Pub Date : 2025-01-27DOI: 10.1109/TITS.2025.3527633
Giancarlo Santamato;Lorenzo Tozzetti;Massimiliano Solazzi;Eugenio Fedeli;Fabrizio Di Pasquale
In this work, we propose the concept of the Smart Rail, an innovative system for the continuous monitoring of the track geometry based on embedded arrays of Fiber Bragg Grating sensors and Raman-based distributed temperature sensors. First, we discuss how our technology design, based on a custom metallic patch embedding the FBG sensors and brazed on the track, overcomes the robustness concerns of the State of the Art. The metrological principle is formulated based on an analytical/FE model allowing the correlation of the measured signals to the local curvature deformation of the rail, and then to reconstruct the global track geometry. The effect of spatial sampling on the detection of even short-wave defects is addressed through simulations, as being a crucial trade-off between effectiveness and complexity. Experimental results performed on a first prototype demonstrate an efficient strain transfer with excellent agreement with the theoretical predictions. Hence the proposed technology seems very promising for the next generation of monitoring systems, in terms of robustness and compatibility with maintenance operations.
{"title":"SmartRail: A System for the Continuous Monitoring of the Track Geometry Based on Embedded Arrays of Fiber Optic Sensors","authors":"Giancarlo Santamato;Lorenzo Tozzetti;Massimiliano Solazzi;Eugenio Fedeli;Fabrizio Di Pasquale","doi":"10.1109/TITS.2025.3527633","DOIUrl":"https://doi.org/10.1109/TITS.2025.3527633","url":null,"abstract":"In this work, we propose the concept of the Smart Rail, an innovative system for the continuous monitoring of the track geometry based on embedded arrays of Fiber Bragg Grating sensors and Raman-based distributed temperature sensors. First, we discuss how our technology design, based on a custom metallic patch embedding the FBG sensors and brazed on the track, overcomes the robustness concerns of the State of the Art. The metrological principle is formulated based on an analytical/FE model allowing the correlation of the measured signals to the local curvature deformation of the rail, and then to reconstruct the global track geometry. The effect of spatial sampling on the detection of even short-wave defects is addressed through simulations, as being a crucial trade-off between effectiveness and complexity. Experimental results performed on a first prototype demonstrate an efficient strain transfer with excellent agreement with the theoretical predictions. Hence the proposed technology seems very promising for the next generation of monitoring systems, in terms of robustness and compatibility with maintenance operations.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3262-3272"},"PeriodicalIF":7.9,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535574","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.2025.3529838
Yongqiang Lu;Hongjie Ma;Edward Smart;Hui Yu
Autonomous vehicles (AVs) still pose challenges in improving intelligence, safety, and reliability in complex motorway scenarios. Recently, deep reinforcement learning (DRL) has demonstrated superior decision-making capabilities in dynamic environments compared to rule-based methods. However, it requires considerable training resources due to a lack of innovative DRL component design (e.g., state space and reward) to link observation and action accurately. Its opaque nature may also result in hazardous driving conditions. In this paper, we introduce a hybrid autopilot framework that amalgamates three modules: (i) DRL is employed to build a smart, learnable, and scalable driving policy across various motorway scenarios; (ii) a kinematic-based co-pilot strategy is devised to bolster training efficiency and provide flexible decision-making guidance; and (iii) a rule-based system assesses and determines the final action outputs in real-time between itself and the DRL policy to further enhance safety. Extensive simulations are conducted under different complex motorway scenarios. The results indicate that the proposed framework surpasses the baseline DRL policy in terms of training efficiency, intelligence, safety, and reliability.
{"title":"Enhancing Autonomous Driving Decision: A Hybrid Deep Reinforcement Learning-Kinematic-Based Autopilot Framework for Complex Motorway Scenes","authors":"Yongqiang Lu;Hongjie Ma;Edward Smart;Hui Yu","doi":"10.1109/TITS.2025.3529838","DOIUrl":"https://doi.org/10.1109/TITS.2025.3529838","url":null,"abstract":"Autonomous vehicles (AVs) still pose challenges in improving intelligence, safety, and reliability in complex motorway scenarios. Recently, deep reinforcement learning (DRL) has demonstrated superior decision-making capabilities in dynamic environments compared to rule-based methods. However, it requires considerable training resources due to a lack of innovative DRL component design (e.g., state space and reward) to link observation and action accurately. Its opaque nature may also result in hazardous driving conditions. In this paper, we introduce a hybrid autopilot framework that amalgamates three modules: (i) DRL is employed to build a smart, learnable, and scalable driving policy across various motorway scenarios; (ii) a kinematic-based co-pilot strategy is devised to bolster training efficiency and provide flexible decision-making guidance; and (iii) a rule-based system assesses and determines the final action outputs in real-time between itself and the DRL policy to further enhance safety. Extensive simulations are conducted under different complex motorway scenarios. The results indicate that the proposed framework surpasses the baseline DRL policy in terms of training efficiency, intelligence, safety, and reliability.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3198-3209"},"PeriodicalIF":7.9,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535543","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.2025.3529523
Wentao Zhang;Guoqiang Hu
In this paper, we study the package delivery problem where the transportation tasks, including arriving at the delivery locations and returning to the depots, are required to be completed within a time window. To this end, a time-homogeneous preset-time algorithm is presented to coordinate multiple vehicles within an identical time window, where arrival time delays are used to characterize the arrival time of the vehicles. Consequently, the considered package delivery problem is formulated by two phases: “Active phase” and “Sleeping phase”, over which vehicles use the neighboring information to achieve coordination. For the proposed algorithm, we use Lyapunov based method to derive condition guaranteeing the coordination of vehicles, under a very mild communication topology condition. As an extension, a time-heterogeneous preset-time algorithm is designed. We demonstrate that coordination among vehicles is determined by the maximal preset-time. Built upon this observation, we further show that there is an equivalence between the proposed formulation and the dynamical equation of the interacting vehicles. Finally, a numerical example for a package delivery problem, comprised of two coordination phases, is carried out to illustrate the proposed preset-time coordination formulation, and the time-heterogeneous case is further discussed as well.
{"title":"A Preset-Time Method for Multi-Robot Coordination With Application to Package Delivery","authors":"Wentao Zhang;Guoqiang Hu","doi":"10.1109/TITS.2025.3529523","DOIUrl":"https://doi.org/10.1109/TITS.2025.3529523","url":null,"abstract":"In this paper, we study the package delivery problem where the transportation tasks, including arriving at the delivery locations and returning to the depots, are required to be completed within a time window. To this end, a time-homogeneous preset-time algorithm is presented to coordinate multiple vehicles within an identical time window, where arrival time delays are used to characterize the arrival time of the vehicles. Consequently, the considered package delivery problem is formulated by two phases: “Active phase” and “Sleeping phase”, over which vehicles use the neighboring information to achieve coordination. For the proposed algorithm, we use Lyapunov based method to derive condition guaranteeing the coordination of vehicles, under a very mild communication topology condition. As an extension, a time-heterogeneous preset-time algorithm is designed. We demonstrate that coordination among vehicles is determined by the maximal preset-time. Built upon this observation, we further show that there is an equivalence between the proposed formulation and the dynamical equation of the interacting vehicles. Finally, a numerical example for a package delivery problem, comprised of two coordination phases, is carried out to illustrate the proposed preset-time coordination formulation, and the time-heterogeneous case is further discussed as well.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3185-3197"},"PeriodicalIF":7.9,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535575","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 : 2025-01-24DOI: 10.1109/TITS.2025.3528961
Pooja;Sandeep Kumar Sood
In the constantly changing realm of logistics and transportation management, the incorporation of Information and Communication Technology (ICT) has catalyzed transformative paradigm shifts in the approach and resolution of Vehicle Route Optimization (VRO). The current scientometric research paper embarks on a comprehensive exploration of the scholarly endeavors acquired from the Scopus database in the realm of ICT-assisted vehicle route optimization, spanning 2014–2023. The scientometric implications of the article encompass several pivotal dimensions, including publication patterns, (author, country, institution) co-authorship, geographical distribution, Document Co-citation network Analysis (DCA) and top articles based on betweenness centrality corresponding to each opted category of the current knowledge domain. A meticulous examination of the analyses revealed a significant research impact in the pervasive computing and communication technology categories. The co-authorship analysis presenting the interconnectedness of collaborative efforts across countries, authors, and institutions highlights the authors and universities of China and the United States as dominant players in the domain. The DCA elucidates research themes, including intelligent transportation systems, unmanned aerial vehicle-based wireless sensor networks, electric vehicle-based sustainable VRO, and vehicular ad-hoc networks. These themes underscore the current research trajectories within the field. Notably, quantum computing and blockchain emerged as prominent technologies. Overall, the study unveils the transformative impact of ICT on VRO, highlighting the key themes, future research directions and a collaborative research community poised for substantial innovation in this area of research.
{"title":"A Multifaceted Analysis of Intelligent Vehicle Route Optimization","authors":"Pooja;Sandeep Kumar Sood","doi":"10.1109/TITS.2025.3528961","DOIUrl":"https://doi.org/10.1109/TITS.2025.3528961","url":null,"abstract":"In the constantly changing realm of logistics and transportation management, the incorporation of Information and Communication Technology (ICT) has catalyzed transformative paradigm shifts in the approach and resolution of Vehicle Route Optimization (VRO). The current scientometric research paper embarks on a comprehensive exploration of the scholarly endeavors acquired from the Scopus database in the realm of ICT-assisted vehicle route optimization, spanning 2014–2023. The scientometric implications of the article encompass several pivotal dimensions, including publication patterns, (author, country, institution) co-authorship, geographical distribution, Document Co-citation network Analysis (DCA) and top articles based on betweenness centrality corresponding to each opted category of the current knowledge domain. A meticulous examination of the analyses revealed a significant research impact in the pervasive computing and communication technology categories. The co-authorship analysis presenting the interconnectedness of collaborative efforts across countries, authors, and institutions highlights the authors and universities of China and the United States as dominant players in the domain. The DCA elucidates research themes, including intelligent transportation systems, unmanned aerial vehicle-based wireless sensor networks, electric vehicle-based sustainable VRO, and vehicular ad-hoc networks. These themes underscore the current research trajectories within the field. Notably, quantum computing and blockchain emerged as prominent technologies. Overall, the study unveils the transformative impact of ICT on VRO, highlighting the key themes, future research directions and a collaborative research community poised for substantial innovation in this area of research.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"2833-2850"},"PeriodicalIF":7.9,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535421","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 : 2025-01-24DOI: 10.1109/TITS.2025.3529021
Han Zhang;Yuanhao Li;Wanzhong Zhao;Weimei Quan;Chunyan Wang
To improve the overall performance of human-vehicle cooperation and enhance the drivers’ confidence in the advanced driver assistance system (ADAS), an adaptive haptic assistance control scheme for the steer-by-wire (SBW) vehicle is presented in this paper. A comprehensive human-vehicle system model is built, including vehicle dynamics, the SBW model, and the driver’s arm neuromuscular dynamics model, as a foundation for controller design. An expert driver model based on a multi-layer feed-forward neural network (MLFN) is developed to generate the reference steering angle for haptic assistance design. The individual driver’s arm characteristics are identified and incorporated into the adaptive haptic assistance controller design to generate personalized torque assistance, facilitating a typical driver to achieve the same trajectory-tracking performance as experts. The nonsingular fast terminal sliding mode (NFTSM) is applied to calculate the assistance torque to ensure the fast finite-time convergence and robustness of the system. Simulations and driver-in-the-loop experiments are conducted, with results showing that the proposed haptic assistance controller can help drivers complete the trajectory-tracking task by providing personalized torque assistance while reducing their steering workload.
{"title":"Adaptive Haptic Assistance Control Considering Individual Driver’s Arm Characteristics","authors":"Han Zhang;Yuanhao Li;Wanzhong Zhao;Weimei Quan;Chunyan Wang","doi":"10.1109/TITS.2025.3529021","DOIUrl":"https://doi.org/10.1109/TITS.2025.3529021","url":null,"abstract":"To improve the overall performance of human-vehicle cooperation and enhance the drivers’ confidence in the advanced driver assistance system (ADAS), an adaptive haptic assistance control scheme for the steer-by-wire (SBW) vehicle is presented in this paper. A comprehensive human-vehicle system model is built, including vehicle dynamics, the SBW model, and the driver’s arm neuromuscular dynamics model, as a foundation for controller design. An expert driver model based on a multi-layer feed-forward neural network (MLFN) is developed to generate the reference steering angle for haptic assistance design. The individual driver’s arm characteristics are identified and incorporated into the adaptive haptic assistance controller design to generate personalized torque assistance, facilitating a typical driver to achieve the same trajectory-tracking performance as experts. The nonsingular fast terminal sliding mode (NFTSM) is applied to calculate the assistance torque to ensure the fast finite-time convergence and robustness of the system. Simulations and driver-in-the-loop experiments are conducted, with results showing that the proposed haptic assistance controller can help drivers complete the trajectory-tracking task by providing personalized torque assistance while reducing their steering workload.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"2977-2987"},"PeriodicalIF":7.9,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535433","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 : 2025-01-23DOI: 10.1109/TITS.2024.3517879
Li-Sha Xu;Ting Huang;Bo-Wen Zhao;Yue-Jiao Gong;Jing Liu
The significance of maritime transportation highlights the need to enhance the efficiency of container terminals. This study addresses a challenge within maritime transportation, specifically the continuous berth allocation and time-variant quay crane assignment problem (C/T-V BACAP). We formulate a comprehensive mathematical model of C/T-V BACAP. To solve the problem, we propose an effective memetic algorithm with a heuristic decoding method, named HMA, which comprises three essential components: a three-stage heuristic decoding method, a clustering-based evolutionary strategy, and a target-guided local search operator. The three-stage heuristic decoding method guarantees solution feasibility and high quality through the entire optimization, allowing the following strategies to fully utilize their search capabilities. The clustering-based evolutionary strategy refines the search space and diversifies the promising candidates. Meanwhile, the target-guided local search operator rapidly optimizes the allocation for the challenging vessel. The experimental results demonstrate that the proposed algorithm delivers excellent performance, especially in handling large-scale instances (up to 60 vessels). Our proposed method outperforms the state-of-the-art BACAP algorithms by an average margin of 150% in terms of berth offset and waiting time in most problem instances.
{"title":"Continuous Berth Allocation and Time-Variant Quay Crane Assignment: Memetic Algorithm With a Heuristic Decoding Method","authors":"Li-Sha Xu;Ting Huang;Bo-Wen Zhao;Yue-Jiao Gong;Jing Liu","doi":"10.1109/TITS.2024.3517879","DOIUrl":"https://doi.org/10.1109/TITS.2024.3517879","url":null,"abstract":"The significance of maritime transportation highlights the need to enhance the efficiency of container terminals. This study addresses a challenge within maritime transportation, specifically the continuous berth allocation and time-variant quay crane assignment problem (C/T-V BACAP). We formulate a comprehensive mathematical model of C/T-V BACAP. To solve the problem, we propose an effective memetic algorithm with a heuristic decoding method, named HMA, which comprises three essential components: a three-stage heuristic decoding method, a clustering-based evolutionary strategy, and a target-guided local search operator. The three-stage heuristic decoding method guarantees solution feasibility and high quality through the entire optimization, allowing the following strategies to fully utilize their search capabilities. The clustering-based evolutionary strategy refines the search space and diversifies the promising candidates. Meanwhile, the target-guided local search operator rapidly optimizes the allocation for the challenging vessel. The experimental results demonstrate that the proposed algorithm delivers excellent performance, especially in handling large-scale instances (up to 60 vessels). Our proposed method outperforms the state-of-the-art BACAP algorithms by an average margin of 150% in terms of berth offset and waiting time in most problem instances.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3387-3401"},"PeriodicalIF":7.9,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535519","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}
In the domain of route planning, the critical concern for travel efficiency has shifted towards optimizing travel time over distance due to the rise in congestion and the dynamic nature of modern road networks. Addressing this shift, we introduce Dynamic Route Optimization with Multi-Category Constraints (DROMC) for Point-of-Interest (POI) visits, which seeks to find the most time-efficient path that satisfies a user-defined list of requirements, considering both the spatial and temporal dimensions. This paper proposes a novel approach that leverages a path enumeration algorithm, which iteratively validates the k-fastest paths until all user queries are satisfied, ensuring adherence to time constraints and POI availability. To enhance the algorithm’s efficiency, we employ several key methodologies. First, we adapt the kSP algorithm to account for POI-focused path enumeration. We also introduce a Shared Prefix Tree (SPFT) with binary encoding, which significantly improves the storage and retrieval of path information. Moreover, we integrate a grid-based heuristic for quicker computation and implement strategic pruning methods to circumvent redundant calculations and manage POI business hours effectively. Our extensive experiments on real-world networks demonstrate the algorithm’s superiority in finding more efficient paths in shorter time frames compared to existing methods.
{"title":"Dynamic Route Optimization With Multi-Category Constraints for POIs Visit","authors":"Jiajia Li;Chunhui Liu;Dan He;Lei Li;Xiaofang Zhou;Rui Zhu","doi":"10.1109/TITS.2024.3520580","DOIUrl":"https://doi.org/10.1109/TITS.2024.3520580","url":null,"abstract":"In the domain of route planning, the critical concern for travel efficiency has shifted towards optimizing travel time over distance due to the rise in congestion and the dynamic nature of modern road networks. Addressing this shift, we introduce Dynamic Route Optimization with Multi-Category Constraints (DROMC) for Point-of-Interest (POI) visits, which seeks to find the most time-efficient path that satisfies a user-defined list of requirements, considering both the spatial and temporal dimensions. This paper proposes a novel approach that leverages a path enumeration algorithm, which iteratively validates the k-fastest paths until all user queries are satisfied, ensuring adherence to time constraints and POI availability. To enhance the algorithm’s efficiency, we employ several key methodologies. First, we adapt the kSP algorithm to account for POI-focused path enumeration. We also introduce a Shared Prefix Tree (SPFT) with binary encoding, which significantly improves the storage and retrieval of path information. Moreover, we integrate a grid-based heuristic for quicker computation and implement strategic pruning methods to circumvent redundant calculations and manage POI business hours effectively. Our extensive experiments on real-world networks demonstrate the algorithm’s superiority in finding more efficient paths in shorter time frames compared to existing methods.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3499-3512"},"PeriodicalIF":7.9,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535531","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}
In large-scale urban environments, precise six-degree-of-freedom (6DOF) pose estimation is essential for vehicles and robots to perform autonomous driving and exploration, as well as to achieve high intelligence and full autonomy of Unmanned Aerial Vehicles (UAV). Achieving 6DOF pose estimation in Global Navigation Satellite System (GNSS)-denied environments is challenging. The performance of relative 6DOF localization systems based on Light Detection and Ranging (LiDAR), vision, and inertial data is easily affected by environmental conditions, leading to error accumulation and a significant decrease in estimation accuracy in complex environments. To address this issue, we propose a tightly coupled framework based on nonlinear optimization for vision, LiDAR, inertial, and GNSS raw data. In the experimental section, we validate the effectiveness of the proposed optimization factor model for GNSS data, LiDAR data, and visual data in improving position and orientation estimation accuracy through simulations. Additionally, we use real datasets to compare the proposed algorithm with several existing open-source programs in terms of computational efficiency, pose estimation accuracy, worst-case scenarios, and reliability. The experimental results show that, although the total processing time increases, the position estimation accuracy and orientation estimation accuracy of the proposed fusion algorithm improve by at least 58.0%. Overall, the proposed tightly-coupled algorithm outperforms the existing methods.
{"title":"Tightly-Coupled 6DoF Localization in Complex Environments With GNSS Raw Data","authors":"Yanfang Shi;Baowang Lian;Yonghong Zeng;Ernest Kurniawan","doi":"10.1109/TITS.2025.3528888","DOIUrl":"https://doi.org/10.1109/TITS.2025.3528888","url":null,"abstract":"In large-scale urban environments, precise six-degree-of-freedom (6DOF) pose estimation is essential for vehicles and robots to perform autonomous driving and exploration, as well as to achieve high intelligence and full autonomy of Unmanned Aerial Vehicles (UAV). Achieving 6DOF pose estimation in Global Navigation Satellite System (GNSS)-denied environments is challenging. The performance of relative 6DOF localization systems based on Light Detection and Ranging (LiDAR), vision, and inertial data is easily affected by environmental conditions, leading to error accumulation and a significant decrease in estimation accuracy in complex environments. To address this issue, we propose a tightly coupled framework based on nonlinear optimization for vision, LiDAR, inertial, and GNSS raw data. In the experimental section, we validate the effectiveness of the proposed optimization factor model for GNSS data, LiDAR data, and visual data in improving position and orientation estimation accuracy through simulations. Additionally, we use real datasets to compare the proposed algorithm with several existing open-source programs in terms of computational efficiency, pose estimation accuracy, worst-case scenarios, and reliability. The experimental results show that, although the total processing time increases, the position estimation accuracy and orientation estimation accuracy of the proposed fusion algorithm improve by at least 58.0%. Overall, the proposed tightly-coupled algorithm outperforms the existing methods.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3369-3386"},"PeriodicalIF":7.9,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535542","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 : 2025-01-22DOI: 10.1109/TITS.2025.3529365
Jia Hu;Tian Xu;Xuerun Yan;Hong Wang;Jintao Lai
Automated Vehicle (AV) safety is a critical issue and appeals to worldwide focus. To ensure AV safety, AV functions should be tested and evaluated in an enormous number of scenarios. Since such AV testing is time-consuming, scenario filters have been developed to identify safety-critical scenarios and omit ordinary ones. However, the scenarios identified by these filters do not uniquely match the AV function to be tested and are most likely not critical for the AV function. Therefore, an enhanced scenario filter is proposed in this paper. It bears the following features: 1) Automated-driving-function-specific scenario identification; 2) High coverage of critical scenarios; 3) Enhanced identification efficiency by avoiding adopting a surrogate model; 4) High reliability of critical scenario identification. To enable the above features, the proposed filter formulates the identification problem into an optimization problem and solves it with a model-free approach. Experiments have been conducted to evaluate and validate the proposed filter. The results confirm that the proposed filter is able to improve coverage of critical scenarios, efficiency of identification, and reliability of identification compared to the state-of-the-art filter. Specifically, the proposed filter improves coverage by up to 70 percent, efficiency by up to 97 percent, and reliability by up to 22 percent. The results also reveal that the proposed filter shows an increasing advantage for testing AV functions with higher complexity.
{"title":"An Accelerated Filter for Critical Scenario Identification in Automated Driving Function Testing: A Model-Free Approach","authors":"Jia Hu;Tian Xu;Xuerun Yan;Hong Wang;Jintao Lai","doi":"10.1109/TITS.2025.3529365","DOIUrl":"https://doi.org/10.1109/TITS.2025.3529365","url":null,"abstract":"Automated Vehicle (AV) safety is a critical issue and appeals to worldwide focus. To ensure AV safety, AV functions should be tested and evaluated in an enormous number of scenarios. Since such AV testing is time-consuming, scenario filters have been developed to identify safety-critical scenarios and omit ordinary ones. However, the scenarios identified by these filters do not uniquely match the AV function to be tested and are most likely not critical for the AV function. Therefore, an enhanced scenario filter is proposed in this paper. It bears the following features: 1) Automated-driving-function-specific scenario identification; 2) High coverage of critical scenarios; 3) Enhanced identification efficiency by avoiding adopting a surrogate model; 4) High reliability of critical scenario identification. To enable the above features, the proposed filter formulates the identification problem into an optimization problem and solves it with a model-free approach. Experiments have been conducted to evaluate and validate the proposed filter. The results confirm that the proposed filter is able to improve coverage of critical scenarios, efficiency of identification, and reliability of identification compared to the state-of-the-art filter. Specifically, the proposed filter improves coverage by up to 70 percent, efficiency by up to 97 percent, and reliability by up to 22 percent. The results also reveal that the proposed filter shows an increasing advantage for testing AV functions with higher complexity.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3128-3146"},"PeriodicalIF":7.9,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535482","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 : 2025-01-17DOI: 10.1109/TITS.2024.3516956
Jie Tang;Sunjian Zheng;Bo Yu;Xue Liu
Map matching is a pivotal component of intelligent urban transportation, offering foundational data for technologies such as path planning, traffic analysis, and trajectory analysis. Diverging from conventional rule-based and topological map matching algorithms, we approach the map matching task from a data-driven perspective, presenting an Elevation-Aware Map Matching Model under conditions of sparse data. This paper initiates from the vehicular standpoint, constructing an Elevation-Aware Unit utilizing imagery and sensor data to acquire elevation information for diverse urban roads. Subsequently, this unit is integrated into the map matching model, enhancing the model’s resilience to noise. Concurrently, employing a Fine-tuning transfer learning approach, we formulate a cross-domain map matching model to maximize the reduction of model development costs. The model undergoes testing on real-world datasets, employing four metrics for evaluation. The results indicate the superiority of this map matching model over existing counterparts, particularly in intricate urban road scenarios where the model exhibits outstanding performance. Additionally, we validate the effectiveness of the Elevation-Aware Unit, underscoring the significance of height information for map matching models.
{"title":"Elevation-Aware Map Matching Model Leveraging Transfer Learning in Sparse Data Conditions","authors":"Jie Tang;Sunjian Zheng;Bo Yu;Xue Liu","doi":"10.1109/TITS.2024.3516956","DOIUrl":"https://doi.org/10.1109/TITS.2024.3516956","url":null,"abstract":"Map matching is a pivotal component of intelligent urban transportation, offering foundational data for technologies such as path planning, traffic analysis, and trajectory analysis. Diverging from conventional rule-based and topological map matching algorithms, we approach the map matching task from a data-driven perspective, presenting an Elevation-Aware Map Matching Model under conditions of sparse data. This paper initiates from the vehicular standpoint, constructing an Elevation-Aware Unit utilizing imagery and sensor data to acquire elevation information for diverse urban roads. Subsequently, this unit is integrated into the map matching model, enhancing the model’s resilience to noise. Concurrently, employing a Fine-tuning transfer learning approach, we formulate a cross-domain map matching model to maximize the reduction of model development costs. The model undergoes testing on real-world datasets, employing four metrics for evaluation. The results indicate the superiority of this map matching model over existing counterparts, particularly in intricate urban road scenarios where the model exhibits outstanding performance. Additionally, we validate the effectiveness of the Elevation-Aware Unit, underscoring the significance of height information for map matching models.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 3","pages":"3724-3737"},"PeriodicalIF":7.9,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143563903","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}