Pub Date : 2024-12-16DOI: 10.1109/TITS.2024.3510945
Stavros Orfanoudakis;Cesar Diaz-Londono;Yunus Emre Yılmaz;Peter Palensky;Pedro P. Vergara
As electric vehicle (EV) numbers rise, concerns about the capacity of current charging and power grid infrastructure grow, necessitating the development of smart charging solutions. While many smart charging simulators have been developed in recent years, only a few support the development of Reinforcement Learning (RL) algorithms in the form of a Gym environment, and those that do usually lack depth in modeling Vehicle-to-Grid (V2G) scenarios. To address the aforementioned issues, this paper introduces EV2Gym, a realistic simulator platform for the development and assessment of small and large-scale smart charging algorithms within a standardized platform. The proposed simulator is populated with comprehensive EV, charging station, power transformer, and EV behavior models validated using real data. EV2Gym has a highly customizable interface empowering users to choose from pre-designed case studies or craft their own customized scenarios to suit their specific requirements. Moreover, it incorporates a diverse array of RL, mathematical programming, and heuristic algorithms to speed up the development and benchmarking of new solutions. By offering a unified and standardized platform, EV2Gym aims to provide researchers and practitioners with a robust environment for advancing and assessing smart charging algorithms.
{"title":"EV2Gym: A Flexible V2G Simulator for EV Smart Charging Research and Benchmarking","authors":"Stavros Orfanoudakis;Cesar Diaz-Londono;Yunus Emre Yılmaz;Peter Palensky;Pedro P. Vergara","doi":"10.1109/TITS.2024.3510945","DOIUrl":"https://doi.org/10.1109/TITS.2024.3510945","url":null,"abstract":"As electric vehicle (EV) numbers rise, concerns about the capacity of current charging and power grid infrastructure grow, necessitating the development of smart charging solutions. While many smart charging simulators have been developed in recent years, only a few support the development of Reinforcement Learning (RL) algorithms in the form of a Gym environment, and those that do usually lack depth in modeling Vehicle-to-Grid (V2G) scenarios. To address the aforementioned issues, this paper introduces EV2Gym, a realistic simulator platform for the development and assessment of small and large-scale smart charging algorithms within a standardized platform. The proposed simulator is populated with comprehensive EV, charging station, power transformer, and EV behavior models validated using real data. EV2Gym has a highly customizable interface empowering users to choose from pre-designed case studies or craft their own customized scenarios to suit their specific requirements. Moreover, it incorporates a diverse array of RL, mathematical programming, and heuristic algorithms to speed up the development and benchmarking of new solutions. By offering a unified and standardized platform, EV2Gym aims to provide researchers and practitioners with a robust environment for advancing and assessing smart charging algorithms.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"2410-2421"},"PeriodicalIF":7.9,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106274","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 : 2024-12-13DOI: 10.1109/TITS.2024.3516892
{"title":"2024 Index IEEE Transactions on Intelligent Transportation Systems Vol. 25","authors":"","doi":"10.1109/TITS.2024.3516892","DOIUrl":"https://doi.org/10.1109/TITS.2024.3516892","url":null,"abstract":"","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"25 12","pages":"1-312"},"PeriodicalIF":7.9,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10798999","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142870213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-11DOI: 10.1109/TITS.2024.3509394
Jiakai Zhou;Jun Yang;Xiaoliang Wu;Wanlin Zhou;Yang Wang
In autonomous driving, efficiently and accurately recognizing taillight states using dashcams is essential for interpreting other vehicles’ intentions. Recent video-based taillight recognition methods outperform earlier image-based approaches. However, they face challenges in efficiently integrating spatiotemporal information and managing high computational costs. In this paper, we introduce ETR, an accurate and efficient Transformer-based video classification model designed to enhance taillight recognition. Specifically, we first design a lightweight backbone to extract temporal and spatial features from videos and generate queries with prior information. Next, we develop a hierarchical progressive Transformer decoder that integrates feature maps from different levels of the backbone to enhance the model’s global information. Finally, we employ a classification head to predict the taillight state of the video. Additionally, we introduce a public dataset, ETR-Taillights, to address the current lack of open datasets for vehicle taillight recognition. The dataset contains 28,799 dashcam video clips, making it the largest public taillight recognition dataset. Experiments show that our method achieves a 91.69% F-measure on the ETR-Taillights dataset, surpassing the latest taillight recognition methods, VIF by 6.94% and CNN-LSTM by 10.82%. Additionally, it achieves an inference speed of 45.06 FPS, being 3.6 times faster than VIF. Furthermore, we conduct real-world road tests to demonstrate our method’s robustness and effectiveness in practical scenarios. Our model and dataset are available at https://github.com/yang590/vehicle-taillight.
{"title":"ETR: Enhancing Taillight Recognition via Transformer-Based Video Classification","authors":"Jiakai Zhou;Jun Yang;Xiaoliang Wu;Wanlin Zhou;Yang Wang","doi":"10.1109/TITS.2024.3509394","DOIUrl":"https://doi.org/10.1109/TITS.2024.3509394","url":null,"abstract":"In autonomous driving, efficiently and accurately recognizing taillight states using dashcams is essential for interpreting other vehicles’ intentions. Recent video-based taillight recognition methods outperform earlier image-based approaches. However, they face challenges in efficiently integrating spatiotemporal information and managing high computational costs. In this paper, we introduce ETR, an accurate and efficient Transformer-based video classification model designed to enhance taillight recognition. Specifically, we first design a lightweight backbone to extract temporal and spatial features from videos and generate queries with prior information. Next, we develop a hierarchical progressive Transformer decoder that integrates feature maps from different levels of the backbone to enhance the model’s global information. Finally, we employ a classification head to predict the taillight state of the video. Additionally, we introduce a public dataset, ETR-Taillights, to address the current lack of open datasets for vehicle taillight recognition. The dataset contains 28,799 dashcam video clips, making it the largest public taillight recognition dataset. Experiments show that our method achieves a 91.69% F-measure on the ETR-Taillights dataset, surpassing the latest taillight recognition methods, VIF by 6.94% and CNN-LSTM by 10.82%. Additionally, it achieves an inference speed of 45.06 FPS, being 3.6 times faster than VIF. Furthermore, we conduct real-world road tests to demonstrate our method’s robustness and effectiveness in practical scenarios. Our model and dataset are available at <uri>https://github.com/yang590/vehicle-taillight</uri>.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"2721-2733"},"PeriodicalIF":7.9,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183931","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 : 2024-12-11DOI: 10.1109/TITS.2024.3510584
Yunfan Huang;Maode Ma
Vehicular Ad Hoc Networks (VANETs) play a critical role in enabling communication among intelligent vehicles, yet their dynamic and decentralized nature makes them highly vulnerable to cyber-attacks. Traditional Intrusion Detection Systems (IDSs) provide limited defense against these evolving threats, as they rely on static rules or machine learning (ML) models that lack the capacity for real-time updates. The Incremental Lifetime Learning IDS (ILL-IDS) was introduced to address this limitation by enabling adaptive learning of new attack types. However, ILL-IDS depends heavily on large volumes of high-quality labeled data, making the model update process costly and labor-intensive. In response, this study proposes the Automatic Incremental Lifetime Learning IDS (AILL-IDS), a novel IDS framework that significantly reduces the need for labeled data through incremental semi-supervised learning. This approach not only enables AILL-IDS to detect unknown attacks and adapt its model dynamically with minimal labeled data but also ensures continuous detection during the model update process, enhancing both speed and accuracy in threat detection. Experimental results demonstrate that AILL-IDS achieves a high detection rate of 0.97 and an average F1 score of 0.90, using only 5.5% labeled data, thereby offering an efficient and scalable solution for securing VANETs against emerging cyber threats.
{"title":"AILL-IDS: An Automatic Incremental Lifetime Learning Intrusion Detection System for Vehicular Ad Hoc Networks","authors":"Yunfan Huang;Maode Ma","doi":"10.1109/TITS.2024.3510584","DOIUrl":"https://doi.org/10.1109/TITS.2024.3510584","url":null,"abstract":"Vehicular Ad Hoc Networks (VANETs) play a critical role in enabling communication among intelligent vehicles, yet their dynamic and decentralized nature makes them highly vulnerable to cyber-attacks. Traditional Intrusion Detection Systems (IDSs) provide limited defense against these evolving threats, as they rely on static rules or machine learning (ML) models that lack the capacity for real-time updates. The Incremental Lifetime Learning IDS (ILL-IDS) was introduced to address this limitation by enabling adaptive learning of new attack types. However, ILL-IDS depends heavily on large volumes of high-quality labeled data, making the model update process costly and labor-intensive. In response, this study proposes the Automatic Incremental Lifetime Learning IDS (AILL-IDS), a novel IDS framework that significantly reduces the need for labeled data through incremental semi-supervised learning. This approach not only enables AILL-IDS to detect unknown attacks and adapt its model dynamically with minimal labeled data but also ensures continuous detection during the model update process, enhancing both speed and accuracy in threat detection. Experimental results demonstrate that AILL-IDS achieves a high detection rate of 0.97 and an average F1 score of 0.90, using only 5.5% labeled data, thereby offering an efficient and scalable solution for securing VANETs against emerging cyber threats.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"2669-2678"},"PeriodicalIF":7.9,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106239","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 : 2024-12-11DOI: 10.1109/TITS.2024.3509339
Asma Hamissi;Amine Dhraief;Layth Sliman
The anticipated proliferation of Unmanned Aerial Vehicles (UAVs) in the airspace in the coming years has raised concerns about how to manage their flights to avoid collisions and crashes at various stages of flight. To this end, many Unmanned Aircraft Traffic Management systems (UTM) have been designed. These systems use various methods for managing UAV conflicts. Several surveys have reviewed conflict resolution methods for UAVs. However, to the best of our knowledge, there is no survey specifically addressing conflict detection and resolution methods in UTM, particularly those using AI-based methods. Therefore, this article serves as a comprehensive survey of all UAVs conflicts detection and resolution methods proposed in the literature and their use in the UTM systems. This survey classifies the methods into two categories: classical (non-learning) methods and learning-based methods. Classical methods typically rely on pre-defined algorithms or rules for UAVs to avoid collisions, whereas Artificial Intelligence-based methods, including Machine Learning (ML) and especially Reinforcement Learning (RL), enable UAVs to adapt to their environment, autonomously resolve conflicts, and exhibit intelligent behavior based on their experiences. It also presents their application in the conflict resolution service for UTMs. Additionally, the challenges and issues associated with each type of methods are discussed. This article can serve as a foundational resource for researchers in guiding their selection of methods for conflict resolution, particularly those relevant to UTM systems.
{"title":"A Comprehensive Survey on Conflict Detection and Resolution in Unmanned Aircraft System Traffic Management","authors":"Asma Hamissi;Amine Dhraief;Layth Sliman","doi":"10.1109/TITS.2024.3509339","DOIUrl":"https://doi.org/10.1109/TITS.2024.3509339","url":null,"abstract":"The anticipated proliferation of Unmanned Aerial Vehicles (UAVs) in the airspace in the coming years has raised concerns about how to manage their flights to avoid collisions and crashes at various stages of flight. To this end, many Unmanned Aircraft Traffic Management systems (UTM) have been designed. These systems use various methods for managing UAV conflicts. Several surveys have reviewed conflict resolution methods for UAVs. However, to the best of our knowledge, there is no survey specifically addressing conflict detection and resolution methods in UTM, particularly those using AI-based methods. Therefore, this article serves as a comprehensive survey of all UAVs conflicts detection and resolution methods proposed in the literature and their use in the UTM systems. This survey classifies the methods into two categories: classical (non-learning) methods and learning-based methods. Classical methods typically rely on pre-defined algorithms or rules for UAVs to avoid collisions, whereas Artificial Intelligence-based methods, including Machine Learning (ML) and especially Reinforcement Learning (RL), enable UAVs to adapt to their environment, autonomously resolve conflicts, and exhibit intelligent behavior based on their experiences. It also presents their application in the conflict resolution service for UTMs. Additionally, the challenges and issues associated with each type of methods are discussed. This article can serve as a foundational resource for researchers in guiding their selection of methods for conflict resolution, particularly those relevant to UTM systems.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"1395-1418"},"PeriodicalIF":7.9,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183821","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}
Trajectory similarity is a fundamental operation in spatial-temporal data mining with wide-ranging applications. However, trajectories inherently exhibit diversity due to varied sampling and distribution of trajectory points, influenced by different motion patterns, sampling methods, and route constraints. This diversity leads to varying results in trajectory similarity measures, including DTW, LCSS, ED, Hausdorff, EDR, etc. In this paper, we argue for a comprehensive consideration of various distance metrics to enhance accuracy. To address this, this paper proposes a Multi-source Deep Trajectory Representation Learning method for accurate and efficient similarity queries. In particular, MDTRL comprises two key modules: (1) A novel trajectory representation module that incorporates an attention-based embedding mechanism and a deep metric learning network aggregating multiple measures. (2) A continuous metric learning strategy that adaptively updates similarity, thereby enhancing the accuracy of similarity queries. We employ the locality sensitive hashing index to further improve the similarity query. Extensive experiments conducted on real trajectory datasets reveal that MDTRL has state-of-the-art solutions, in terms of both effectiveness and efficiency across multi-source trajectories. It achieves 5x-15x speedup and 10%-15% accuracy improvement over Euclidean, Hausdorff, DTW, and Discrete Fréchet measures.
{"title":"MDTRL: A Multi-Source Deep Trajectory Representation Learning for the Accurate and Fast Similarity Query","authors":"Junhua Fang;Chunhui Feng;Pingfu Chao;Jiajie Xu;Pengpeng Zhao;Lei Zhao","doi":"10.1109/TITS.2024.3510534","DOIUrl":"https://doi.org/10.1109/TITS.2024.3510534","url":null,"abstract":"Trajectory similarity is a fundamental operation in spatial-temporal data mining with wide-ranging applications. However, trajectories inherently exhibit diversity due to varied sampling and distribution of trajectory points, influenced by different motion patterns, sampling methods, and route constraints. This diversity leads to varying results in trajectory similarity measures, including DTW, LCSS, ED, Hausdorff, EDR, etc. In this paper, we argue for a comprehensive consideration of various distance metrics to enhance accuracy. To address this, this paper proposes a Multi-source Deep Trajectory Representation Learning method for accurate and efficient similarity queries. In particular, MDTRL comprises two key modules: (1) A novel trajectory representation module that incorporates an attention-based embedding mechanism and a deep metric learning network aggregating multiple measures. (2) A continuous metric learning strategy that adaptively updates similarity, thereby enhancing the accuracy of similarity queries. We employ the locality sensitive hashing index to further improve the similarity query. Extensive experiments conducted on real trajectory datasets reveal that MDTRL has state-of-the-art solutions, in terms of both effectiveness and efficiency across multi-source trajectories. It achieves 5x-15x speedup and 10%-15% accuracy improvement over Euclidean, Hausdorff, DTW, and Discrete Fréchet measures.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"2115-2128"},"PeriodicalIF":7.9,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183813","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 : 2024-12-11DOI: 10.1109/TITS.2024.3510853
Zheng Fu;Kun Jiang;Yuhang Xu;Yunlong Wang;Tuopu Wen;Hao Gao;Zhihua Zhong;Diange Yang
Despite the remarkable advancements in autonomous driving, the challenge persists in achieving interpretable action decision-making, primarily owing to the intricate and ambiguous relationship between detected agents and driving intention. In this study, we introduce an interpretable action prediction model, denoted as the Prediction-Driven Attention Network (PDANet), designed to undertake action decisions and provide corresponding interpretations cohesively. The PDANet is inspired by the perceptual mechanisms inherent in human drivers, who allocate attention according to their driving intentions. Specifically, we elaborate a prediction module to generate vehicle prospective trajectories to characterize driving intentions. Subsequently, the features of this predicted trajectory are utilized to modulate the attention distribution among agents through the top-down attention module, yielding an attention map. Finally, two distinct task tokens are applied to aggregate agent features and generate the final output according to the derived attention map. Extensive experiments conducted on the publicly available BDD-OIA and nu-AR datasets demonstrate that our proposed method outperforms all prior works in terms of both action prediction and behavior interpretation tasks. Remarkably, our method attains a noteworthy enhancement in the behavior interpretation task, surpassing the previous state-of-the-art by a substantial margin of +10.8% in terms of F1-score on the nu-AR dataset. We also validate our algorithm on Carla Town05 long in a closed-loop decision-making scenario, highlighting the generality and robustness of our approach. Furthermore, qualitative results show that the agents selected by our model are more closely aligned with human cognitive processes.
{"title":"Top-Down Attention-Based Mechanisms for Interpretable Autonomous Driving","authors":"Zheng Fu;Kun Jiang;Yuhang Xu;Yunlong Wang;Tuopu Wen;Hao Gao;Zhihua Zhong;Diange Yang","doi":"10.1109/TITS.2024.3510853","DOIUrl":"https://doi.org/10.1109/TITS.2024.3510853","url":null,"abstract":"Despite the remarkable advancements in autonomous driving, the challenge persists in achieving interpretable action decision-making, primarily owing to the intricate and ambiguous relationship between detected agents and driving intention. In this study, we introduce an interpretable action prediction model, denoted as the Prediction-Driven Attention Network (PDANet), designed to undertake action decisions and provide corresponding interpretations cohesively. The PDANet is inspired by the perceptual mechanisms inherent in human drivers, who allocate attention according to their driving intentions. Specifically, we elaborate a prediction module to generate vehicle prospective trajectories to characterize driving intentions. Subsequently, the features of this predicted trajectory are utilized to modulate the attention distribution among agents through the top-down attention module, yielding an attention map. Finally, two distinct task tokens are applied to aggregate agent features and generate the final output according to the derived attention map. Extensive experiments conducted on the publicly available BDD-OIA and nu-AR datasets demonstrate that our proposed method outperforms all prior works in terms of both action prediction and behavior interpretation tasks. Remarkably, our method attains a noteworthy enhancement in the behavior interpretation task, surpassing the previous state-of-the-art by a substantial margin of +10.8% in terms of F1-score on the nu-AR dataset. We also validate our algorithm on Carla Town05 long in a closed-loop decision-making scenario, highlighting the generality and robustness of our approach. Furthermore, qualitative results show that the agents selected by our model are more closely aligned with human cognitive processes.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"2212-2226"},"PeriodicalIF":7.9,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183961","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 this study, we address the challenge of traversability analysis for autonomous vehicles in diverse environments, leveraging LiDAR sensors. We propose the Transformer-Voxel-Bird’s eye view (BEV) Network (TVBNet), a novel dual-branch framework designed to increase the accuracy and versatility of such analyses in both urban and off-road conditions. TVBNet first preprocesses raw point cloud data through voxelization and the generation of a BEV. It incorporates a Transformer network with a rotational attention mechanism to aggregate features from multiple point cloud frames, capturing long-range correlations both within and between point clouds. Additionally, a Swin Transformer extracts the relative positional relationships in the BEV projection, facilitating a comprehensive understanding of the scene. The fusion of data from both branches via a multisource feature fusion module, which employs a context aggregation mechanism based on a residual structure, allows for robust local to global contextual understanding. This approach not only improves the extraction of correlation features between 2D BEV and 3D voxel data but also demonstrates superior performance on the challenging off-road dataset RELLIS-3D and the urban dataset SemanticKITTI.
{"title":"Dual-Branch Transformer Network for Enhancing LiDAR-Based Traversability Analysis in Autonomous Vehicles","authors":"Shiliang Shao;Xianyu Shi;Guangjie Han;Ting Wang;Chunhe Song;Qi Zhang","doi":"10.1109/TITS.2024.3508839","DOIUrl":"https://doi.org/10.1109/TITS.2024.3508839","url":null,"abstract":"In this study, we address the challenge of traversability analysis for autonomous vehicles in diverse environments, leveraging LiDAR sensors. We propose the Transformer-Voxel-Bird’s eye view (BEV) Network (TVBNet), a novel dual-branch framework designed to increase the accuracy and versatility of such analyses in both urban and off-road conditions. TVBNet first preprocesses raw point cloud data through voxelization and the generation of a BEV. It incorporates a Transformer network with a rotational attention mechanism to aggregate features from multiple point cloud frames, capturing long-range correlations both within and between point clouds. Additionally, a Swin Transformer extracts the relative positional relationships in the BEV projection, facilitating a comprehensive understanding of the scene. The fusion of data from both branches via a multisource feature fusion module, which employs a context aggregation mechanism based on a residual structure, allows for robust local to global contextual understanding. This approach not only improves the extraction of correlation features between 2D BEV and 3D voxel data but also demonstrates superior performance on the challenging off-road dataset RELLIS-3D and the urban dataset SemanticKITTI.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"2582-2595"},"PeriodicalIF":7.9,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106296","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 : 2024-12-11DOI: 10.1109/TITS.2024.3510582
Mingu Jeon;Jae-Kyung Cho;Hee-Yeun Kim;Byeonggyu Park;Seung-Woo Seo;Seong-Woo Kim
Sound can be utilized to gather information about vehicles approaching a Non-Line-of-Sight (NLoS) region that remains hidden from Line-of-Sight (LoS) sensors due to its reflective and diffractive characteristics, like a radar. However, due to the inability to determine the location of NLoS vehicles in previous studies, it has not been possible to construct a sound-based active emergency braking system. This paper introduces a novel approach for localization of vehicles approaching in NLoS regions through sound. Specifically, a new particle filter method incorporating Acoustic-Spatial Pseudo-Likelihood (ASPLE) has been proposed to track objects using both acoustic and spatial information from the ego vehicle. Also, the Acoustic Recognition based Invisible-target Localization (ARIL) dataset, which is the firstly providing the location of the NLoS vehicle as ground truth using Bird’s Eye View camera, is proposed. The proposed method is validated using two datasets: the ARIL dataset and the Occluded Vehicle Acoustic Detection Dataset (OVAD) dataset. The proposed method exhibited remarkable performance in localizing NLoS targets in both datasets, predicting the location of the vehicle in the NLoS region. Lastly, the analysis of how the reflection of sound affects to the proposed method, highlighting variations based on the spatial situations, and demonstrate the empirical convergence of the method is described. Our code and dataset is available at https://github.com/mingujeon/NLoSVehicleLocalization.
{"title":"Non-Line-of-Sight Vehicle Localization Based on Sound","authors":"Mingu Jeon;Jae-Kyung Cho;Hee-Yeun Kim;Byeonggyu Park;Seung-Woo Seo;Seong-Woo Kim","doi":"10.1109/TITS.2024.3510582","DOIUrl":"https://doi.org/10.1109/TITS.2024.3510582","url":null,"abstract":"Sound can be utilized to gather information about vehicles approaching a Non-Line-of-Sight (NLoS) region that remains hidden from Line-of-Sight (LoS) sensors due to its reflective and diffractive characteristics, like a radar. However, due to the inability to determine the location of NLoS vehicles in previous studies, it has not been possible to construct a sound-based active emergency braking system. This paper introduces a novel approach for localization of vehicles approaching in NLoS regions through sound. Specifically, a new particle filter method incorporating Acoustic-Spatial Pseudo-Likelihood (ASPLE) has been proposed to track objects using both acoustic and spatial information from the ego vehicle. Also, the Acoustic Recognition based Invisible-target Localization (ARIL) dataset, which is the firstly providing the location of the NLoS vehicle as ground truth using Bird’s Eye View camera, is proposed. The proposed method is validated using two datasets: the ARIL dataset and the Occluded Vehicle Acoustic Detection Dataset (OVAD) dataset. The proposed method exhibited remarkable performance in localizing NLoS targets in both datasets, predicting the location of the vehicle in the NLoS region. Lastly, the analysis of how the reflection of sound affects to the proposed method, highlighting variations based on the spatial situations, and demonstrate the empirical convergence of the method is described. Our code and dataset is available at <uri>https://github.com/mingujeon/NLoSVehicleLocalization</uri>.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"2321-2338"},"PeriodicalIF":7.9,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143184101","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 : 2024-12-11DOI: 10.1109/TITS.2024.3508841
Shida Nie;Yujia Xie;Congshuai Guo;Hui Liu;Fawang Zhang;Rui Liu
Off-road environments with varied terrain and obstacle types present substantial challenges to the safe maneuvering of unmanned ground vehicles (UGVs). This study addresses the need for personalized path planning by introducing a multi-source off-road potential field (MOPF) method that quantifies risk and impediments in off-road settings based on internal and external characteristics. Specifically, Vehicle capability boundaries are defined by longitudinal dynamics analysis of the ego-vehicle to prevent instability due to insufficient driving force and limited adhesion conditions. A novel Non-Uniform Safety Margin Expression (NSME) is proposed to adjust the MOPF, allowing it to consider the vehicle’s state to enhance travel efficiency and minimize detours. The MOPF can be adapted according to the characteristics of the ego vehicle, drivers, and cargo. To incorporate driving styles, the Driving Style Probabilistic Roadmap (DSPRM) algorithm is developed, leading to smoother and more personalized paths. Comparative tests demonstrate that our method enables personalized path planning, achieving an average reduction of 10.29% in path length and 30.83% in path slope compared to traditional planning methods, while maintaining a safe distance from obstacles.
{"title":"Personalized Off-Road Path Planning Based on Internal and External Characteristics for Obstacle Avoidance","authors":"Shida Nie;Yujia Xie;Congshuai Guo;Hui Liu;Fawang Zhang;Rui Liu","doi":"10.1109/TITS.2024.3508841","DOIUrl":"https://doi.org/10.1109/TITS.2024.3508841","url":null,"abstract":"Off-road environments with varied terrain and obstacle types present substantial challenges to the safe maneuvering of unmanned ground vehicles (UGVs). This study addresses the need for personalized path planning by introducing a multi-source off-road potential field (MOPF) method that quantifies risk and impediments in off-road settings based on internal and external characteristics. Specifically, Vehicle capability boundaries are defined by longitudinal dynamics analysis of the ego-vehicle to prevent instability due to insufficient driving force and limited adhesion conditions. A novel Non-Uniform Safety Margin Expression (NSME) is proposed to adjust the MOPF, allowing it to consider the vehicle’s state to enhance travel efficiency and minimize detours. The MOPF can be adapted according to the characteristics of the ego vehicle, drivers, and cargo. To incorporate driving styles, the Driving Style Probabilistic Roadmap (DSPRM) algorithm is developed, leading to smoother and more personalized paths. Comparative tests demonstrate that our method enables personalized path planning, achieving an average reduction of 10.29% in path length and 30.83% in path slope compared to traditional planning methods, while maintaining a safe distance from obstacles.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 2","pages":"2397-2409"},"PeriodicalIF":7.9,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106273","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：