IEEE Transactions on Intelligent Transportation Systems最新文献_第9页

Priority-Based Conflict Resolution for Manned and Unmanned Aircraft Integrated Operations 基于优先级的有人无人机综合作战冲突解决

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-08-10 DOI: 10.1109/TITS.2026.3719353

Zhaoxuan Liu;Kaiquan Cai;Yongwen Zhu;Kanglin Liu

{"title":"Priority-Based Conflict Resolution for Manned and Unmanned Aircraft Integrated Operations","authors":"Zhaoxuan Liu;Kaiquan Cai;Yongwen Zhu;Kanglin Liu","doi":"10.1109/TITS.2026.3719353","DOIUrl":"https://doi.org/10.1109/TITS.2026.3719353","url":null,"abstract":"Integration of Unmanned Aircraft Systems into the airspace is one of the major challenges in global air traffic management. Unlike previous conflict resolution methods intended solely for a specific type of aircraft, either manned or unmanned, this paper develops a priority-based approach for manned and unmanned aircraft resolution coordination in nonsegregated airspace. The motivation is to maximize the resolution efficiency profit of a priority ranking mechanism, where the most conflict-influential aircraft are handled first with aircraft heterogeneity considered. To support such mechanism, complex relations among multiple aircraft need to be analyzed for the determination of the deconflicting aircraft and the corresponding resolution order. First, aircraft priorities are allocated by an extended PageRank algorithm, where influential aircraft assume larger values and more maneuver responsibilities for deconfliction. The influence of aircraft is determined by its heterogeneous attributes (e.g., vehicle type, onboard system capability, mission category, health state) and its conflict severity in the overall conflict scenario. Next, feasible resolution strategies, including speed and heading maneuver options, are illustrated in the solution space diagram according to aircraft priority order. For final maneuver decision-making, the satisficing game theory is applied to ensure maneuver optimality both in terms of safety (e.g., conflict risk) and efficiency (e.g., adjustment cost). Specifically, effects of maneuver delay and secondary conflict are also incorporated to ensure maneuver utility. Simulation results verify the improved approach capability under various integrated operation scenarios. As a result, an efficient resolution is achieved with minimal aircraft maneuvers and deviations.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12043-12062"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149096978","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}

引用次数: 0

Learning-Based High-Level Decision Making for Abortable Overtaking in Autonomous Vehicles 基于学习的自动驾驶车辆可中止超车高层决策

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-08-03 DOI: 10.1109/TITS.2026.3717159

Ehsan Malayjerdi;Gokhan Alcan;Raivo Sell;Eshagh Kargar;Hatem Darweesh;Ville Kyrki

{"title":"Learning-Based High-Level Decision Making for Abortable Overtaking in Autonomous Vehicles","authors":"Ehsan Malayjerdi;Gokhan Alcan;Raivo Sell;Eshagh Kargar;Hatem Darweesh;Ville Kyrki","doi":"10.1109/TITS.2026.3717159","DOIUrl":"https://doi.org/10.1109/TITS.2026.3717159","url":null,"abstract":"Autonomous driving technology aims to enhance safety, efficiency, and decision-making in complex scenarios such as overtaking maneuvers. However, existing methods often lack adaptability in dynamic environments, leading to unsafe maneuvers or failed attempts. This paper introduces a reinforcement learning-based high-level decision-making framework that incorporates an abortable overtaking mechanism to improve safety and maneuver success rates. Using a Deep Q-Network (DQN), the system dynamically assesses traffic conditions to decide whether to proceed with or abort an overtaking maneuver, reducing collision risks. The proposed method was evaluated in 3,000 simulation scenarios, achieving a 92.2% successful overtaking rate, a 40% improvement over OpenPlanner’s 52.7%. Additionally, our approach significantly reduced collisions with oncoming traffic from 83.5% to 17.4%, demonstrating its effectiveness in handling dynamic interactions. The system was further validated in real-world experiments using the iseAuto autonomous shuttle, confirming its feasibility for deployment in real-world driving conditions.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"11983-11996"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097070","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}

引用次数: 0

Weakly Supervised Bird's Eye View Motion Prediction With Object Prior 具有目标先验的弱监督鸟瞰运动预测

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-06-25 DOI: 10.1109/TITS.2026.3704647

Yaqi Shen;Qianliang Wu;Jin Xie;Jian Yang

{"title":"Weakly Supervised Bird's Eye View Motion Prediction With Object Prior","authors":"Yaqi Shen;Qianliang Wu;Jin Xie;Jian Yang","doi":"10.1109/TITS.2026.3704647","DOIUrl":"https://doi.org/10.1109/TITS.2026.3704647","url":null,"abstract":"Current motion prediction methods mainly focus on predicting the motion information for each grid cell on the bird’s eye view representation. However, they predict motion for every single cell without object-level constraints, thereby suffering from limited performance. Inspired by the observation that the scenes can be segmented into a collection of objects with similar motion patterns, we propose an object-aware motion prediction framework to encode the object-level motion information into both the feature and motion spaces for more consistent motion results. Specifically, we design a probabilistic motion feature encoding module to generate probabilistic object-aware features. It utilizes the object priors in the current and future frames to parameterize two probability distributions, i.e., the current distribution and future distribution. Since the future frames are invisible during inference, we introduce a Kullback-Leibler divergence loss to minimize the divergence between these two distributions. By encoding the sampled latent code from the distributions into motion feature space, we can obtain more accurate motion results. Furthermore, we propose a confidence-aware motion encoding module to explicitly aggregate the object-level motion with learnable confidence weights, which aims to preserve the consistent motion patterns of points in the same objects. We conduct thorough experiments on the nuScenes and Waymo datasets. Specifically, our method achieves the mean errors of 0.2670 meters and 0.2807 meters on the slow groups of the two benchmarks, respectively, outperforming the compared weakly supervised method by up to 17%.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12201-12215"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097191","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}

引用次数: 0

Toward Robust Collaborative 3-D Object Detection via Two-Stage Cross-Domain Knowledge Transfer in Autonomous Driving 基于两阶段跨领域知识转移的自动驾驶三维目标鲁棒协同检测

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-07-20 DOI: 10.1109/TITS.2026.3710532

Benwu Wang;Qimin Xu;Xu Li;Wenkai Zhu;Jianxiao Zhu;Haoyang Che;Zhiyuan Xu;Baidan Li

{"title":"Toward Robust Collaborative 3-D Object Detection via Two-Stage Cross-Domain Knowledge Transfer in Autonomous Driving","authors":"Benwu Wang;Qimin Xu;Xu Li;Wenkai Zhu;Jianxiao Zhu;Haoyang Che;Zhiyuan Xu;Baidan Li","doi":"10.1109/TITS.2026.3710532","DOIUrl":"https://doi.org/10.1109/TITS.2026.3710532","url":null,"abstract":"Recent research has demonstrated that Vehicle-to-Everything (V2X) collaborative 3D object detection can provide sufficient scene understanding to support autonomous driving. However, these methods suffer from severe performance degradation when generalized to diverse environments and deployment conditions. Existing 3D adaptive methods tend to transfer from a homogeneous source domain knowledge to the target domain. Yet, the scarcity of well-annotated collaborative datasets and the Simulation-to-Reality (Sim2Real) domain gap limit their effectiveness. To this end, we propose a novel two-stage unsupervised domain adaptation method, S2C-UDA, for multi-agent 3D object detection driven by one single-agent source. Concretely, we first design an agent-wise Joint Domain Adversarial Pre-training network (JDA-PT) to align each target agent with the source domain, thus efficiently releasing pseudo labels. Then comes the customized Multi-level Response Self-training network (MLR-ST) to enhance intra-domain cross-agent adaptation by sequentially integrating feature-, instance-, and result-level responses. This hierarchical framework systematically aligns inter-agent feature distributions while simultaneously mitigating instance discrepancies, thereby facilitating the iteration of reliable detection results. Extensive evaluations on challenging real-world datasets reveal that S2C-UDA achieves superior adaptation performance for cross-domain collaborative 3D object detection in outdoor traffic scenarios.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12385-12399"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097329","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}

引用次数: 0

Double DQN for Optimizing Safety by Minimizing Driver Uncertainty at Highway-Rail Crossings: A Dilemma Field Theory 基于最小化驾驶员不确定性的双DQN公路铁路交叉口安全优化：两难场理论

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-02-09 DOI: 10.1109/TITS.2026.3659064

Yifan Xu;Zhixia Li;Heng Wei;Guohui Zhang;Song Wang;Shiqi Ou;Yiwei Wang;Hanyi Yang;Changjian Zhang;Shanglian Zhou

{"title":"Double DQN for Optimizing Safety by Minimizing Driver Uncertainty at Highway-Rail Crossings: A Dilemma Field Theory","authors":"Yifan Xu;Zhixia Li;Heng Wei;Guohui Zhang;Song Wang;Shiqi Ou;Yiwei Wang;Hanyi Yang;Changjian Zhang;Shanglian Zhou","doi":"10.1109/TITS.2026.3659064","DOIUrl":"https://doi.org/10.1109/TITS.2026.3659064","url":null,"abstract":"This article addresses the stop-go dilemma at four-quadrant gate (4QG) highway-rail crossings (HRCs) by introducing a novel reinforcement learning (RL) and Dilemma Field (DF) framework to minimize driver uncertainty. Conventional Type I and Type II dilemma-zone definitions rely on rigid spatial boundaries, risking over-protection or under-protection when driver behaviors deviate from assumed norms. In contrast, the proposed DF theory represents uncertainty as a continuous probability distribution, capturing the reality that vehicles beyond a nominal zone may remain partially confused while some within a zone might be decisive. A Markov chain stability theorem based on the Foster–Lyapunov criterion demonstrates that reducing the aggregate probability of uncertainty drives near-exponential convergence to safer, more stable traffic flow. To leverage these insights in real time, a Double Deep Q-Network (Double DQN) agent integrates the DF metric into its state and reward functions to adaptively optimize the warning signal activation at 4QG HRCs. Simulation results demonstrate that the proposed method raises minimum time-to-collision margins by 61% and reduces late-amber passing rates by 62% compared to constant-warning-time systems. These findings confirm that a probabilistic treatment of uncertainty, coupled with a learning-based control policy, yields substantially improved safety outcomes.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"13554-13571"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097529","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}

引用次数: 0

Multi-Transform Domain Fusion Architecture for High-Speed Train Bogie Fault Diagnosis in Speed-Varying Conditions 高速列车转向架变速故障诊断的多变换域融合体系

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-06-08 DOI: 10.1109/TITS.2026.3699673

Junxiao Ren;Xuefeng Gao;Qiang Li;Junlin Li;Zengyan Li

{"title":"Multi-Transform Domain Fusion Architecture for High-Speed Train Bogie Fault Diagnosis in Speed-Varying Conditions","authors":"Junxiao Ren;Xuefeng Gao;Qiang Li;Junlin Li;Zengyan Li","doi":"10.1109/TITS.2026.3699673","DOIUrl":"https://doi.org/10.1109/TITS.2026.3699673","url":null,"abstract":"Fault diagnosis of high-speed train bogies faces unprecedented challenges in speed-varying conditions, primarily manifesting in nonlinear dynamic characteristic variations, velocity-dependent fault signatures, and limited adaptability of existing methodologies. To address these critical challenges, this research proposes a novel multi-transform domain fusion architecture. This innovative framework synergistically integrates temporal domain feature with Fast Wavelet Transform and Gramian Angular Field to capture frequency-domain and time-frequency domain characteristics, respectively, while implementing a bespoke interactive attention mechanism for dynamic multi-domain feature fusion. Empirical validation on our curated dataset demonstrates remarkable performance metrics, achieving 100% diagnostic accuracy under iso-velocity conditions. Notably, the framework maintains 97.00% accuracy in the most challenging high-velocity scenarios. In comprehensive velocity condition testing, our methodology achieves a superior accuracy of 99.00%, significantly outperforming existing state-of-the-art approaches. Feature visualization analytics further substantiate the framework’s robust feature extraction capabilities across diverse velocity conditions. The proposed architecture provides a highly transferable approach for fault diagnosis of high-speed train and other complex industrial systems operating under speed-varying conditions.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12279-12288"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097458","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}

引用次数: 0

MapQP: Relational Query and Map-Aware Position Encoding for Online HD Map Construction MapQP：用于在线高清地图构建的关系查询和地图感知位置编码

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-07-13 DOI: 10.1109/TITS.2026.3704445

Ruikai Li;Hao Shan;Runxin Wang;Ziyang Yan;Han Jiang;Jianru Xiao;Yilong Ren;Haiyang Yu;Sijia Wen;Saru Kumari;Zhiyong Cui

{"title":"MapQP: Relational Query and Map-Aware Position Encoding for Online HD Map Construction","authors":"Ruikai Li;Hao Shan;Runxin Wang;Ziyang Yan;Han Jiang;Jianru Xiao;Yilong Ren;Haiyang Yu;Sijia Wen;Saru Kumari;Zhiyong Cui","doi":"10.1109/TITS.2026.3704445","DOIUrl":"https://doi.org/10.1109/TITS.2026.3704445","url":null,"abstract":"In autonomous driving systems, high-definition (HD) map plays a critical role by providing rich and detailed static environmental semantic information. Although DETR (DEtection TRansformer)-based methods have demonstrated promising performance in online vectorized HD map construction, existing approaches still result in biased or distorted outcomes, due to the inability to adequately exploit geometric information and accurately model the interrelationships between and within map elements. To address these issues, this article proposes <bold>MapQP</b>, an end-to-end framework that unifies relational <bold>q</b>uery modeling and map-aware <bold>p</b>ositional encoding for accurate and coherent HD map construction. Specifically, a relational query (RE-Query) mechanism is designed to accurately model the spatial relationships between map elements while explicitly characterizing the subordinate relationships of points. To further effectively leverage the geometric and positional features of the model, a map position encoding scheme is proposed specifically designed for vectorized HD map construction, which utilizes the coordinates of reference points and positional queries. We conduct extensive experiments on two of the most challenging datasets, nuScenes and Argoverse2. The experimental results demonstrate that MapQP achieves state-of-the-art (SOTA) performance on the nuScenes dataset, reaching 73.7 mAP. Notably, MapQP relies solely on single-frame multi-view RGB images, without requiring other computationally expensive additional inputs.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12233-12246"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097460","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}

引用次数: 0

WSPM3D: Weakly Supervised Prompted Monocular 3-D Object Detection Using Image-Level Labels 使用图像级标签的弱监督提示单目3-D目标检测

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-07-17 DOI: 10.1109/TITS.2026.3709512

Aoran Zhang;Zhigang Ling;Peiwei Chen;Haoran Tan;Yaonan Wang

{"title":"WSPM3D: Weakly Supervised Prompted Monocular 3-D Object Detection Using Image-Level Labels","authors":"Aoran Zhang;Zhigang Ling;Peiwei Chen;Haoran Tan;Yaonan Wang","doi":"10.1109/TITS.2026.3709512","DOIUrl":"https://doi.org/10.1109/TITS.2026.3709512","url":null,"abstract":"Weakly supervised monocular 3D object detection aims to predict 3D object locations and attributes using annotations on RGB images. Existing methods typically rely on large-scale 2D bounding box annotations. However, large-scale annotations remain costly. Moreover, inaccurate 2D boxes often lead to poor supervision and significantly degrade 3D detection performance. To address this limitation, we propose a novel Weakly-Supervised Prompted Monocular 3D (WSPM3D) Object Detection framework that relies solely on image-level labels and unlabeled point clouds. First, a point-prompt generation (PPG) module is introduced to extract semantic activation cues from image-level labels. Then, an occlusion-aware segmentation module (SAM2-SwinT) is developed to produce stable and consistent 2D pseudo-boxes using semantic cues from PPG. Furthermore, we introduce a Distance-Aware Refinement (DAR) module to enhance the quality of pseudo-boxes for distant objects, so that these enhanced 2D pseudo-boxes can guide the extraction of Candidate Object LiDAR Points (COLPs) to implicitly boost the performance of 3D object detection. Finally, two auxiliary geometric losses are proposed to prevent depth localization drift and align the predicted and LiDAR-derived BEV heatmaps, offering robust geometric supervision via sparse point clouds. Experimental results on the KITTI and nuScenes datasets demonstrate that our framework achieves superior monocular 3D object detection performance while greatly reducing the cost and potential errors of manual annotations.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12959-12969"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097592","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}

引用次数: 0

A DeepSeek-Based Multidimensional Environment-Contextualized Assessment Framework for Driving Behavior Evaluation 基于深度搜索的多维环境-情境化驾驶行为评估框架

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-07-10 DOI: 10.1109/TITS.2026.3704166

Ping Liu;Zhirui Liu;Mingjie Liu;Hailong Huang;Minglu Li

{"title":"A DeepSeek-Based Multidimensional Environment-Contextualized Assessment Framework for Driving Behavior Evaluation","authors":"Ping Liu;Zhirui Liu;Mingjie Liu;Hailong Huang;Minglu Li","doi":"10.1109/TITS.2026.3704166","DOIUrl":"https://doi.org/10.1109/TITS.2026.3704166","url":null,"abstract":"Existing driving behavior evaluation methods predominantly employ fixed-weight scoring systems that cannot adapt to heterogeneous traffic environments and lack mechanisms for generating personalized, interpretable feedback. This paper proposes an adaptive DeepSeek-based multidimensional environment contextualized assessment (DSMECA) framework for driving behavior evaluation. Firstly, four key dimensions, including safety, efficiency, comfort, and lane discipline, are adopted in the DSMECA framework as evaluation criteria. Accordingly, a continuous adaptive weight system (CAWS) is developed to dynamically compute dimension weights according to real-time traffic states, thereby eliminating the boundary discontinuity and poor scenario adaptability of conventional methods. Then, a hybrid clustering approach combining K-means++ initialization with support vector machine (SVM) boundary optimization is designed to identify driving styles accurately. Furthermore, a decoupled feedback module based on DeepSeek-V3 is introduced to generate interpretable, personalized natural-language evaluation and targeted improvement suggestions through cross-dimensional semantic reasoning. Experimental results from five real-world trajectory subsets demonstrate that DSMECA produces a markedly more discriminative score distribution than the fixed-weight Static Invariant Decontextualized Assessment (SIDA) baseline adopted on the same dataset, achieving an average increase of 22.66% in the highest evaluation tier. Quantitative analysis based on multiple driver samples further verifies the consistency of the LLM-driven feedback module, revealing the application potential in driver training, intelligent traffic monitoring, and traffic safety improvement.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12791-12805"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097682","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}

引用次数: 0

Adaptive Event-Triggered Fuzzy State Observer Control for Surface-Air Vehicles Subject to the Harbor-Approaching Operation 面向近港作业的地空飞行器自适应事件触发模糊状态观测器控制

IF 9.1 1区工程技术

IEEE Transactions on Intelligent Transportation Systems Pub Date : 2026-10-01 Epub Date: 2026-07-03 DOI: 10.1109/TITS.2026.3705994

Guoqing Zhang;Haoyu Zhao;Jiqiang Li;Weidong Zhang

{"title":"Adaptive Event-Triggered Fuzzy State Observer Control for Surface-Air Vehicles Subject to the Harbor-Approaching Operation","authors":"Guoqing Zhang;Haoyu Zhao;Jiqiang Li;Weidong Zhang","doi":"10.1109/TITS.2026.3705994","DOIUrl":"https://doi.org/10.1109/TITS.2026.3705994","url":null,"abstract":"This paper is concerned with an adaptive fuzzy observer control algorithm for the sea-air cooperative system subject to the harbor-approaching operation. The proposed algorithm consists of the guidance and control. In the former, a time-varying velocity function with the exponential form is conceived for achieving desired velocity-changing navigation effect. In the control part, a novel event-triggered fuzzy state observer is designed that uses the fuzzy logic system (FLS) and event-triggered mechanism, which is with two features. That is, the unmeasured variables of the underactuated surface vehicle (USV) and the unmanned aerial vehicle (UAV) are estimated, thereby mitigating the instability effect caused by external noise. Another feature is that the fuzzy triggered gain mechanism, using an adapting indeterminate threshold parameter, is designed to address the explicit problem of event-triggered amplitude gain. Furthermore, Lyapunov-based stability analysis provides a strictly theoretical guarantee with the semi-global uniformly ultimately bounded (SGUUB) stable. Finally, the effectiveness and advantages of the proposed strategy are verified through numerical results.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"27 10","pages":"12605-12616"},"PeriodicalIF":9.1,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097792","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}

引用次数: 0