs and HDVs. Third, existing work tends to make an unrealistic assumption that the behavior of HDVs and CAVs is publicly known and rational. To bridge the research gaps, we propose a safe MARL framework for mixed-autonomy platoons. Specifically, this framework 1) characterizes cooperative safety by designing a cooperative Control Barrier Function (CBF), enabling CAVs to collaboratively improve the safety of the entire platoon, 2) provides a safety guarantee to the MARL-based controller by integrating the CBF-based safety constraints into MARL through a differentiable quadratic programming (QP) layer, and 3) incorporates a conformal prediction module that enables each CAV to estimate the unknown behaviors of the surrounding vehicles with uncertainty qualification. Simulation results show that our proposed control strategy can effectively enhance the system-level safety through CAV cooperation of a mixed-autonomy platoon with a minimal impact on control performance.
{"title":"Enforcing Cooperative Safety for Reinforcement Learning-Based Mixed-Autonomy Platoon Control","authors":"Jingyuan Zhou;Longhao Yan;Jinhao Liang;Kaidi Yang","doi":"10.1109/TITS.2025.3627592","DOIUrl":"https://doi.org/10.1109/TITS.2025.3627592","url":null,"abstract":"It is recognized that the control of mixed-autonomy platoons comprising connected and automated vehicles (CAVs) and human-driven vehicles (HDVs) can enhance traffic flow. Among existing methods, Multi-Agent Reinforcement Learning (MARL) appears to be a promising control strategy because it can manage complex scenarios in real time. However, current research on MARL-based mixed-autonomy platoon control suffers from several limitations. First, existing MARL approaches address safety by penalizing safety violations in the reward function, thus lacking theoretical safety guarantees due to the limited interpretability of RL. Second, few studies have explored the cooperative safety of multi-CAV platoons, where CAVs can be coordinated to further enhance the system-level safety involving the safety of both CAVs and HDVs. Third, existing work tends to make an unrealistic assumption that the behavior of HDVs and CAVs is publicly known and rational. To bridge the research gaps, we propose a safe MARL framework for mixed-autonomy platoons. Specifically, this framework 1) characterizes cooperative safety by designing a cooperative Control Barrier Function (CBF), enabling CAVs to collaboratively improve the safety of the entire platoon, 2) provides a safety guarantee to the MARL-based controller by integrating the CBF-based safety constraints into MARL through a differentiable quadratic programming (QP) layer, and 3) incorporates a conformal prediction module that enables each CAV to estimate the unknown behaviors of the surrounding vehicles with uncertainty qualification. Simulation results show that our proposed control strategy can effectively enhance the system-level safety through CAV cooperation of a mixed-autonomy platoon with a minimal impact on control performance.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 1","pages":"1592-1605"},"PeriodicalIF":8.4,"publicationDate":"2025-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145877116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2025-11-26DOI: 10.1109/TITS.2025.3633448
Jie Tang;Yefei Hou;Jialu Liu;Bo Yu
Autonomous driving technology is becoming a significant trend in the development of public transportation. A critical task in autonomous driving perception is 3D object detection, which provides essential data support for downstream applications. Most mainstream 3D object detection methods rely on the Cartesian coordinate system, where they construct object queries to interact with image features and position embedding. However, these methods have the following problems: 1) Sensor-captured detail information diminishes with increasing distance, while pixels represent the same space in Cartesian coordinates, preventing the model from fully leveraging details in closer regions. 2) Multi-view images suffer from spatial misalignment due to overlapping fields of view. 3) The performance of existing single-branch depth prediction networks lacks the necessary accuracy. These issues hinder the feature interaction and affect detection performance. We propose an innovative framework PRTF. Based on Polar space, we design the Two-Stage Transformation Encoder: in the first stage, Dual-DepthNet is used to improve the accuracy of depth prediction. In the second stage, Polar points are generated to address spatial misalignment, enabling effective encoding of details at close distance. In the Temporal Decoder, object queries are leveraged to integrate temporal information, effectively compensating for ambiguous information. By enhancing spatial information at both near and far distances in Polar space, the overall performance of multi-view 3D object detection is significantly improved. PRTF achieves state-of-the-art performance on nuScenes Test with 56.1% mAP and 63.9% NDS, exceeding multi-modal frameworks that combine image and radar data.
{"title":"PRTF: Polar Space Represented Multi-View 3D Object Detection With Temporal Fusion Enhancement","authors":"Jie Tang;Yefei Hou;Jialu Liu;Bo Yu","doi":"10.1109/TITS.2025.3633448","DOIUrl":"https://doi.org/10.1109/TITS.2025.3633448","url":null,"abstract":"Autonomous driving technology is becoming a significant trend in the development of public transportation. A critical task in autonomous driving perception is 3D object detection, which provides essential data support for downstream applications. Most mainstream 3D object detection methods rely on the Cartesian coordinate system, where they construct object queries to interact with image features and position embedding. However, these methods have the following problems: 1) Sensor-captured detail information diminishes with increasing distance, while pixels represent the same space in Cartesian coordinates, preventing the model from fully leveraging details in closer regions. 2) Multi-view images suffer from spatial misalignment due to overlapping fields of view. 3) The performance of existing single-branch depth prediction networks lacks the necessary accuracy. These issues hinder the feature interaction and affect detection performance. We propose an innovative framework PRTF. Based on Polar space, we design the Two-Stage Transformation Encoder: in the first stage, Dual-DepthNet is used to improve the accuracy of depth prediction. In the second stage, Polar points are generated to address spatial misalignment, enabling effective encoding of details at close distance. In the Temporal Decoder, object queries are leveraged to integrate temporal information, effectively compensating for ambiguous information. By enhancing spatial information at both near and far distances in Polar space, the overall performance of multi-view 3D object detection is significantly improved. PRTF achieves state-of-the-art performance on nuScenes Test with 56.1% mAP and 63.9% NDS, exceeding multi-modal frameworks that combine image and radar data.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 1","pages":"1538-1549"},"PeriodicalIF":8.4,"publicationDate":"2025-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145877106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The min-max multiple traveling salesman problem (min-max mTSP) is a significant variant of the min-max routing problem, focusing on minimizing the longest subtour cost among multiple salesmen working cooperatively. This problem is highly relevant in real-world scenarios but is notoriously challenging, especially as the scale increases with numerous salesmen covering thousands of cities. This paper presents a novel approach for solving large-scale min-max mTSP. Our method, based on deep reinforcement learning, introduces a novel two-stage process. In the first stage, we generate an initial solution using a constructive model incorporating global and local attention mechanisms through a gated network. Additionally, we employ multi-task training on a single constructive model across various mTSP problems with differing numbers of salesmen, using weighted task balancing to balance the multi-task learning process. In the second stage, the initial solution is iteratively refined using improvement policy, which re-optimizes the current subtours to form a new better one. To the best of our knowledge, our method is the first capable of handling problems with up to 10,000 nodes. The experimental results demonstrate that our approach achieves the best solution on 71% of the problems in randomly uniform datasets, outperforming all existing methods. Our code is available at https://github.com/1hhix/CMIP
{"title":"CMIP: Combining Constructive Model With Improvement Policy for Large-Scale Min-Max Multiple Traveling Salesman Problem","authors":"Binbin Zuo;Weifan Li;Jiankuo Zhao;Tianxiang Bai;Linqian Yang;Zhe Ma;Yuanheng Zhu","doi":"10.1109/TITS.2025.3632076","DOIUrl":"https://doi.org/10.1109/TITS.2025.3632076","url":null,"abstract":"The min-max multiple traveling salesman problem (min-max mTSP) is a significant variant of the min-max routing problem, focusing on minimizing the longest subtour cost among multiple salesmen working cooperatively. This problem is highly relevant in real-world scenarios but is notoriously challenging, especially as the scale increases with numerous salesmen covering thousands of cities. This paper presents a novel approach for solving large-scale min-max mTSP. Our method, based on deep reinforcement learning, introduces a novel two-stage process. In the first stage, we generate an initial solution using a constructive model incorporating global and local attention mechanisms through a gated network. Additionally, we employ multi-task training on a single constructive model across various mTSP problems with differing numbers of salesmen, using weighted task balancing to balance the multi-task learning process. In the second stage, the initial solution is iteratively refined using improvement policy, which re-optimizes the current subtours to form a new better one. To the best of our knowledge, our method is the first capable of handling problems with up to 10,000 nodes. The experimental results demonstrate that our approach achieves the best solution on 71% of the problems in randomly uniform datasets, outperforming all existing methods. Our code is available at <uri>https://github.com/1hhix/CMIP</uri>","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 1","pages":"1550-1564"},"PeriodicalIF":8.4,"publicationDate":"2025-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145877120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 : 2025-11-18DOI: 10.1109/TITS.2025.3631922
Akshay Gupta;Pushpa Choudhary;Manoranjan Parida
Nighttime driving presents unique challenges and risks compared to daytime driving. This study analyzed rear-end conflicts on expressways and identified thresholds for various conflict indicators under both day and night conditions. Utilizing cost-effective 3D LiDAR technology, renowned for its robustness in low-light environments, this study elucidates the multifaceted influence of various factors on traffic safety dynamics across day and night conditions. Extreme value theory was applied to evaluate safety, incorporating factors like traffic environment and driver characteristics that are often overlooked in naturalistic studies. The analysis also included the effect of percentage oblique width on safety-critical events. Interestingly, drivers experienced about three times higher crash risks during the day compared to night, likely due to increased vigilance and caution at night. These findings offer valuable recommendations for setting headway requirements based on lighting conditions and can help improve advanced driver assistance systems to detect and respond more effectively to unsafe following distances.
{"title":"Advanced Sensor Analytics and Extreme Value Modeling: Dichotomizing Day–Night Variability in Rear-End Collisions on Expressways","authors":"Akshay Gupta;Pushpa Choudhary;Manoranjan Parida","doi":"10.1109/TITS.2025.3631922","DOIUrl":"https://doi.org/10.1109/TITS.2025.3631922","url":null,"abstract":"Nighttime driving presents unique challenges and risks compared to daytime driving. This study analyzed rear-end conflicts on expressways and identified thresholds for various conflict indicators under both day and night conditions. Utilizing cost-effective 3D LiDAR technology, renowned for its robustness in low-light environments, this study elucidates the multifaceted influence of various factors on traffic safety dynamics across day and night conditions. Extreme value theory was applied to evaluate safety, incorporating factors like traffic environment and driver characteristics that are often overlooked in naturalistic studies. The analysis also included the effect of percentage oblique width on safety-critical events. Interestingly, drivers experienced about three times higher crash risks during the day compared to night, likely due to increased vigilance and caution at night. These findings offer valuable recommendations for setting headway requirements based on lighting conditions and can help improve advanced driver assistance systems to detect and respond more effectively to unsafe following distances.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 1","pages":"1499-1510"},"PeriodicalIF":8.4,"publicationDate":"2025-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145877113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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：