Pub Date : 2025-02-04DOI: 10.1109/TITS.2025.3533603
Meng Long;Edward Chung
Headway regularity is an essential indicator of transit reliability, directly influencing passenger waiting time and transit service quality. In this paper, we employ multi-agent reinforcement learning (MARL) to develop a Cooperative Transit signal priority strategy with Variable phase for Headway adherence (CTVH) under a multi-intersection network. Each signalized intersection is controlled by an RL agent, which determines the next step’s signal, adapting to real-time traffic dynamics of transits and non-transits and promoting transit headway adherence. The proposed approach considers four critical aspects, i.e., complicated states with multiple conflicting bus requests, rational actions constrained by domain knowledge, comprehensive rewards balancing buses and cars, and a collaborative training scheme among agents. They are correspondingly addressed by proper state representation with estimated bus headway deviations, irrational actions masking, reward functions formulated by general traffic queue and transit headway deviation, and appropriate MARL approach with synchronous action processing. Our method also takes into account the phase transition loss by setting yellow and all-red time. Simulation results compared with the coordinated fixed-time signal (CFT) and bus holding (BH) strategy verify the merits of the proposed method in terms of improvements in transit headway adherence and influence on general traffic. Based on the results, we further discuss the BH method’s limitations due to bus bay length and various holding lines and the CTVH method’s benefits in the three-intersection environment and the entire-line network. The proposed method has a promising application in practice to improve transit reliability.
{"title":"Multi-Agent Reinforcement Learning for Cooperative Transit Signal Priority to Promote Headway Adherence","authors":"Meng Long;Edward Chung","doi":"10.1109/TITS.2025.3533603","DOIUrl":"https://doi.org/10.1109/TITS.2025.3533603","url":null,"abstract":"Headway regularity is an essential indicator of transit reliability, directly influencing passenger waiting time and transit service quality. In this paper, we employ multi-agent reinforcement learning (MARL) to develop a Cooperative Transit signal priority strategy with Variable phase for Headway adherence (CTVH) under a multi-intersection network. Each signalized intersection is controlled by an RL agent, which determines the next step’s signal, adapting to real-time traffic dynamics of transits and non-transits and promoting transit headway adherence. The proposed approach considers four critical aspects, i.e., complicated states with multiple conflicting bus requests, rational actions constrained by domain knowledge, comprehensive rewards balancing buses and cars, and a collaborative training scheme among agents. They are correspondingly addressed by proper state representation with estimated bus headway deviations, irrational actions masking, reward functions formulated by general traffic queue and transit headway deviation, and appropriate MARL approach with synchronous action processing. Our method also takes into account the phase transition loss by setting yellow and all-red time. Simulation results compared with the coordinated fixed-time signal (CFT) and bus holding (BH) strategy verify the merits of the proposed method in terms of improvements in transit headway adherence and influence on general traffic. Based on the results, we further discuss the BH method’s limitations due to bus bay length and various holding lines and the CTVH method’s benefits in the three-intersection environment and the entire-line network. The proposed method has a promising application in practice to improve transit reliability.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3588-3602"},"PeriodicalIF":7.9,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143564215","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 : 2025-01-30DOI: 10.1109/TITS.2025.3532455
Xiaojie Lin;Baihe Ma;Xu Wang;Guangsheng Yu;Ying He;Wei Ni;Ren Ping Liu
Driving trajectory data remains vulnerable to privacy breaches despite existing mitigation measures. Traditional methods for detecting driving trajectories typically rely on map-matching the path using Global Positioning System (GPS) data, which is susceptible to GPS data outage. This paper introduces CAN-Trace, a novel privacy attack mechanism that leverages Controller Area Network (CAN) messages to uncover driving trajectories, posing a significant risk to drivers’ long-term privacy. A new trajectory reconstruction algorithm is proposed to transform the CAN messages, specifically vehicle speed and accelerator pedal position, into weighted graphs accommodating various driving statuses. CAN-Trace identifies driving trajectories using graph-matching algorithms applied to the created graphs in comparison to road networks. We also design a new metric to evaluate matched candidates, which allows for potential data gaps and matching inaccuracies. Empirical validation under various real-world conditions, encompassing different vehicles and driving regions, demonstrates the efficacy of CAN-Trace: it achieves an attack success rate of up to 90.59% in the urban region, and 99.41% in the suburban region.
{"title":"CAN-Trace Attack: Exploit CAN Messages to Uncover Driving Trajectories","authors":"Xiaojie Lin;Baihe Ma;Xu Wang;Guangsheng Yu;Ying He;Wei Ni;Ren Ping Liu","doi":"10.1109/TITS.2025.3532455","DOIUrl":"https://doi.org/10.1109/TITS.2025.3532455","url":null,"abstract":"Driving trajectory data remains vulnerable to privacy breaches despite existing mitigation measures. Traditional methods for detecting driving trajectories typically rely on map-matching the path using Global Positioning System (GPS) data, which is susceptible to GPS data outage. This paper introduces CAN-Trace, a novel privacy attack mechanism that leverages Controller Area Network (CAN) messages to uncover driving trajectories, posing a significant risk to drivers’ long-term privacy. A new trajectory reconstruction algorithm is proposed to transform the CAN messages, specifically vehicle speed and accelerator pedal position, into weighted graphs accommodating various driving statuses. CAN-Trace identifies driving trajectories using graph-matching algorithms applied to the created graphs in comparison to road networks. We also design a new metric to evaluate matched candidates, which allows for potential data gaps and matching inaccuracies. Empirical validation under various real-world conditions, encompassing different vehicles and driving regions, demonstrates the efficacy of CAN-Trace: it achieves an attack success rate of up to 90.59% in the urban region, and 99.41% in the suburban region.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3223-3236"},"PeriodicalIF":7.9,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535551","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 : 2025-01-30DOI: 10.1109/TITS.2025.3532519
Shunyu Liu;Yunpeng Qing;Shuqi Xu;Hongyan Wu;Jiangtao Zhang;Jingyuan Cong;Tianhao Chen;Yun-Fu Liu;Mingli Song
Inverse Reinforcement Learning (IRL) aims to reconstruct the reward function from expert demonstrations to facilitate policy learning, and has demonstrated its remarkable success in imitation learning. To promote expert-like behavior, existing IRL methods mainly focus on learning global reward functions to minimize the trajectory difference between the imitator and the expert. However, these global designs are still limited by the redundant noise and error propagation problems, leading to the unsuitable reward assignment and thus downgrading the agent capability in complex multi-stage tasks. In this paper, we propose a novel Curricular Subgoal-based Inverse Reinforcement Learning (CSIRL) framework, that explicitly disentangles one task with several local subgoals to guide agent imitation. Specifically, CSIRL firstly introduces decision uncertainty of the trained agent over expert trajectories to dynamically select specific states as subgoals, which directly determines the exploration boundary of different task stages. To further acquire local reward functions for each stage, we customize a meta-imitation objective based on these curricular subgoals to train an intrinsic reward generator. Experiments on the D4RL and autonomous driving benchmarks demonstrate that the proposed methods yields results superior to the state-of-the-art counterparts, as well as better interpretability. Our code is publicly available at https://github.com/Plankson/CSIRL.
{"title":"Curricular Subgoals for Inverse Reinforcement Learning","authors":"Shunyu Liu;Yunpeng Qing;Shuqi Xu;Hongyan Wu;Jiangtao Zhang;Jingyuan Cong;Tianhao Chen;Yun-Fu Liu;Mingli Song","doi":"10.1109/TITS.2025.3532519","DOIUrl":"https://doi.org/10.1109/TITS.2025.3532519","url":null,"abstract":"Inverse Reinforcement Learning (IRL) aims to reconstruct the reward function from expert demonstrations to facilitate policy learning, and has demonstrated its remarkable success in imitation learning. To promote expert-like behavior, existing IRL methods mainly focus on learning global reward functions to minimize the trajectory difference between the imitator and the expert. However, these global designs are still limited by the redundant noise and error propagation problems, leading to the unsuitable reward assignment and thus downgrading the agent capability in complex multi-stage tasks. In this paper, we propose a novel Curricular Subgoal-based Inverse Reinforcement Learning (CSIRL) framework, that explicitly disentangles one task with several local subgoals to guide agent imitation. Specifically, CSIRL firstly introduces decision uncertainty of the trained agent over expert trajectories to dynamically select specific states as subgoals, which directly determines the exploration boundary of different task stages. To further acquire local reward functions for each stage, we customize a meta-imitation objective based on these curricular subgoals to train an intrinsic reward generator. Experiments on the D4RL and autonomous driving benchmarks demonstrate that the proposed methods yields results superior to the state-of-the-art counterparts, as well as better interpretability. Our code is publicly available at <uri>https://github.com/Plankson/CSIRL</uri>.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3016-3027"},"PeriodicalIF":7.9,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535448","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 : 2025-01-30DOI: 10.1109/TITS.2025.3532436
Hongcheng Yang;Dingkang Liang;Zhe Liu;Jingyu Li;Zhikang Zou;Xiaoqing Ye;Xiang Bai
The ratio of foreground and background points directly impacts the accuracy and speed of the lidar-based 3D object detection methods. However, existing methods generally ignore the impact of ground points. Although some traditional ground segmentation algorithms are available to remove ground point clouds, they usually suffer from over-segmentation, which leads to a sub-optimal and even worse performance for the downstream 3D detection task. We conduct an in-depth analysis and attribute this phenomenon to the reason that some crucial foreground points attached to the ground (e.g., the wheels of Cars, or the feet of Pedestrians) are directly removed due to over-segmentation. To this end, we propose a new Attached Point Restoring (APR) module to recover these discarded foreground points. Experimental results demonstrate the effectiveness and generalization of APR by integrating it into various ground segmentation algorithms to boost the performance or the running time of 3D detection on KITTI and Waymo datasets. Finally, we hope this paper can serve as a new guide to inspire future research in this field. Code is available at https://github.com/yhc2021/GPR.
{"title":"An Empirical Study of Ground Segmentation for 3-D Object Detection","authors":"Hongcheng Yang;Dingkang Liang;Zhe Liu;Jingyu Li;Zhikang Zou;Xiaoqing Ye;Xiang Bai","doi":"10.1109/TITS.2025.3532436","DOIUrl":"https://doi.org/10.1109/TITS.2025.3532436","url":null,"abstract":"The ratio of foreground and background points directly impacts the accuracy and speed of the lidar-based 3D object detection methods. However, existing methods generally ignore the impact of ground points. Although some traditional ground segmentation algorithms are available to remove ground point clouds, they usually suffer from over-segmentation, which leads to a sub-optimal and even worse performance for the downstream 3D detection task. We conduct an in-depth analysis and attribute this phenomenon to the reason that some crucial foreground points attached to the ground (e.g., the wheels of Cars, or the feet of Pedestrians) are directly removed due to over-segmentation. To this end, we propose a new Attached Point Restoring (APR) module to recover these discarded foreground points. Experimental results demonstrate the effectiveness and generalization of APR by integrating it into various ground segmentation algorithms to boost the performance or the running time of 3D detection on KITTI and Waymo datasets. Finally, we hope this paper can serve as a new guide to inspire future research in this field. Code is available at <uri>https://github.com/yhc2021/GPR</uri>.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3071-3083"},"PeriodicalIF":7.9,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535576","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 : 2025-01-29DOI: 10.1109/TITS.2025.3528406
Bing Han;Yingxia Chi;Yuan Xu;Yongshin Park
Although multimodal transport has been widely developed, the multimodal transport operation system is still not as mature as other single modes of transport. Currently, the optimization of multimodal transport solutions and the allocation of capacity are planned as two separate parts, and the research on customer classification of multimodal transport is insufficient. The current bottleneck in multimodal transportation systems is optimizing multimodal customer classification and transportation solutions. Additionally, such an optimization can significantly improve the system’s overall revenue. Based on the customer classification theory of revenue management, we classified and managed multimodal transport customers and allocated and priced the transportation capacity according to the demand characteristics and price sensitivities of different customers. Furthermore, we considered the impact of transportation scheme planning on the profit of multimodal transport. Accordingly, we developed a joint optimization model for multimodal transport schemes, capacity allocation, and pricing by considering the customer classification. We solved the model using a hybrid particle swarm algorithm and validated it using arithmetic examples. The results indicate that a customer classification strategy can significantly improve the profit of multimodal transport operators when customer demand is unstable, and the total profit of the transportation system is increased by 7%. Moreover, these results suggest combining transportation solution optimization with customer classification can lead to more profitable multimodal revenue management solutions. Thus, our results can guide multimodal operators for systematically dealing with the customer classification problem and optimizing transportation schemes while improving their profits. Moreover, this study offers a reference for decision-making in multimodal operation management.
{"title":"Multimodal Transport Scheme Optimization and Capacity Allocation Considering Customer Classification","authors":"Bing Han;Yingxia Chi;Yuan Xu;Yongshin Park","doi":"10.1109/TITS.2025.3528406","DOIUrl":"https://doi.org/10.1109/TITS.2025.3528406","url":null,"abstract":"Although multimodal transport has been widely developed, the multimodal transport operation system is still not as mature as other single modes of transport. Currently, the optimization of multimodal transport solutions and the allocation of capacity are planned as two separate parts, and the research on customer classification of multimodal transport is insufficient. The current bottleneck in multimodal transportation systems is optimizing multimodal customer classification and transportation solutions. Additionally, such an optimization can significantly improve the system’s overall revenue. Based on the customer classification theory of revenue management, we classified and managed multimodal transport customers and allocated and priced the transportation capacity according to the demand characteristics and price sensitivities of different customers. Furthermore, we considered the impact of transportation scheme planning on the profit of multimodal transport. Accordingly, we developed a joint optimization model for multimodal transport schemes, capacity allocation, and pricing by considering the customer classification. We solved the model using a hybrid particle swarm algorithm and validated it using arithmetic examples. The results indicate that a customer classification strategy can significantly improve the profit of multimodal transport operators when customer demand is unstable, and the total profit of the transportation system is increased by 7%. Moreover, these results suggest combining transportation solution optimization with customer classification can lead to more profitable multimodal revenue management solutions. Thus, our results can guide multimodal operators for systematically dealing with the customer classification problem and optimizing transportation schemes while improving their profits. Moreover, this study offers a reference for decision-making in multimodal operation management.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3161-3174"},"PeriodicalIF":7.9,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535580","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 : 2025-01-29DOI: 10.1109/TITS.2024.3504405
Yinglin Li;Weiwei Wu;Hantao Zhao;Yi Shi;Yan Lyu
Understanding the movement of crowds is important to the management of public places and urban safety. Existing researches mostly focused on tracking pedestrians in video clips from a single camera or across multiple cameras (Multi-Object Tracking) by identifying individuals with similar appearance or spatial-temporal movement features. However, how crowds navigate through invisible area between cameras in crowded environments have been overlooked. Moreover, identifying individuals across camera in a crowded environment could be challenging due to cluttered pedestrian appearance and highly uncertain movements. In this paper, we focus on recovering crowd trajectories in the invisible area of sparse camera networks within crowded public environments. We achieve better spatial-temporal feature matching by estimating the most likely travel time between segmented tracklet observations of individuals with elaborate consideration of pedestrian interactions, which reduces the dependence on unreliable appearance features. Subsequently, we recover trajectories for matched tracklets in the invisible area with a high fidelity crowd simulation model. Extensive experiments on two real-world trajectory datasets show that our proposed method is superior to existing spatial-temporal based MOT methods and improves the appearance-based MOT models in terms of association accuracy and trajectory fidelity.
{"title":"Recovering Crowd Trajectories in Invisible Area of Camera Networks","authors":"Yinglin Li;Weiwei Wu;Hantao Zhao;Yi Shi;Yan Lyu","doi":"10.1109/TITS.2024.3504405","DOIUrl":"https://doi.org/10.1109/TITS.2024.3504405","url":null,"abstract":"Understanding the movement of crowds is important to the management of public places and urban safety. Existing researches mostly focused on tracking pedestrians in video clips from a single camera or across multiple cameras (Multi-Object Tracking) by identifying individuals with similar appearance or spatial-temporal movement features. However, how crowds navigate through invisible area between cameras in crowded environments have been overlooked. Moreover, identifying individuals across camera in a crowded environment could be challenging due to cluttered pedestrian appearance and highly uncertain movements. In this paper, we focus on recovering crowd trajectories in the invisible area of sparse camera networks within crowded public environments. We achieve better spatial-temporal feature matching by estimating the most likely travel time between segmented tracklet observations of individuals with elaborate consideration of pedestrian interactions, which reduces the dependence on unreliable appearance features. Subsequently, we recover trajectories for matched tracklets in the invisible area with a high fidelity crowd simulation model. Extensive experiments on two real-world trajectory datasets show that our proposed method is superior to existing spatial-temporal based MOT methods and improves the appearance-based MOT models in terms of association accuracy and trajectory fidelity.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3350-3368"},"PeriodicalIF":7.9,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535552","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}
Aiming at the problem of low merging efficiency, poor platoon stability, and high collision risk when multiple connected and automated vehicles merge into the same target platoon, we propose a multi-vehicle self-organized cooperative control strategy for platoon formation, which includes vehicle self-organizing formation control and platoon cooperative merging control. The vehicle self-organizing formation control module organizes the merging vehicles within the V2V communication range into multiple local platoons. The dynamic self-adjusting critical interval and a fixed-topology second-order platoon consistency control protocol are proposed to divided the vehicles reasonably and make the states of local platoon vehicles consistent. The merging vehicles merge into the target platoon as a whole in the form of a local platoon, which transforms the complex multi-vehicle merge problem into a platoon cooperative control problem and improves the merging efficiency. The platoon cooperative merging control module adopts a distributed model predictive control (DMPC) theory to design two longitudinal cooperative merging controllers, which control the target platoon to split to create a merging gap and the local platoon to align with this gap longitudinally. The lateral merging controller controls the local platoon change the lane to merge into the target platoon safely and smoothly. Simulation experiments are conducted in typical scenarios, and it is verified that the proposed control strategy can enable multi-vehicles to merge into a platoon efficiently, safely, and stably.
{"title":"A Multi-Vehicle Self-Organized Cooperative Control Strategy for Platoon Formation in Connected Environment","authors":"Mengqi Zhang;Chunyan Wang;Wanzhong Zhao;Jinqiang Liu;Ziyu Zhang","doi":"10.1109/TITS.2024.3504572","DOIUrl":"https://doi.org/10.1109/TITS.2024.3504572","url":null,"abstract":"Aiming at the problem of low merging efficiency, poor platoon stability, and high collision risk when multiple connected and automated vehicles merge into the same target platoon, we propose a multi-vehicle self-organized cooperative control strategy for platoon formation, which includes vehicle self-organizing formation control and platoon cooperative merging control. The vehicle self-organizing formation control module organizes the merging vehicles within the V2V communication range into multiple local platoons. The dynamic self-adjusting critical interval and a fixed-topology second-order platoon consistency control protocol are proposed to divided the vehicles reasonably and make the states of local platoon vehicles consistent. The merging vehicles merge into the target platoon as a whole in the form of a local platoon, which transforms the complex multi-vehicle merge problem into a platoon cooperative control problem and improves the merging efficiency. The platoon cooperative merging control module adopts a distributed model predictive control (DMPC) theory to design two longitudinal cooperative merging controllers, which control the target platoon to split to create a merging gap and the local platoon to align with this gap longitudinally. The lateral merging controller controls the local platoon change the lane to merge into the target platoon safely and smoothly. Simulation experiments are conducted in typical scenarios, and it is verified that the proposed control strategy can enable multi-vehicles to merge into a platoon efficiently, safely, and stably.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"4002-4018"},"PeriodicalIF":7.9,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535571","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 paper describes the design and validation of a spatial image registration algorithm for a vehicular Head-Mounted Augmented Reality (AR) system. AR can considerably improve the driving experience by increasing the driver’s situational awareness. AR can only work if stable and realistic holograms are generated. The process of generating the holograms so that they appear in a specific position in the world is also known as image registration. Since AR devices employ see-through Head-Mounted Displays, realistic image registration requires high-accuracy head tracking. Solutions exist in static environments where state-of-the-art simultaneous localization and mapping algorithms suffice. Vehicles are more challenging. In aerospace, costly optical-inertial tracking systems are regularly employed. This paper focuses instead on low-cost ground vehicles and proposes a solution that does not require aerospace-grade Inertial Measurement Units and is easily integrable on cars. The proposed solution, tested on a racing circuit, is based on passive markers and on the stereoscopic detection of the road plane on which the AR features are anchored.
{"title":"Design of a Cost Effective Spatial Image Registration System for Augmented Reality in Vehicular Applications","authors":"Matteo Corno;Luca Franceschetti;Sergio Matteo Savaresi","doi":"10.1109/TITS.2025.3530496","DOIUrl":"https://doi.org/10.1109/TITS.2025.3530496","url":null,"abstract":"The paper describes the design and validation of a spatial image registration algorithm for a vehicular Head-Mounted Augmented Reality (AR) system. AR can considerably improve the driving experience by increasing the driver’s situational awareness. AR can only work if stable and realistic holograms are generated. The process of generating the holograms so that they appear in a specific position in the world is also known as image registration. Since AR devices employ see-through Head-Mounted Displays, realistic image registration requires high-accuracy head tracking. Solutions exist in static environments where state-of-the-art simultaneous localization and mapping algorithms suffice. Vehicles are more challenging. In aerospace, costly optical-inertial tracking systems are regularly employed. This paper focuses instead on low-cost ground vehicles and proposes a solution that does not require aerospace-grade Inertial Measurement Units and is easily integrable on cars. The proposed solution, tested on a racing circuit, is based on passive markers and on the stereoscopic detection of the road plane on which the AR features are anchored.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"2967-2976"},"PeriodicalIF":7.9,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535585","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}
Pedestrian trajectory prediction is a key component for various applications that involve human and vehicle interactions, such as autonomous driving, traffic management and smart city planning. Existing methods based on graph neural networks have limited ability to capture group interactions and precisely model complex associations among multi-agents. To solve these problems, we propose OST-HGCN, an optimized hypergraph convolutional network. It models multi-agent trajectory interactions from both temporal and spatial perspectives using hypergraph structures, and optimizes the spatio-temporal hypergraph structure to enable fine-grained analysis of multi-agent trajectory motion intentions and high-order interactions. We employ OST-HGCN to a CVAE-based prediction framework, and use the optimized hypergraph structure to predict multi-agent plausible trajectories. We conduct extensive experiments on four real trajectory prediction datasets of NBA, NFL, SDD and ETH-UCY, and verify the effectiveness of the proposed OST-HGCN.
{"title":"OST-HGCN: Optimized Spatial-Temporal Hypergraph Convolution Network for Trajectory Prediction","authors":"Xuanqi Lin;Yong Zhang;Shun Wang;Yongli Hu;Baocai Yin","doi":"10.1109/TITS.2025.3529666","DOIUrl":"https://doi.org/10.1109/TITS.2025.3529666","url":null,"abstract":"Pedestrian trajectory prediction is a key component for various applications that involve human and vehicle interactions, such as autonomous driving, traffic management and smart city planning. Existing methods based on graph neural networks have limited ability to capture group interactions and precisely model complex associations among multi-agents. To solve these problems, we propose OST-HGCN, an optimized hypergraph convolutional network. It models multi-agent trajectory interactions from both temporal and spatial perspectives using hypergraph structures, and optimizes the spatio-temporal hypergraph structure to enable fine-grained analysis of multi-agent trajectory motion intentions and high-order interactions. We employ OST-HGCN to a CVAE-based prediction framework, and use the optimized hypergraph structure to predict multi-agent plausible trajectories. We conduct extensive experiments on four real trajectory prediction datasets of NBA, NFL, SDD and ETH-UCY, and verify the effectiveness of the proposed OST-HGCN.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3056-3070"},"PeriodicalIF":7.9,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535578","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 : 2025-01-27DOI: 10.1109/TITS.2025.3529691
Xinyin Xiang;Jin Cao;Weiguo Fan
Cyber-physical systems (CPSs) connected in the form of the Industrial Internet of Things (IIoT) are susceptible to various security threats. Due to the extensive deployment of infrastructure for IIoT devices, the trustworthiness and security of data are among the major concerns in CPSs. Therefore, establishing security measures against potential threats through trust assessment and trust authentication has become a key goal. Blockchain has the characteristics of traceability, anonymity, transparency, etc., and can achieve trust authentication for trust assessment. In our work, we propose a lightweight decentralized authentication and trust management scheme for edge AI-enabled CPSs that supports access control on the basis of extended chaotic maps, which meets the privacy and security needs of data transmission in a broader sense. Moreover, we develop a trust model for checking the trustworthiness of data collected by smart devices/sensor nodes. A formal security analysis is executed by utilizing the broadly applicable real-or-random (RoR) model. Our scheme, which is different from previous methods, combines high security with relatively low communication and computational costs. Through an informal security analysis, we verify that our proposal is in compliance with the security requirements and can withstand various forms of attacks. Furthermore, the functionality and performance analysis results indicate that our method is better suited for lightweight validation in CPS networks while providing a higher level of security than other methods.
{"title":"Secure Authentication and Trust Management Scheme for Edge AI-Enabled Cyber-Physical Systems","authors":"Xinyin Xiang;Jin Cao;Weiguo Fan","doi":"10.1109/TITS.2025.3529691","DOIUrl":"https://doi.org/10.1109/TITS.2025.3529691","url":null,"abstract":"Cyber-physical systems (CPSs) connected in the form of the Industrial Internet of Things (IIoT) are susceptible to various security threats. Due to the extensive deployment of infrastructure for IIoT devices, the trustworthiness and security of data are among the major concerns in CPSs. Therefore, establishing security measures against potential threats through trust assessment and trust authentication has become a key goal. Blockchain has the characteristics of traceability, anonymity, transparency, etc., and can achieve trust authentication for trust assessment. In our work, we propose a lightweight decentralized authentication and trust management scheme for edge AI-enabled CPSs that supports access control on the basis of extended chaotic maps, which meets the privacy and security needs of data transmission in a broader sense. Moreover, we develop a trust model for checking the trustworthiness of data collected by smart devices/sensor nodes. A formal security analysis is executed by utilizing the broadly applicable real-or-random (RoR) model. Our scheme, which is different from previous methods, combines high security with relatively low communication and computational costs. Through an informal security analysis, we verify that our proposal is in compliance with the security requirements and can withstand various forms of attacks. Furthermore, the functionality and performance analysis results indicate that our method is better suited for lightweight validation in CPS networks while providing a higher level of security than other methods.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3237-3249"},"PeriodicalIF":7.9,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535429","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：