Listing 1 - 10 of 53 | << page >> |
Sort by
|
Choose an application
Path planning --- Interactif features --- Building design --- Object recognition --- Path planning --- Interactif features --- Building design --- Object recognition
Choose an application
Mobile robot motion planning in unstructured dynamic environments is a challenging task. Thus, often suboptimal methods are employed which perform global path planning and local obstacle avoidance separately. This work introduces a holistic planning algorithm which is based on the concept of state
obstacle avoidance --- Pfadplanung --- motion planning --- autonomes Fahren --- HindernisvermeidungMobile robots --- path planning --- Mobile Roboter --- Bewegungsplanung --- autonomous driving
Choose an application
Dans le domaine de la construction, il est important de pouvoir capturer la réalité de manière complète et précise. Avec le scanning laser, la photogrammétrie est la technologie la plus employée à cet effet. Elle vise à recréer un objet sous forme de nuage de point depuis des images prise autour de celui-ci. Cependant, les meilleures pratiques pour effectuer un relevé photogrammétrique sont parfois floues; et évaluer leurs impacts peut s'avérer laborieux. En effet, un nombre importants de facteurs viennent influencer la qualité finale d'une reconstruction, autant en termes de paramètres inhérents à l'appareil photo qu'en termes de positionnement et orientation des photos. L'utilisation de drones décuple encore ce phénomène en augmentant le nombre de positions et d'orientations de la caméra possibles. La campagne de relevé devient un processus long et la bonne qualité de la reconstruction finale n'est jamais assurée. Dans ce contexte, ce travail propose une méthode complètement virtuelle et automatisée permettant la comparaison de la qualité de reconstructions photogrammétriques en recréant une campagne de relevé directement dans le logiciel de photogrammétrie Metashape. La qualité s'entend en termes de fidélité géométrique, confiance et exhaustivité de la reconstruction. Elle permet de traiter chaque paramètre individuellement et évalue son impact de manière automatique et rapide. Le processus est ici illustré pour les conséquences de la prise d'image sur la qualité finale du relevé. Elle permet par exemple de mettre en évidence qu'une prise d'image circulaire est suffisante pour les relevés basse résolution d'objets relativement simples. Si une plus haute résolution est requise ou que l'objet à capturer est plus élaboré, il est alors préférable d'utiliser un planificateur de vol tridimensionnel. Les relevés nadir ne sont jamais à même de retranscrire correctement la géométrie de l'objet. Le processus, ici appliqué à la position et l'orientation des images, s'inscrit dans un contexte plus grand en fournissant une méthode innovante pour tester l'influence des paramètres utilisés sur un processus de reconstruction photogrammétrique. In the field of construction, it is important to be able to capture reality completely and accurately. Along with laser scanning, photogrammetry is the most used technology for this purpose. It aims to recreate an object as a point cloud from images taken around it. However, the best practises in photogrammetry are sometimes blurred, and evaluating their impact can be laborious. Indeed, a lot of important factors influence the final quality of a reconstruction, as much in terms of parameters inherent to the camera as in terms of positioning and orientation of the pictures. The use of drones increases this phenomenon by increasing the number of possible positions and orientations. The survey campaign becomes a long process and the good quality of the final reconstruction is never assured. Facing this issue, this work proposes a completely virtual and automated method of comparison of photogrammetric reconstruction by recreating a survey campaign directly in the photogrammetry software Metashape. It allows to treat each parameter individually and to evaluate its impact in an automatic and fast way. The process is illustrated here on the consequences of the image capture scenario on the final quality of the survey. It shows that a circular image capture is sufficient for low resolution surveys of relatively simple objects. If a higher resolution is required or if the object to be captured is more elaborate, it is then preferable to use a three-dimensional flight planner. Nadir surveys are never able to correctly capture the geometry of the object. The process, applied here to the position and orientation of images, is part of a larger context by providing a new method to test the influence of the parameters of a photogrammetric reconstruction process.
Choose an application
The Cooperative Control of Multiagent Systems course will illustrate the various attributes needed in such systems and the complexity inherent to the design. Cooperative systems are currently limited in capacity and in availability, partly due to this so-called complexity and to the multifaceted nature of design and analysis. This course will focus on the well-known problem of multiagent path planning, with brief discussions of advanced techniques for formation flight health management. The optimization problem and its solution will be cast in the framework of dynamic programming and Markov decision processes, typical of problems of optimization under uncertainty. A discussion of the results of numerical simulations, integrating decision-making with closed-loop dynamics of the air vehicles, for both formation flight and path planning, will conclude the course.
Renewable energy sources --- Electric power systems --- Electric power --- Mechanical Engineering --- Engineering & Applied Sciences --- Mechanical Engineering - General --- Technological innovations --- Conservation --- Power systems, Electric --- Systems, Electric power --- Alternate energy sources --- Alternative energy sources --- Energy sources, Renewable --- Sustainable energy sources --- Electric power production --- Power resources --- Renewable natural resources --- Agriculture and energy --- Complexity theory. --- Unmanned aerial vehicles. --- Path planning. --- Markov processes. --- Dynamic programming. --- Cooperative systems.
Choose an application
Miniaturization of electronic devices and recent developments in wireless communication technology are leading to the creation of a range of personal information appliances, or biotic sensors, which can be attached to or implanted in human bodies. The wireless networking of such devices is known as the wireless body area network (BAN). BAN can share information effectively and securely, reduce functional redundancies, and allow new conveniences and services. Moreover, it provides new possibilities for high-quality service from hospitals, by linking various biotic sensors to establish a body-area network of personal health information. In Body Area Communications: Channel Modeling, Communication Systems, and EMC, Wang and Wang provide a systematic introduction to body area networks leading readers from an introductory level to in-depth and more advanced topics. . Provides a concise introduction to this emerging topic based on classroom-tested materials. Details the latest IEEE 802.15.6 standard activities. Moves from very basic physics, to useful mathematic models, and then to practical considerations. Covers not only EM physics and communications, but also biological applications. Topics approached include: link budget, bit error rate performance, RAKE and diversity reception; SAR analysis for human safety evaluation; and modeling of electromagnetic interference to implanted cardiac pacemakers . Provides Matlab and Fortran programs for download from the Companion WebsiteThis book is ideal for graduate students, engineers and researchers interested in body area networks, or those who would like to apply expertise in signal processing, application development and implementation, IC design, instrumentation, software framework, hardware/software optimization, distributed processing, and communications to BAN applications. Researchers and practicing engineers in biomedical engineering, who are interested in extending techniques to the wireless communications space, will also find this book to be a helpful reference.
Body area networks (Electronics) --- Medical telematics. --- Body area networks (Electronics) --- Medical telematics. --- Electronic books. --- Amplitude shift keying --- Artificial intelligence --- Bit error rate --- Blood pressure --- Body area networks --- Channel models --- Communication systems --- Conductivity --- Demodulation --- Electrocardiography --- Electromagnetic compatibility --- Electromagnets --- Equations --- Error statistics --- Fading --- Finite element methods --- Human factors --- Impulse response --- Loss measurement --- Microwave integrated circuits --- Path planning --- Propagation losses --- Time domain analysis --- Transmitters --- Ultra wideband technology --- Body area networks (Electronics) --- Medical telematics. --- Electronic books. --- Amplitude shift keying --- Artificial intelligence --- Bit error rate --- Blood pressure --- Body area networks --- Channel models --- Communication systems --- Conductivity --- Demodulation --- Electrocardiography --- Electromagnetic compatibility --- Electromagnets --- Equations --- Error statistics --- Fading --- Finite element methods --- Human factors --- Impulse response --- Loss measurement --- Microwave integrated circuits --- Path planning --- Propagation losses --- Time domain analysis --- Transmitters --- Ultra wideband technology
Choose an application
This book contains the latest research on machine learning and embedded computing in advanced driver assistance systems (ADAS). It encompasses research in detection, tracking, LiDAR
n/a --- FPGA --- recurrence plot (RP) --- residual learning --- neural networks --- driver monitoring --- navigation --- depthwise separable convolution --- optimization --- dynamic path-planning algorithms --- object tracking --- sub-region --- cooperative systems --- convolutional neural networks --- DSRC --- VANET --- joystick --- road scene --- convolutional neural network (CNN) --- multi-sensor --- p-norm --- occlusion --- crash injury severity prediction --- deep leaning --- squeeze-and-excitation --- electric vehicles --- perception in challenging conditions --- T-S fuzzy neural network --- total vehicle mass of the front vehicle --- electrocardiogram (ECG) --- communications --- generative adversarial nets --- camera --- adaptive classifier updating --- Vehicle-to-X communications --- convolutional neural network --- predictive --- Geobroadcast --- infinity norm --- urban object detector --- machine learning --- automated-manual transition --- red light-running behaviors --- photoplethysmogram (PPG) --- panoramic image dataset --- parallel architectures --- visual tracking --- autopilot --- ADAS --- kinematic control --- GPU --- road lane detection --- obstacle detection and classification --- Gabor convolution kernel --- autonomous vehicle --- Intelligent Transport Systems --- driving decision-making model --- Gaussian kernel --- autonomous vehicles --- enhanced learning --- ethical and legal factors --- kernel based MIL algorithm --- image inpainting --- fusion --- terrestrial vehicle --- driverless --- drowsiness detection --- map generation --- object detection --- interface --- machine vision --- driving assistance --- blind spot detection --- deep learning --- relative speed --- autonomous driving assistance system --- discriminative correlation filter bank --- recurrent neural network --- emergency decisions --- LiDAR --- real-time object detection --- vehicle dynamics --- path planning --- actuation systems --- maneuver algorithm --- autonomous driving --- smart band --- the emergency situations --- two-wheeled --- support vector machine model --- global region --- biological vision --- automated driving
Choose an application
The advent of Internet of Things offers a scalable and seamless connection of physical objects, including human beings and devices. This, along with artificial intelligence, has moved transportation towards becoming intelligent transportation. This book is a collection of eleven articles that have served as examples of the success of internet of things and artificial intelligence deployment in transportation research. Topics include collision avoidance for surface ships, indoor localization, vehicle authentication, traffic signal control, path-planning of unmanned ships, driver drowsiness and stress detection, vehicle density estimation, maritime vessel flow forecast, and vehicle license plate recognition. High-performance computing services have become more affordable in recent years, which triggered the adoption of deep-learning-based approaches to increase the performance standards of artificial intelligence models. Nevertheless, it has been pointed out by various researchers that traditional shallow-learning-based approaches usually have an advantage in applications with small datasets. The book can provide information to government officials, researchers, and practitioners. In each article, the authors have summarized the limitations of existing works and offered valuable information on future research directions.
History of engineering & technology --- decision-making --- autonomous navigation --- collision avoidance --- scene division --- deep reinforcement learning --- maritime autonomous surface ships --- internet of things --- crowdsourcing --- indoor localization --- data fusion --- security --- authentication --- Inertial Measurement Units --- road transportation --- traffic signal control --- speed guidance --- vehicle arrival time --- connected vehicle --- unmanned ships --- DDPG --- autonomous path planning --- end-to-end --- at-risk driving --- deep support vector machine --- driver drowsiness --- driver stress --- multi-objective genetic algorithm --- multiple kernel learning --- urban freeway --- hybrid dynamic system --- state transition --- unknown inputs observer --- vehicle density --- maritime vessel flows --- intelligent transportation systems --- deep learning --- automatic license plate recognition --- intelligent vehicle access --- histogram of oriented gradients --- artificial neural networks --- convolutional neural networks --- time-frequency --- Inertial Measurement Unit (IMU) --- road anomalies --- decision-making --- autonomous navigation --- collision avoidance --- scene division --- deep reinforcement learning --- maritime autonomous surface ships --- internet of things --- crowdsourcing --- indoor localization --- data fusion --- security --- authentication --- Inertial Measurement Units --- road transportation --- traffic signal control --- speed guidance --- vehicle arrival time --- connected vehicle --- unmanned ships --- DDPG --- autonomous path planning --- end-to-end --- at-risk driving --- deep support vector machine --- driver drowsiness --- driver stress --- multi-objective genetic algorithm --- multiple kernel learning --- urban freeway --- hybrid dynamic system --- state transition --- unknown inputs observer --- vehicle density --- maritime vessel flows --- intelligent transportation systems --- deep learning --- automatic license plate recognition --- intelligent vehicle access --- histogram of oriented gradients --- artificial neural networks --- convolutional neural networks --- time-frequency --- Inertial Measurement Unit (IMU) --- road anomalies
Choose an application
This book presents the results of the successful Sensors Special Issue on Intelligent Vehicles that received submissions between March 2019 and May 2020. The Guest Editors of this Special Issue are Dr. David Fernández-Llorca, Dr. Ignacio Parra-Alonso, Dr. Iván García-Daza and Dr. Noelia Parra-Alonso, all from the Computer Engineering Department at the University of Alcalá (Madrid, Spain). A total of 32 manuscripts were finally accepted between 2019 and 2020, presented by top researchers from all over the world. The reader will find a well-representative set of current research and developments related to sensors and sensing for intelligent vehicles. The topics of the published manuscripts can be grouped into seven main categories: (1) assistance systems and automatic vehicle operation, (2) vehicle positioning and localization, (3) fault diagnosis and fail-x systems, (4) perception and scene understanding, (5) smart regenerative braking systems for electric vehicles, (6) driver behavior modeling and (7) intelligent sensing. We, the Guest Editors, hope that the readers will find this book to contain interesting papers for their research, papers that they will enjoy reading as much as we have enjoyed organizing this Special Issue
History of engineering & technology --- tracking-by-detection --- multi-vehicle tracking --- Siamese network --- data association --- Markov decision process --- driving behavior --- real-time monitoring --- driver distraction --- mobile application --- portable system --- simulation test --- dynamic driving behavior --- traffic scene augmentation --- corridor model --- IMU --- vision --- classification networks --- Hough transform --- lane markings detection --- semantic segmentation --- transfer learning --- autonomous --- off-road driving --- tire-road forces estimation --- slip angle estimation --- gauge sensors --- fuzzy logic system --- load transfer estimation --- simulation results --- normalization --- lateral force empirical model --- driver monitor --- lane departure --- statistical process control --- fault detection --- sensor fault --- signal restoration --- intelligent vehicle --- autonomous vehicle --- kinematic model --- visual SLAM --- sparse direct method --- photometric calibration --- corner detection and filtering --- loop closure detection --- road friction coefficient --- tire model --- nonlinear observer --- self-aligning torque --- lateral displacement --- Lyapunov method --- automatic parking system (APS) --- end-to-end parking --- reinforcement learning --- parking slot tracking --- deceleration planning --- multi-layer perceptron --- smart regenerative braking --- electric vehicles --- vehicle speed prediction --- driver behavior modeling --- electric vehicle control --- driver characteristics online learning --- objects’ edge detection --- stixel histograms accumulate --- point cloud segmentation --- autonomous vehicles --- scene understanding --- occlusion reasoning --- road detection --- advanced driver assistance system --- trajectory prediction --- risk assessment --- collision warning --- connected vehicles --- vehicular communications --- vulnerable road users --- fail-operational systems --- fall-back strategy --- automated driving --- advanced driving assistance systems --- illumination --- shadow detection --- shadow edge --- image processing --- traffic light detection --- intelligent transportation system --- lane-changing --- merging maneuvers --- game theory --- decision-making --- intelligent vehicles --- model predictive controller --- automatic train operation --- softness factor --- fusion velocity --- online obtaining --- hardware-in-the-loop simulation --- driving assistant --- driving diagnosis --- accident risk maps --- driving safety --- intelligent driving --- virtual test environment --- millimeter wave radar --- lane-change decision --- risk perception --- mixed traffic --- minimum safe deceleration --- automated driving system (ADS) --- sensor fusion --- multi-lane detection --- particle filter --- self-driving car --- unscented Kalman filter --- vehicle model --- Monte Carlo localization --- millimeter-wave radar --- square-root cubature Kalman filter --- Sage-Husa algorithm --- target tracking --- stationary and moving object classification --- localization --- LiDAR --- GNSS --- Global Positioning System (GPS) --- monte carlo --- autonomous driving --- robot motion --- path planning --- piecewise linear approximation --- multiple-target path planning --- autonomous mobile robot --- homotopy based path planning --- LiDAR signal processing --- sensor and information fusion --- advanced driver assistance systems --- autonomous racing --- high-speed camera --- real-time systems --- LiDAR odometry --- fail-aware --- sensors --- sensing --- percepction --- object detection and tracking --- scene segmentation --- vehicle positioning --- fail-x systems --- driver behavior modelling --- automatic operation
Choose an application
This book presents the results of the successful Sensors Special Issue on Intelligent Vehicles that received submissions between March 2019 and May 2020. The Guest Editors of this Special Issue are Dr. David Fernández-Llorca, Dr. Ignacio Parra-Alonso, Dr. Iván García-Daza and Dr. Noelia Parra-Alonso, all from the Computer Engineering Department at the University of Alcalá (Madrid, Spain). A total of 32 manuscripts were finally accepted between 2019 and 2020, presented by top researchers from all over the world. The reader will find a well-representative set of current research and developments related to sensors and sensing for intelligent vehicles. The topics of the published manuscripts can be grouped into seven main categories: (1) assistance systems and automatic vehicle operation, (2) vehicle positioning and localization, (3) fault diagnosis and fail-x systems, (4) perception and scene understanding, (5) smart regenerative braking systems for electric vehicles, (6) driver behavior modeling and (7) intelligent sensing. We, the Guest Editors, hope that the readers will find this book to contain interesting papers for their research, papers that they will enjoy reading as much as we have enjoyed organizing this Special Issue
tracking-by-detection --- multi-vehicle tracking --- Siamese network --- data association --- Markov decision process --- driving behavior --- real-time monitoring --- driver distraction --- mobile application --- portable system --- simulation test --- dynamic driving behavior --- traffic scene augmentation --- corridor model --- IMU --- vision --- classification networks --- Hough transform --- lane markings detection --- semantic segmentation --- transfer learning --- autonomous --- off-road driving --- tire-road forces estimation --- slip angle estimation --- gauge sensors --- fuzzy logic system --- load transfer estimation --- simulation results --- normalization --- lateral force empirical model --- driver monitor --- lane departure --- statistical process control --- fault detection --- sensor fault --- signal restoration --- intelligent vehicle --- autonomous vehicle --- kinematic model --- visual SLAM --- sparse direct method --- photometric calibration --- corner detection and filtering --- loop closure detection --- road friction coefficient --- tire model --- nonlinear observer --- self-aligning torque --- lateral displacement --- Lyapunov method --- automatic parking system (APS) --- end-to-end parking --- reinforcement learning --- parking slot tracking --- deceleration planning --- multi-layer perceptron --- smart regenerative braking --- electric vehicles --- vehicle speed prediction --- driver behavior modeling --- electric vehicle control --- driver characteristics online learning --- objects’ edge detection --- stixel histograms accumulate --- point cloud segmentation --- autonomous vehicles --- scene understanding --- occlusion reasoning --- road detection --- advanced driver assistance system --- trajectory prediction --- risk assessment --- collision warning --- connected vehicles --- vehicular communications --- vulnerable road users --- fail-operational systems --- fall-back strategy --- automated driving --- advanced driving assistance systems --- illumination --- shadow detection --- shadow edge --- image processing --- traffic light detection --- intelligent transportation system --- lane-changing --- merging maneuvers --- game theory --- decision-making --- intelligent vehicles --- model predictive controller --- automatic train operation --- softness factor --- fusion velocity --- online obtaining --- hardware-in-the-loop simulation --- driving assistant --- driving diagnosis --- accident risk maps --- driving safety --- intelligent driving --- virtual test environment --- millimeter wave radar --- lane-change decision --- risk perception --- mixed traffic --- minimum safe deceleration --- automated driving system (ADS) --- sensor fusion --- multi-lane detection --- particle filter --- self-driving car --- unscented Kalman filter --- vehicle model --- Monte Carlo localization --- millimeter-wave radar --- square-root cubature Kalman filter --- Sage-Husa algorithm --- target tracking --- stationary and moving object classification --- localization --- LiDAR --- GNSS --- Global Positioning System (GPS) --- monte carlo --- autonomous driving --- robot motion --- path planning --- piecewise linear approximation --- multiple-target path planning --- autonomous mobile robot --- homotopy based path planning --- LiDAR signal processing --- sensor and information fusion --- advanced driver assistance systems --- autonomous racing --- high-speed camera --- real-time systems --- LiDAR odometry --- fail-aware --- sensors --- sensing --- percepction --- object detection and tracking --- scene segmentation --- vehicle positioning --- fail-x systems --- driver behavior modelling --- automatic operation
Choose an application
Unmanned aerial vehicles (UAVs) are being increasingly used in different applications in both military and civilian domains. These applications include surveillance, reconnaissance, remote sensing, target acquisition, border patrol, infrastructure monitoring, aerial imaging, industrial inspection, and emergency medical aid. Vehicles that can be considered autonomous must be able to make decisions and react to events without direct intervention by humans. Although some UAVs are able to perform increasingly complex autonomous manoeuvres, most UAVs are not fully autonomous; instead, they are mostly operated remotely by humans. To make UAVs fully autonomous, many technological and algorithmic developments are still required. For instance, UAVs will need to improve their sensing of obstacles and subsequent avoidance. This becomes particularly important as autonomous UAVs start to operate in civilian airspaces that are occupied by other aircraft. The aim of this volume is to bring together the work of leading researchers and practitioners in the field of unmanned aerial vehicles with a common interest in their autonomy. The contributions that are part of this volume present key challenges associated with the autonomous control of unmanned aerial vehicles, and propose solution methodologies to address such challenges, analyse the proposed methodologies, and evaluate their performance.
n/a --- super twisting sliding mode controller (STSMC) --- monocular visual SLAM --- modulation --- bio-inspiration --- simulation --- horizontal control --- sensor fusion --- ADRC --- high-order sliding mode --- over-the-horizon air confrontation --- longitudinal motion model --- autonomous control --- real-time ground vehicle detection --- maneuver decision --- nonlinear dynamics --- UAV automatic landing --- harmonic extended state observer --- image processing --- General Visual Inspection --- actuator faults --- actuator fault --- remote sensing --- aerial infrared imagery --- agricultural UAV --- SC-FDM --- tilt rotors --- mass eccentricity --- wind disturbance --- decoupling algorithm --- adaptive discrete mesh --- disturbance --- super twisting extended state observer (STESO) --- heuristic exploration --- sliding mode control --- UAS --- Q-Network --- UAV communication system --- UAV --- reinforcement learning --- autonomous landing area selection --- peak-to-average power ratio (PAPR) --- slung load --- aircraft maintenance --- flight mechanics --- octree --- unmanned aerial vehicle --- convolutional neural network --- aircraft --- performance evaluation --- quadrotor --- vertical take off --- data link --- path planning --- coaxial-rotor --- fixed-time extended state observer (FTESO) --- multi-UAV system --- hardware-in-the-loop --- distributed swarm control --- vertical control
Listing 1 - 10 of 53 | << page >> |
Sort by
|