IEEE Transactions on Intelligent Vehicles最新文献_第4页

Extremum Seeking-Based Braking Friction Force Maximization Algorithm Using Fuzzy Logic Without Slip Ratio for ABSs 基于极值搜索的制动摩擦力最大化算法（使用模糊逻辑），不含防抱死制动系统的滑动比

IF 14 1区工程技术

IEEE Transactions on Intelligent Vehicles Pub Date : 2024-07-18 DOI: 10.1109/TIV.2024.3430816

Jinwoo Ha;Sesun You;Young-jin Ko;Wonhee Kim

{"title":"Extremum Seeking-Based Braking Friction Force Maximization Algorithm Using Fuzzy Logic Without Slip Ratio for ABSs","authors":"Jinwoo Ha;Sesun You;Young-jin Ko;Wonhee Kim","doi":"10.1109/TIV.2024.3430816","DOIUrl":"https://doi.org/10.1109/TIV.2024.3430816","url":null,"abstract":"In this paper, we propose an extremum seeking-based algorithm using fuzzy logic for maximizing the braking friction force in anti-lock brake systems (ABSs) without relying on vehicle speed information and slip ratio dynamics. Many current ABSs algorithms utilize slip ratio as a control parameter. If the slip ratio is inaccurately measured, the braking performance of the ABSs may not be optimal. To address this, we propose a method to achieve maximum friction force by designing a reference generator that generates the control inputs for the ABSs without requiring slip ratio information. We design an extended state observer that can estimate the braking friction force and braking friction coefficient. Based on the estimated friction force, the desired wheel cylinder pressure (WCP), which is the control input of the hydraulic brake system, is generated to converge to the maximum friction force using the extremum seeking control algorithm. To achieve improved braking performance, the initial desired WCP is calculated using fuzzy logic for quick convergence to the optimal region. The proposed method is experimentally validated using a hardware-in-the-loop simulation, which includes components such as MATLAB/Simulink, CarSim, SCALEXIO real-time system, and a hydraulic brake system.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 8","pages":"5272-5283"},"PeriodicalIF":14.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600239","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

RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation RoMe：通过网格表示实现大规模路面重建

IF 14 1区工程技术

IEEE Transactions on Intelligent Vehicles Pub Date : 2024-06-21 DOI: 10.1109/TIV.2024.3417512

Ruohong Mei;Wei Sui;Jiaxin Zhang;Xue Qin;Gang Wang;Tao Peng;Tao Chen;Cong Yang

{"title":"RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation","authors":"Ruohong Mei;Wei Sui;Jiaxin Zhang;Xue Qin;Gang Wang;Tao Peng;Tao Chen;Cong Yang","doi":"10.1109/TIV.2024.3417512","DOIUrl":"https://doi.org/10.1109/TIV.2024.3417512","url":null,"abstract":"In autonomous driving applications, accurate and efficient road surface reconstruction is paramount. This paper introduces RoMe, a novel framework designed for the robust reconstruction of large-scale road surfaces. Leveraging a unique mesh representation, RoMe ensures that the reconstructed road surfaces are accurate and seamlessly aligned with semantics. To address challenges in computational efficiency, we propose a waypoint sampling strategy, enabling RoMe to reconstruct vast environments by focusing on sub-areas and subsequently merging them. Furthermore, we incorporate an extrinsic optimization module to enhance the robustness against inaccuracies in extrinsic calibration. Our extensive evaluations of both public datasets and wild data underscore RoMe's superiority in terms of speed, accuracy, and robustness. For instance, it costs only 2 GPU hours to recover a road surface of \u0000<inline-formula><tex-math>$600times 600$</tex-math></inline-formula>\u0000 square meters from thousands of images. Notably, RoMe's capability extends beyond mere reconstruction, offering significant value for auto-labeling tasks in autonomous driving applications.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 7","pages":"5173-5185"},"PeriodicalIF":14.0,"publicationDate":"2024-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142320504","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

An Intelligent Sensor-Based Back Seat Monitoring System for Preventing Pediatric Vehicular Heatstroke 基于智能传感器的预防儿童车内中暑的后座监测系统

IF 14 1区工程技术

IEEE Transactions on Intelligent Vehicles Pub Date : 2024-06-04 DOI: 10.1109/TIV.2024.3408842

Leila Sharara;Klaus Thelen;Jonas Gillner;Jan Wolf;Hadi Syed;Hibah Syed;Roy Taylor;Laxmi Shankar;Matthias Berger;Daniel Forta;Sandro Rogowski;Ines Hornung;Lubna Alazzawi;Mohammed Ismail

{"title":"An Intelligent Sensor-Based Back Seat Monitoring System for Preventing Pediatric Vehicular Heatstroke","authors":"Leila Sharara;Klaus Thelen;Jonas Gillner;Jan Wolf;Hadi Syed;Hibah Syed;Roy Taylor;Laxmi Shankar;Matthias Berger;Daniel Forta;Sandro Rogowski;Ines Hornung;Lubna Alazzawi;Mohammed Ismail","doi":"10.1109/TIV.2024.3408842","DOIUrl":"https://doi.org/10.1109/TIV.2024.3408842","url":null,"abstract":"This research introduces an innovative automotive child back seat monitoring system aimed at preventing heatstroke incidents associated with leaving children unattended in vehicles. The device integrates sensors, wireless connectivity, and intelligent algorithms to detect and respond to potential risks. Internal sensors continuously monitor factors such as occupancy status, in-vehicle temperature, and the child's respiration rate in real-time. A hybrid approach is adopted for enhanced accuracy, utilizing Force Sensing Resistor (FSR) sensors for presence and breathing detection, along with motion sensors for movement tracking. Intelligent algorithms process the data to identify critical conditions and activate preventive measures. Data is transmitted through a mobile application for immediate alerts to caregivers. The system incorporates a Simplified Frequency Analysis (SFA) for rapid processing, surpassing conventional methods by up to 80 times faster on a low-cost Microcontroller (MC), which makes it ideal for real-time applications. Testing results confirm its high accuracy in real-time occupancy detection and breath monitoring, triggering alerts as needed. The proposed system meets rigorous automotive industry standards for temperature and power requirements, ensuring optimal functionality and energy efficiency in extreme environments. With a minimal standby current of 104 <inline-formula><tex-math>$mu$</tex-math></inline-formula>A and the ability to withstand temperatures from −40 <inline-formula><tex-math>$^{circ }$</tex-math></inline-formula>C to +85 <inline-formula><tex-math>$^{circ }$</tex-math></inline-formula>C, this technology has the potential to save lives and establish child heatstroke prevention as a standard vehicle feature.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 11","pages":"7176-7192"},"PeriodicalIF":14.0,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144511186","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

Dream to Drive With Predictive Individual World Model 梦想驾驶预测性个人世界模型

IF 14 1区工程技术

IEEE Transactions on Intelligent Vehicles Pub Date : 2024-06-04 DOI: 10.1109/TIV.2024.3408830

Yinfeng Gao;Qichao Zhang;Da-Wei Ding;Dongbin Zhao

{"title":"Dream to Drive With Predictive Individual World Model","authors":"Yinfeng Gao;Qichao Zhang;Da-Wei Ding;Dongbin Zhao","doi":"10.1109/TIV.2024.3408830","DOIUrl":"https://doi.org/10.1109/TIV.2024.3408830","url":null,"abstract":"It is still a challenging topic to make reactive driving behaviors in complex urban environments as road users' intentions are unknown. Model-based reinforcement learning (MBRL) offers great potential to learn a reactive policy by constructing a world model that can provide informative states and imagination training. However, a critical limitation in relevant research lies in the scene-level reconstruction representation learning, which may overlook key interactive vehicles and hardly model the interactive features among vehicles and their long-term intentions. Therefore, this paper presents a novel MBRL method with a predictive individual world model (PIWM) for autonomous driving. PIWM describes the driving environment from an individual-level perspective and captures vehicles' interactive relations and their intentions via trajectory prediction task. Meanwhile, a behavior policy is learned jointly with PIWM. It is trained in PIWM's imagination and effectively navigates in the urban driving scenes leveraging intention-aware latent states. The proposed method is trained and evaluated on simulation environments built upon real-world challenging interactive scenarios. Compared with popular model-free and state-of-the-art model-based reinforcement learning methods, experimental results show that the proposed method achieves the best performance in terms of safety and efficiency.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 12","pages":"8224-8238"},"PeriodicalIF":14.0,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144597947","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

Multiagent Reinforcement Learning: Methods, Trustworthiness, Applications in Intelligent Vehicles, and Challenges 多智能体强化学习：方法、可信度、在智能车辆中的应用和挑战

IF 14 1区工程技术

IEEE Transactions on Intelligent Vehicles Pub Date : 2024-06-03 DOI: 10.1109/TIV.2024.3408257

Ziyuan Zhou;Guanjun Liu;Ying Tang

引用次数: 0

An Universal Crack Detection Framework for Intelligent Road-Perceptive Vehicles 智能道路感知车辆通用裂纹检测框架

IF 14 1区工程技术

IEEE Transactions on Intelligent Vehicles Pub Date : 2024-06-03 DOI: 10.1109/TIV.2024.3408649

Senyun Kuang;Yang Liu;Xin Wang;Xiaobo Qu;Yintao Wei

{"title":"An Universal Crack Detection Framework for Intelligent Road-Perceptive Vehicles","authors":"Senyun Kuang;Yang Liu;Xin Wang;Xiaobo Qu;Yintao Wei","doi":"10.1109/TIV.2024.3408649","DOIUrl":"https://doi.org/10.1109/TIV.2024.3408649","url":null,"abstract":"Crack detection is essential for ensuring road safety and preserving the integrity of infrastructure. As intelligent transportation systems mature, vehicles equipped with crack detection capabilities have become more sophisticated. Traditional methods for detecting cracks have relied on designing complex networks, which can be time-consuming and may obscure the task's underlying simplicity, posing challenges for researchers and hindering integration into road-perceptive vehicles. This paper introduces an innovative, universal framework for crack detection that circumvents these issues by utilizing existing pre-trained segmentation methods with visual prompts. We introduce the visual crack prompt (VCP) mechanism, which refines the focus of pre-trained models on high-frequency features, significantly improving their ability to identify and segment specific crack features. Additionally, we present the diverse crack detection 1 K dataset (DCD1K), comprising 1000 images of 16 different crack types, to validate the VCP mechanism's effectiveness. Our experimental results showcase the framework's outstanding performance across six distinct datasets, highlighting its potential to revolutionize crack detection methods.","PeriodicalId":36532,"journal":{"name":"IEEE Transactions on Intelligent Vehicles","volume":"9 12","pages":"8212-8223"},"PeriodicalIF":14.0,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144597585","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

From RAG/RAT to SAGE for Social Transportation: A CoT and New Perspective on Smart Logistics and Mobility 从社会交通的 RAG/RAT 到 SAGE：智能物流和移动性的协同效应和新视角

IF 14 1区工程技术

IEEE Transactions on Intelligent Vehicles Pub Date : 2024-06-01 DOI: 10.1109/TIV.2024.3426992

Fei-Yue Wang

引用次数: 0

The Transactions on Intelligent Vehicles Information 智能车辆信息论文集

IF 14 1区工程技术

IEEE Transactions on Intelligent Vehicles Pub Date : 2024-06-01 DOI: 10.1109/TIV.2024.3430211

引用次数: 0

Enhancement Technology for Perception in Smart Mining Vehicles: 4D Millimeter-Wave Radar and Multi-Sensor Fusion 智能采矿车辆感知增强技术：4D 毫米波雷达和多传感器融合

IF 14 1区工程技术

IEEE Transactions on Intelligent Vehicles Pub Date : 2024-06-01 DOI: 10.1109/TIV.2024.3427718

Jianjian Yang;Tianmu Gui;Yuyuan Zhang;Shirong Ge;Qiankun Huang;Guanghui Zhao

引用次数: 0

IEEE Transactions on Intelligent Vehicles Publication Information 电气和电子工程师学会智能车辆论文集》出版信息

IF 14 1区工程技术

IEEE Transactions on Intelligent Vehicles Pub Date : 2024-06-01 DOI: 10.1109/TIV.2024.3430209

引用次数: 0