Descripteur
Documents disponibles dans cette catégorie (44)



Etendre la recherche sur niveau(x) vers le bas
Pose estimation and 3D reconstruction of vehicles from stereo-images using a subcategory-aware shape prior / Maximilian Alexander Coenen in ISPRS Journal of photogrammetry and remote sensing, Vol 181 (November 2021)
![]()
[article]
Titre : Pose estimation and 3D reconstruction of vehicles from stereo-images using a subcategory-aware shape prior Type de document : Article/Communication Auteurs : Maximilian Alexander Coenen, Auteur ; Franz Rottensteiner, Auteur Année de publication : 2021 Article en page(s) : pp 27 - 47 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] détection d'objet
[Termes IGN] estimation de pose
[Termes IGN] modèle stochastique
[Termes IGN] problème inverse
[Termes IGN] reconstruction 3D
[Termes IGN] reconstruction d'objet
[Termes IGN] robotique
[Termes IGN] véhicule automobile
[Termes IGN] vision par ordinateurRésumé : (auteur) The 3D reconstruction of objects is a prerequisite for many highly relevant applications of computer vision such as mobile robotics or autonomous driving. To deal with the inverse problem of reconstructing 3D objects from their 2D projections, a common strategy is to incorporate prior object knowledge into the reconstruction approach by establishing a 3D model and aligning it to the 2D image plane. However, current approaches are limited due to inadequate shape priors and the insufficiency of the derived image observations for a reliable alignment with the 3D model. The goal of this paper is to show how 3D object reconstruction can profit from a more sophisticated shape prior and from a combined incorporation of different observation types inferred from the images. We introduce a subcategory-aware deformable vehicle model that makes use of a prediction of the vehicle type for a more appropriate regularisation of the vehicle shape. A multi-branch CNN is presented to derive predictions of the vehicle type and orientation. This information is also introduced as prior information for model fitting. Furthermore, the CNN extracts vehicle keypoints and wireframes, which are well-suited for model-to-image association and model fitting. The task of pose estimation and reconstruction is addressed by a versatile probabilistic model. Extensive experiments are conducted using two challenging real-world data sets on both of which the benefit of the developed shape prior can be shown. A comparison to state-of-the-art methods for vehicle pose estimation shows that the proposed approach performs on par or better, confirming the suitability of the developed shape prior and probabilistic model for vehicle reconstruction. Numéro de notice : A2021-772 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2021.07.006 Date de publication en ligne : 14/09/2021 En ligne : https://doi.org/10.1016/j.isprsjprs.2021.07.006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98829
in ISPRS Journal of photogrammetry and remote sensing > Vol 181 (November 2021) . - pp 27 - 47[article]
Titre : An introduction to ethics in robotics and AI Type de document : Monographie Auteurs : Christoph Bartneck, Auteur ; Christoph Lütge, Auteur ; Alan Wagner, Auteur ; Sean Welsch, Auteur Editeur : Springer International Publishing Année de publication : 2021 Importance : 117 p Présentation : . Format : 16 x 24 cm ISBN/ISSN/EAN : 978-3-030-51110-4 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] données massives
[Termes IGN] édition en libre accès
[Termes IGN] éthique
[Termes IGN] navigation autonome
[Termes IGN] protection de la vie privée
[Termes IGN] robotique
[Termes IGN] utilisateur militaire
[Termes IGN] véhicule sans piloteRésumé : (éditeur) This open access book introduces the reader to the foundations of AI and ethics. It discusses issues of trust, responsibility, liability, privacy and risk. It focuses on the interaction between people and the AI systems and Robotics they use. Designed to be accessible for a broad audience, reading this book does not require prerequisite technical, legal or philosophical expertise. Throughout, the authors use examples to illustrate the issues at hand and conclude the book with a discussion on the application areas of AI and Robotics, in particular autonomous vehicles, automatic weapon systems and biased algorithms. A list of questions and further readings is also included for students willing to explore the topic further. Note de contenu : 1- What is AI?
2- What is ethics?
3- Trust and fairness in AI systems
4- Responsibility and liability in the case of AI systems
5- Risks in the business of AI
6- Psychological aspects of AI
7- Privacy issues of AI
8- Application areas of AI
9- Autonomous vehicles
10- Military uses of AI
11- Ethics in AI and Robotics: A Strategic ChallengeNuméro de notice : 28570 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Monographie DOI : 10.1007/978-3-030-51110-4 En ligne : https://doi.org/10.1007/978-3-030-51110-4 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97726 Méthodes de partage d'informations visuelles et inertielles pour la localisation et la cartographie simultanées décentralisées multi-robots / Rodolphe Dubois (2021)
![]()
Titre : Méthodes de partage d'informations visuelles et inertielles pour la localisation et la cartographie simultanées décentralisées multi-robots Type de document : Thèse/HDR Auteurs : Rodolphe Dubois, Auteur ; Vincent Frémont, Directeur de thèse Editeur : Nantes : Ecole Centrale de Nantes Année de publication : 2021 Importance : 259 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de Doctorat de l'Ecole Centrale de Nantes, spécialité Signal, Image, VisionLangues : Français (fre) Descripteur : [Vedettes matières IGN] Informatique
[Termes IGN] cartographie et localisation simultanées
[Termes IGN] fusion de données
[Termes IGN] navigation autonome
[Termes IGN] partage de données localisées
[Termes IGN] robot mobile
[Termes IGN] robotique
[Termes IGN] vision
[Termes IGN] vision par ordinateurRésumé : (auteur) En robotique mobile, les méthodes de cartographie et de localisation simultanées (SLAM) constituent une brique algorithme essentielle afin de percevoir l’environnement et y naviguer de façon autonome. En contexte visuel, les méthodes de SLAM mono-robot ont aujourd’hui atteint un haut degré de maturité, ce qui a permis l’essor de méthodes collaboratives. Néanmoins, les problématiques d’autonomie des agents couplées aux contraintes d’information, de réseau et de ressources interrogent sur la nature des données à transmettre entre les robots. L’objectif de cette thèse est de concevoir des méthodes de partage d’informations visuelles et inertielles qui favorisent l’autonomie des robots et leur permettent d’affiner leur navigation dès lors qu’ils visitent des zones communes. Dans ce but, nous investiguons différents paradigmes d’échanges pour des architectures décentralisées de SLAM visio-inertiel et stéréo-visuel. Tout d’abord, nous proposons trois façons de synthétiser des données visio-inertielles, et développons une architecture de SLAM collaboratif décentralisée chargée d’en organiser le calcul, l’échange et l’intégration. Ces méthodes exploitent respectivement l’échange de sous-cartes visio-inertielles rigides, de paquets condensés par marginalisation et éparsification consistante, et de paquets élagués via la sélection de facteurs visioinertiels bruts. Nous les évaluons sur des jeux de données standards, ainsi que sur notre jeu de données AirMuseum, spécifiquement conçu à cette fin. Enfin, nous appliquons l’architecture développée pour la cartographie dense en étendant une méthode de cartographie collaborative reposant sur l’échange, le recalage et la fusion de sous-cartes localement consistantes associées à des représentations de type TS. Note de contenu : 1- Introduction
I État de l’art
2- La cartographie et la localisation simultanées mono-robot
3- L’émergence des méthodes de SLAM multi-robots
II Contributions
4- Construction d’un jeu de données multi-robots
5- SLAM visio-inertiel décentralisé pour la navigation multi-robots
6- SLAM dense stéréo-visuel décentralisé basé sur l’échange de sous-cartes TSDF
7- Conclusion et Perspectives
III AnnexesNuméro de notice : 28637 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Signal, Image, Vision : Centrale Nantes : 2021 Organisme de stage : Laboratoire des Sciences du Numérique DOI : sans En ligne : https://tel.archives-ouvertes.fr/tel-03273943 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99702
Titre : AI based robot safe learning and control Type de document : Monographie Auteurs : Xuefeng Zhou, Auteur ; Shuai Li, Auteur ; et al., Auteur Editeur : Springer Nature Année de publication : 2020 Importance : 127 p. Format : 21 x 30 cm ISBN/ISSN/EAN : 978-981-1555039-- Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] optimisation (mathématiques)
[Termes IGN] réseau neuronal récurrent
[Termes IGN] robotique
[Termes IGN] sécurité
[Termes IGN] système de contrôle
[Termes IGN] vitesse angulaireRésumé : (éditeur) This open access book mainly focuses on the safe control of robot manipulators. The control schemes are mainly developed based on dynamic neural network, which is an important theoretical branch of deep reinforcement learning. In order to enhance the safety performance of robot systems, the control strategies include adaptive tracking control for robots with model uncertainties, compliance control in uncertain environments, obstacle avoidance in dynamic workspace. The idea for this book on solving safe control of robot arms was conceived during the industrial applications and the research discussion in the laboratory. Most of the materials in this book are derived from the authors’ papers published in journals, such as IEEE Transactions on Industrial Electronics, neurocomputing, etc. This book can be used as a reference book for researcher and designer of the robotic systems and AI based controllers, and can also be used as a reference book for senior undergraduate and graduate students in colleges and universities. Note de contenu : 1- Adaptive Jacobian based trajectory tracking for redundant manipulators with model uncertainties in repetitive tasks
2- RNN based trajectory control for manipulators with uncertain kinematic parameters
3- RNN based adaptive compliance control for robots with model uncertainties
4- Deep RNN based obstacle avoidance control for redundant manipulators
5- Optimization-based compliant control for manipulators under dynamic obstacle constraints
6- RNN for motion-force control of redundant manipulators with optimal joint torqueNuméro de notice : 28518 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE/MATHEMATIQUE Nature : Monographie DOI : sans En ligne : https://directory.doabooks.org/handle/20.500.12854/32049 Format de la ressource électronique : url Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97304
Titre : Collaborative visual-inertial state and scene estimation Type de document : Thèse/HDR Auteurs : Marco Karrer, Auteur ; Margarita Chli, Directeur de thèse Editeur : Zurich : Eidgenossische Technische Hochschule ETH - Ecole Polytechnique Fédérale de Zurich EPFZ Année de publication : 2020 Importance : 151 p. Format : 21 x 30 cm Note générale : bibliographie
A thesis submitted to attain the degree of Doctor of Sciences of ETH Zurich in Mechanical EngineeringLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Acquisition d'image(s) et de donnée(s)
[Termes IGN] cartographie et localisation simultanées
[Termes IGN] centrale inertielle
[Termes IGN] compensation par faisceaux
[Termes IGN] estimation de pose
[Termes IGN] image captée par drone
[Termes IGN] reconstruction d'objet
[Termes IGN] robotique
[Termes IGN] système multi-agents
[Termes IGN] vision par ordinateurIndex. décimale : THESE Thèses et HDR Résumé : (auteur) The capability of a robot to create a map of its workspace on the fly, while constantly updating it and continuously estimating its motion in it, constitutes one of the central research problems in mobile robotics and is referred to as Simultaneous Localization And Mapping (SLAM) in the literature. Relying solely on the sensor-suite onboard the robot, SLAM is a core building block in enabling the navigational autonomy necessary to facilitate the general use of mobile robots and has been the subject of booming research interest spanning over three decades. With the largest body of related literature addressing the challenge of single-agent SLAM, it is only very recently, with the relative maturity of this field that approaches tackling collaborative SLAM with multiple agents have started appearing. The potential of collaborative multi-agent SLAM is great; not only promising to boost the efficiency of robotic missions by splitting the task at hand to more agents but also to improve the overall robustness and accuracy by boosting the amount of data that each agent’s estimation process has access to. While SLAM can be performed using a variety of different sensors, this thesis is focused on the fusion of visual and inertial cues, as one of the most common combinations of sensing modalities in robotics today. The information richness captured by cameras, along with the high-frequency and metric information provided by Inertial Measurement Units (IMUs) in combination with the low weight and power consumption offered by a visual-inertial sensor suite render this setup ideal for a wide variety of applications and robotic platforms, in particular to resource-constrained platforms such as Unmanned Aerial Vehicles (UAVs). The majority of the state-of-the-art visual-inertial estimators are designed as odometry algorithms, providing only estimates consistent within a limited time-horizon. This lack in global consistency of estimates, however, poses a major hurdle in an effective fusion of data from multiple agents and the practi- cal definition of a common reference frame, which is imperative before collaborative effort can be coordinated. In this spirit, this thesis investigates the potential of global optimization, based on a central access point (server) as a first approach, demonstrating global consistency using only monocular-inertial data. Fusing data from multiple agents, not only consistency can be maintained, but also the accuracy is shown to improve at times, revealing the great potential of collaborative SLAM. Aiming at improving the computational efficiency, in a second approach a more efficient system architecture is employed, allowing a more suitable distribution of the computational load amongst the agents and the server. Furthermore, the architecture implements a two-way communication enabling a tighter collaboration between the agents as they become capable of re-using information captured by other agents through communication with the server, enabling improvements of their onboard pose tracking online, during the mission. In addition to general collaborative SLAM without specific assumptions on the agents’ relative pose configuration, we investigate the potential of a configuration with two agents, carrying one camera each with overlapping fields of view, essentially forming a virtual stereo camera. With the ability of each robotic agent to move independently, the potential to control the stereo baseline according to the scene depth is very promising, for example at high altitudes where all scene points are far away and, therefore, only provide weak constraints on the metric scale in a standard single-agent system. To this end, an approach to estimate the time-varying stereo transformation formed between two agents is proposed, by fusing the egomotion estimates of the individual agents along with the image measurements extracted from the view-overlap in a tightly coupled fashion. Taking this virtual stereo camera idea a step further, a novel collaboration framework is presented, utilizing the view-overlap along with relative distance measurements across the two agents (e.g. obtained via Ultra-Wide Band (UWB) modules), in order to successfully perform state estimation at high altitudes where state-of-the-art single-agent methods fail. In the interest of low-latency pose estimation, each agent holds its own estimate of the map, while consistency between the agents is achieved using a novel consensus-based sliding window bundle adjustment. Despite that in this work, experiments are shown in a two-agent setup, the proposed distributed bundle adjustment scheme holds great potential for scaling up to larger problems with multiple agents, due to the asynchronicity of the proposed estimation process and the high level of parallelism it permits. The majority of the developed approaches in this thesis rely on sparse feature maps in order to allow for efficient and timely pose estimation, however, this translates to reduced awareness of the spatial structure of a robot’s workspace, which can be insufficient for tasks requiring careful scene interaction and manipulation of objects. Equipping a typical visual-inertial sensor suite with an RGB-D camera, an add-on framework is presented that enables the efficient fusion of naturally noisy depth information into an accurate, local, dense map of the scene, providing sufficient information for an agent to plan contact with a surface. With the focus on collaborative SLAM using visual-inertial data, the approaches and systems presented in this thesis contribute towards achieving collaborative Visual-Inertial SLAM (VI-SLAM) deployable in challenging real-world scenarios, where the participating agents’ experiences get fused and processed at a central access point. On the other side, it is shown that taking advantage of specific configurations can push the collaboration amongst the agents towards achieving greater general robustness and accuracy of scene and egomotion estimates in scenarios, where state-of-the-art single-agent systems are otherwise unsuccessful, paving the way towards intelligent robot collaboration. Note de contenu : Introduction
1- Real-time dense surface reconstruction for aerial manipulation
2- Towards globally consistent visual-inertial collaborative SLAM
3- CVI-SLAM – collaborative visual-inertial SLAM
4- Collaborative 6DoF relative pose estimation for two UAVs with overlapping fields of view
5- Distributed variable-baseline stereo SLAM from two UAVsNuméro de notice : 28318 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Thèse étrangère Note de thèse : PhD Thesis : Mechanical Engineering : ETH Zurich : 2020 DOI : sans En ligne : https://www.research-collection.ethz.ch/handle/20.500.11850/465334 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98251 Nonparametric Bayesian learning for collaborative robot multimodal introspection / Xuefeng Zhou (2020)
PermalinkPermalinkSmoothing algorithms for navigation, localisation and mapping based on high-grade inertial sensors / Paul Chauchat (2020)
PermalinkPermalinkMachine learning and pose estimation for autonomous robot grasping with collaborative robots / Victor Talbot (2018)
PermalinkPermalinkIndoor navigation of mobile robots based on visual memory and image-based visual servoing / Suman Raj Bista (2016)
PermalinkLocalisation de véhicule par satellites couplée à la navigation à l'estime et aux données cartographiques / David Bétaille (2014)
PermalinkPanorama de l'intelligence artificielle, ses bases méthodologiques, ses développements, 3. L'intelligence artificielle : frontières et applications / Pierre Marquis (2014)
PermalinkPermalink