Dissertations / Theses on the topic 'Fusion des capteurs pour la localisation'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Fusion des capteurs pour la localisation.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Bader, Kaci. "Tolérance aux fautes pour la perception multi-capteurs : application à la localisation d'un véhicule intelligent." Thesis, Compiègne, 2014. http://www.theses.fr/2014COMP2161/document.
Full textPerception is a fundamental input for robotic systems, particularly for positioning, navigation and interaction with the environment. But the data perceived by these systems are often complex and subject to significant imprecision. To overcome these problems, the multi-sensor approach uses either multiple sensors of the same type to exploit their redundancy or sensors of different types for exploiting their complementarity to reduce the sensors inaccuracies and uncertainties. The validation of the data fusion approach raises two major problems. First, the behavior of fusion algorithms is difficult to predict, which makes them difficult to verify by formal approaches. In addition, the open environment of robotic systems generates a very large execution context, which makes the tests difficult and costly. The purpose of this work is to propose an alternative to validation by developing fault tolerance mechanisms : since it is difficult to eliminate all the errors of the perceptual system, We will try to limit impact in their operation. We studied the inherently fault tolerance allowed by data fusion by formally analyzing the data fusion algorithms, and we have proposed detection and recovery mechanisms suitable for multi-sensor perception, we implemented the proposed mechanisms on vehicle localization application using Kalman filltering data fusion. We evaluated the proposed mechanims using the real data replay and fault injection technique
Touil, Khalid. "Contribution de la fusion multi-capteurs par approche probabiliste et de croyance pour la localisation." Littoral, 2009. http://www.theses.fr/2009DUNK0257.
Full textThe work presented in this thesis, is focused on the contribution of multisensor fusion by probabilistic and belief approaches for localization. In fact, two problems of multisensor fusion for improving the navigation of land vehicles in dense urban environment have been addressed. As a first step, we proposed a new solution for the integration of navigation systems : GPS and inertial (INS). The reason for the integration is to exploit the advantages of each system used. This solution is based on new nonlinear and nonparametric filters. In a second step, two solutions based on the transferable belief model (TBM) have been proposed to resolve the divergence of the filter in case where these sensors are potentially failing. The first is to introduce an annex sensor in characteristics are known (digital map). The exploitation of digital map information is made by a correlation between the position of the vehicle and the geometric elements representing the roads on the map known as map-matching. A new algorithm for map-matching based on the TBM has been proposed to identify the most credible road that the vehicule is to be suciptible. The second is to propose an algorithm of information fusion to take into account the context. This incorporation allows to select at any time that the relevant measures and to reduce the importance or simply to exclude measures that could disrupt information
Djama, Zahir. "Approche multi modèles à sauts markoviens et fusion multi capteurs pour la localisation d'un robot mobile." Paris 12, 2001. http://www.theses.fr/2001PA12A001.
Full textFusion and filtering techniques currently used for the localization of a mobile robot present two main drawbacks. The first one concerns the fact that no a priori reliable information on the input and the measurement noise covariance is generaily available. The second one is tied to the fact that the process of localization is often modelled under the form of a unique model leading to the introduction of modelling errors that degrade the quality of the filtering. The work presented in this thesis presents two contributions. The first one consists in taking into account the existence of several regimes in the localization process. This one is modelled under the form of a Markovian hybrid process both from state and observation procesess point of view. The second contribution consists in proposing an on-une adaptative estimation of statistical parameters such as state and observation noise variances along with an optimal management of observations. The fusion of data is performed by Kalman filters of adaptive linear type for linear process and of adaptive extended type for non linear process. This approach has been validated in simulation on a robot equipped with an odometer, two telemeters perpendicularly displayed and a compas. In order to show its efficiency, a comparative analysis of its performance with respect to existing approaches is presented. Thus, gains values on accuracy obtained hy this approach compared to classical filters are 2 on translation and 2 on orientation
Smaili, Cherif. "Fusion de données multi-capteurs à l'aide d'un réseau bayésien pour l'estimation d'état d'un véhicule." Phd thesis, Université Nancy II, 2010. http://tel.archives-ouvertes.fr/tel-00551833.
Full textRoquel, Arnaud. "Exploitation du conflit entre capteurs pour la gestion d'un système complexe multi-capteurs." Phd thesis, Université Paris Sud - Paris XI, 2012. http://tel.archives-ouvertes.fr/tel-00804661.
Full textLherbier, Régis. "Étude d'une méthode de coopération entre capteurs pour la localisation dynamique d'un robot mobile." Compiègne, 1994. http://www.theses.fr/1994COMPD763.
Full textAl, Assaad Hiba. "Apport des modèles numériques d'élévation pour l'enrichissement des cartes de navigation par fusion multi-capteurs." Thesis, Littoral, 2020. http://www.theses.fr/2020DUNK0558.
Full textTe work presented in this thesis concerns the study of a multi-sensor fusion method for the estimation of 3-D localization and the attitude of a land vehicle. We have developed and validated, in a real situation, a centralized fusion method based on state modeling from GNSS/INS measurements delivered by the ublox EVK-M8U sensor. The measurement system is also completed by OSM digital road maps and elevation data from the ASTER/World 30 digital models. Some measurements are modeled by equations with strong non-linearities which we have chosen to process by particle filtering. The cartographic data are taken into account statistically from the metric of Mahalanobis. In addition, we have developed a new method for managing digital elevation models (DEM), known as the "Fenêtre Glissante Adjacente" (FGA) method, in order to limit the impact of the artifacts that are found in this data. During the DEM management step, we implemented geometric approaches (TIN, FGA) which make the altitude correction more robust and favors an increase in performance in estimating the inclination parameter of the segments of the digital road maps
Zendjebil, Iman mayssa. "Localisation 3D basée sur une approche de suppléance multi-capteurs pour la réalité augmentée mobile en milieu extérieur." Thesis, Evry-Val d'Essonne, 2010. http://www.theses.fr/2010EVRY0024/document.
Full textThe democratization of mobile devices such as smartphones, PDAs or tablet-PCs makes it possible to use Augmented Reality systems in large scale environments. However, in order to implement such systems, many issues must be adressed. Among them, 3D localization is one of the most important. Indeed, the estimation of the position and orientation (also called pose) of the viewpoint (of the camera or the user) allows to register the virtual objects over the visible part of the real world. In this paper, we present an original localization system for large scale environments which uses a markerless vision-based approach to estimate the camera pose. It relies on natural feature points extracted from images. Since this type of method is sensitive to brightness changes, occlusions and sudden motion which are likely to occur in outdoor environment, we use two more sensors to assist the vision process. In our work, we would like to demonstrate the feasibility of an assistance scheme in large scale outdoor environment. The intent is to provide a fallback system for the vision in case of failure as well as to reinitialize the vision system when needed. The complete localization system aims to be autonomous and adaptable to different situations. We present here an overview of our system, its performance and some results obtained from experiments performed in an outdoor environment under real conditions
Baig, Qadeer. "Fusion de données multi capteurs pour la détection et le suivi d'objets mobiles à partir d'un véhicule autonome." Phd thesis, Université de Grenoble, 2012. http://tel.archives-ouvertes.fr/tel-00858441.
Full textZureiki, Ayman. "Fusion de données multi-capteurs pour la construction incrémentale du modèle tridimensionnel texturé d'un environnement intérieur par un robot mobilen." Toulouse 3, 2008. http://thesesups.ups-tlse.fr/319/.
Full textThis thesis examines the problem of 3D Modelling of indoor environment by a mobile robot. Our main contribution consists in constructing a heterogeneous geometrical model containing textured planar landmarks, 3D lines and interest points. For that, we must fuse geometrical and photometrical data. Hence, we began by improving the stereo vision algorithm, and proposed a new approach of stereo matching by graph cuts. The most significant contribution is the construction of a reduced graph that allows to accelerate the global method and to provide better results than the local methods. Also, to perceive the environment, the robot is equipped by a 3D laser scanner and by a camera. We proposed an algorithmic chain allowing to incrementally constructing a heterogeneous map, using the algorithm of Simultaneous Localization and Mapping based (EKF-SLAM). Mapping the texture on the planar landmarks makes more robust the phase of data association
Evennou, Frédéric. "Techniques et technologies de localisation avancées pour terminaux mobiles dans les environnements indoor." Phd thesis, Université Joseph Fourier (Grenoble), 2007. http://tel.archives-ouvertes.fr/tel-00136064.
Full textL'utilisation d'une technique de localisation basée sur des mesures temporelles est moins contraignante que le fingerprinting. L'émission d'impulsions radio très brèves confère à la technologie 802.15.4a un fort pouvoir séparateur des multi-trajets. Le phénomène de multi-trajets est la principale contrainte au déploiement d'une technologie de localisation par mesures temporelles. La détection du premier trajet est très importante.
Des estimateurs comme le filtre de Kalman ou le filtre particulaire sont nécessaires pour limiter les effets des multi-trajets, des bruits de mesure, etc. Ces filtres peuvent aussi intégrer des informations de cartographie. Bien souvent, l'exploitation d'une seule technologie est insuffisante. La fusion d'informations de localisation est une étape supplémentaire pour améliorer la localisation. Des architectures de fusion robustes permettent de corriger les défauts de chacune des technologies pour conduire à un système plus robuste et plus précis en toutes circonstances.
Ce travail présente une approche innovante pour la localisation WiFi avec l'exploitation de cartographie dans l'estimateur tout en gardant une faible complexité suivant la plate-forme de déploiement visée. L'exploration des capacités de la localisation par ULB est proposée dans un second temps, avant d'aborder une réflexion sur les méthodes de fusion multi-capteurs.
Fillatreau, Philippe. "Localisation et modélisation tridimensionnelles pour un robot mobile autonome tout terrain." Phd thesis, Université Paul Sabatier - Toulouse III, 1994. http://tel.archives-ouvertes.fr/tel-00261834.
Full textLe, Marchand Olivier. "Approche autonome pour la localisation et la surveillance de l'intégrité d'un véhicule automobile en environnement complexe." Phd thesis, Université de Technologie de Compiègne, 2010. http://tel.archives-ouvertes.fr/tel-00672343.
Full textMalartre, Florent. "Perception intelligente pour la navigation rapide de robots mobiles en environnement naturel." Phd thesis, Université Blaise Pascal - Clermont-Ferrand II, 2011. http://tel.archives-ouvertes.fr/tel-00673435.
Full textRodriguez, Florez Sergio Alberto. "Contributions des systèmes de vision à la localisation et au suivi d'objets par fusion multi-capteur pour les véhicules intelligents." Phd thesis, Université de Technologie de Compiègne, 2010. http://tel.archives-ouvertes.fr/tel-00635330.
Full textAmri, Mohamed-Hédi. "Fusion ensembliste de donn´ees pour la surveillance des personnes d´ependantes en habitat intelligent." Thesis, Orléans, 2015. http://www.theses.fr/2015ORLE2030/document.
Full textOur research work is a part of the project FUI 14 FEDER Collectivités E-monitor’âge. This project takes place within the framework of Ambient Assisted Living (AAL) which aims to improve the safety and the comfort of elderly people living in smart nursing homes. This work aims to monitor the activities of elderly persons using information from different sensors. The ADL (Activities of Daily Living) are used to evaluate the ability of the person to perform on their own a selection of the activities which are essential for an independent living in the everyday life. Generally, process knowledge and measurements coming from sensors are prone to indeterminable noise. In our work, we suppose that these errors are unknown but bounded. Taking into account this hypothesis, we show how to solve the estimation issue using set-membership computations techniques. Our algorithm, based on set-membership approach, consists of two steps. The prediction step, based on the use of a random walk mobility with minimum assumptions (maximum speed of moving), employs the previous state estimate to provide the prediction zone where the person may be located. The correction step uses the informations coming from the sensors to refine this predicted zone. This step uses a relaxed constraints propagation technique, q-relaxed intersection, to deal with faulty measurements. This proposed method allows us to compute the uncertainty domain for the reconstructed localization of moving targets as dealing with outliers
Oudet, Jean-Philippe. "Architecture distribuée pour la détection d'activité dans un Espace Intelligent." Mémoire, Université de Sherbrooke, 2011. http://savoirs.usherbrooke.ca/handle/11143/1634.
Full textKhairallah, Mahmoud. "Flow-Based Visual-Inertial Odometry for Neuromorphic Vision Sensors." Electronic Thesis or Diss., université Paris-Saclay, 2022. http://www.theses.fr/2022UPAST117.
Full textRather than generating images constantly and synchronously, neuromorphic vision sensors -also known as event-based cameras- permit each pixel to provide information independently and asynchronously whenever brightness change is detected. Consequently, neuromorphic vision sensors do not encounter the problems of conventional frame-based cameras like image artifacts and motion blur. Furthermore, they can provide lossless data compression, higher temporal resolution and higher dynamic range. Hence, event-based cameras conveniently replace frame-based cameras in robotic applications requiring high maneuverability and varying environmental conditions. In this thesis, we address the problem of visual-inertial odometry using event-based cameras and an inertial measurement unit. Exploiting the consistency of event-based cameras with the brightness constancy conditions, we discuss the availability of building a visual odometry system based on optical flow estimation. We develop our approach based on the assumption that event-based cameras provide edge-like information about the objects in the scene and apply a line detection algorithm for data reduction. Line tracking allows us to gain more time for computations and provides a better representation of the environment than feature points. In this thesis, we do not only show an approach for event-based visual-inertial odometry but also event-based algorithms that can be used as stand-alone algorithms or integrated into other approaches if needed
Drevelle, Vincent. "Étude de méthodes ensemblistes robustes pour une localisation multi-sensorielle intègre : application à la navigation des véhicules en milieu urbain." Compiègne, 2011. http://www.theses.fr/2011COMP1986.
Full textIn this thesis, confidence domains for vehicle localization are characterized by using robust interval methods. Positioning is of prime importance in mobile robotics and more specifically for intelligent vehicle applications. When position information is used in a safety-critical context, like autonomous vehicle navigation, an integrity method is needed to check that the positioning error stays within the limits specified for the mission. In aeronautical navigation, protection levels are defined as bounds on the position error associated to a given integrity risk. This work aims to compute a confidence domain in which the user in guaranteed to be located with a given integrity risk. The possible presence of outliers is handled by the use of robust set-membership methods. Sensor measurements and model parameters are prone to errors, which are often modeled by their probability distribution. In the set-membership working frame,errors can be represented by intervals, thus making the assumption of bounded errors. When guaranteed error bounds are unknown or too pessimistic, error bounds associated with a risk can be used. The risk taken on measurements is then propagated to the computed confidence domain. Global navigation satellite systems enable high precision absolute positioning in open sky environments, but measurements suffer from multipath and non-line-ofsight propagation in urban areas. Robustness to outliers is thus needed. To counter the lack of visible satellites in urban canyons, position is constrained by a 3D map of the drivable space and by using the proprioceptive sensors embedded in recent vehicles. This document presents three positioning methods based on a robust set inversion via interval analysis with GPS pseudorange measurements : Snapshot computation of a position confidence domain, with GPS measurements and altitude constraint from a digital elevation model. Use of a precise 3D model of the drivable space as a positioning constraint, and observation of the GPS receiver’s clock drift. Robust pose estimation from a sliding horizon of positions and proprioceptive measurements, constrained by a 3D map. These positioning methods have been implemented in real-time and tested with real data in difficult environments for satellite positioning
Vassal, Patrick. "Fusion d'images multi-modales pour la radiothérapie conformationnelle : application au repositionnement du patient." Phd thesis, Université Joseph Fourier (Grenoble), 1998. http://tel.archives-ouvertes.fr/tel-00005155.
Full textNdjeng, Ndjeng Alexandre. "Localisation robuste multi-capteurs et multi-modèles." Thesis, Evry-Val d'Essonne, 2009. http://www.theses.fr/2009EVRY0013/document.
Full textMany research works have been devoted in the last years in order to provide an accurate and high integrity solution to the problem outdoor vehicles localization. These research efforts are mainly based on the probability estimation theory. They use multi-sensor fusion approach and a single-model based Kalman filtering, through some variants adapted to nonlinear systems. The single complex model that is used is assumed to describe the dynamics of the vehicle. We rather propose a multiple model approach in this thesis. The presented study derives from a modular analysis of the dynamics of the vehicle, ie the evolution of the vehicle is considered as a discrete process, which combines several simple models. Each model is dedicated to a particular manoeuvre of the vehicle. This evolution space discretizing will improves the system robustness to modelling defects. Our approach is a variant of the IMM algorithm, which takes into account the asynchronism of the embedded sensors. In order to achieve this goal, a new system constrained modelling is developed, which allows to update the various models likelihood even in absence of exteroceptive sensors. However, the performance of such a system requires the use of good quality data. Several operations are presented, illustrating the corrections on the sensors bias, measurements noise and taking into account the road bank angle. The developed methodology is validated through a comparison with the probabilistic fusion algorithms EKF, UKF, DD1, DD2 and particle filtering. This comparison is based on measurements of accuracy and confidence, then the use of statistical consistency and credibility measures, from simulation scenarios and then real data
Makhoul, Abdallah. "Réseaux de capteurs : localisation, couverture et fusion de données." Besançon, 2008. http://www.theses.fr/2008BESA2025.
Full textThis thesis tackles the problems of localization, coverage and data fusion in randomly deployed sensor networks. First, we introduce a novel approach for node's localization. It is based on a single mobile beacon aware of its positions. Sensor nodes receiving beacon packets will be able to locate themselves. The mobile beacon follows a defined Hilbert curve. On the other hand, we exploit the localization phase to construct sets of active nodes that ensure as much as possible the zone coverage. To optimize the energy consumption, we construct disjoint sets of active nodes such that only one of them is active at any moment, while ensuring at the same time both the network connectivity and the area coverage. We present and study four different scheduling methods. Ln a third step, we study the problem of data fusion in sensor networks in particular the" average consensus" problem. It allows the nodes of a sensor network to track the average of n sensor measurements. To compute the average, we propose an iterative asynchronous algorithm that is robust to the dynamic topology changes and the loss of messages. To show the effectiveness of the proposed algorithms, we conducted series of simulations based on OMNet++
André, Cyrille. "Approche crédibiliste pour la fusion multi capteurs décentralisée." Phd thesis, Université Paris Sud - Paris XI, 2013. http://tel.archives-ouvertes.fr/tel-00976761.
Full textBrulin, Damien. "Fusion de données multi-capteurs pour l'habitat intelligent." Thesis, Orléans, 2010. http://www.theses.fr/2010ORLE2066/document.
Full textThe smart home concept has been widely developed in the last years in order to propose solutions for twomain concerns : optimized energy management in building and help for in-home support for elderly people.In this context, the CAPTHOM project, in which this thesis is in line with, has been developed. To respondto these problems, many sensors, of different natures, are used to detect the human presence, to determinethe position and the posture of the person. In fact, no sensor can , alone, answers to all information justifyingthe development of a multi-sensor system and a data fusion method. In this project, the selected sensorsare passive infrared sensors (PIR), thermopiles and a video camera. No sensor is carried by the person(non invasive system). We propose a global architecture of intelligent sensor made of four fusion modulesallowing respectively to detect the human presence, to locate in 3D the person, to determine the posture andto help to make a decision according to the application. The human presence module fuses information ofthe three sensors : PIR sensors for the movement, thermopiles for the presence in case of immobility and thecamera to identify the detected entity. The 3D localisation of the person is realized thanks to position recedinghorizon estimation. This method, called Visual Receding Horizon Estimation (VRHE), formulates the positionestimation problem into an nonlinear optimisation problem under constraints in the image plane. The fusionmodule for the posture determination is based on fuzzy logic. It insures the posture determination regardlessof the person and the distance from the camera. Finally, the module to make a decision fuses the outputs of the preceding modules and gives the opportunity to launch alarms (elderly people monitoring) or to commandhome automation devices (lightning, heating) for the energy management of buildings
Salehi, Achkan. "Localisation précise d'un véhicule par couplage vision/capteurs embarqués/systèmes d'informations géographiques." Thesis, Université Clermont Auvergne (2017-2020), 2018. http://www.theses.fr/2018CLFAC064/document.
Full textThe fusion between sensors and databases whose errors are independant is the most re-liable and therefore most widespread solution to the localization problem. Current autonomousand semi-autonomous vehicles, as well as augmented reality applications targeting industrialcontexts exploit large sensor and database graphs that are difficult and expensive to synchro-nize and calibrate. Thus, the democratization of these technologies requires the exploration ofthe possiblity of exploiting low-cost and easily accessible sensors and databases. These infor-mation sources are naturally tainted by higher uncertainty levels, and many obstacles to theireffective and efficient practical usage persist. Moreover, the recent but dazzling successes ofdeep neural networks in various tasks seem to indicate that they could be a viable and low-costalternative to some components of current SLAM systems.In this thesis, we focused on large-scale localization of a vehicle in a georeferenced co-ordinate frame from a low-cost system, which is based on the fusion between a monocularvideo stream, 3d non-textured but georeferenced building models, terrain elevation models anddata either from a low-cost GPS or from vehicle odometry. Our work targets the resolutionof two problems. The first one is related to the fusion via barrier term optimization of VS-LAM and positioning measurements provided by a low-cost GPS. This method is, to the bestof our knowledge, the most robust against GPS uncertainties, but it is more demanding in termsof computational resources. We propose an algorithmic optimization of that approach basedon the definition of a novel barrier term. The second problem is the data association problembetween the primitives that represent the geometry of the scene (e.g. 3d points) and the 3d buil-ding models. Previous works in that area use simple geometric criteria and are therefore verysensitive to occlusions in urban environments. We exploit deep convolutional neural networksin order to identify and associate elements from the map that correspond to 3d building mo-del façades. Although our contributions are for the most part independant from the underlyingSLAM system, we based our experiments on constrained key-frame based bundle adjustment.The solutions that we propose are evaluated on synthetic sequences as well as on real urbandatasets. These experiments show important performance gains for VSLAM/GPS fusion, andconsiderable improvements in the robustness of building constraints to occlusions
Kueviakoe, Kangni. "Localisation multi-capteurs garantie : résolution d'un problème de satisfaction de contraintes." Thesis, Paris 11, 2014. http://www.theses.fr/2014PA112241/document.
Full textThis thesis deals with the vehicle locationand addresses the problem of SLAM (simultaneous localization and mapping). Several methods are used to solve this kind of problem. They can be classified into two broad categories of approaches: probabilistic approach and deterministic approaches. This work addresses the deterministic approaches and more precisely the approach based on interval analysis. The work has been conducted on real data sets collected in outdoor environments with proprioceptive and exteroceptive sensors.When multiple sensors providing complementary or redundant information are put into play, it is important to merge the data to improve the estimated pose. The approach detailed in this document uses the intervals methods and presents the localization problem as a constraint satisfaction problem.The resolution is done using a solver interval. Several solvers were compared. One thing is clear: local consistency algorithms do not address the uncertainty of the orientation. This thesis proposes a method of locating usable in real time applications and corrects the uncertainty in the heading of the vehicle. We compared our results with those of the extended Kalman filter (probabilistic reference method) and highlighted one of the interests of our method: the assurance of consistency of the pose (position and orientation of the mobile).This thesis proposes two contributions. The first is methodological. In the state of the art all works affirm the need (or obligation) to pre-decompose the constraints of the problem before the resolution step. Our work allows to prove otherwise. The second contribution relates to the reduction of the orientation uncertainty by combining constraint propagation and a bisection approach
Alibay, Manu. "Fusion de données capteurs étendue pour applications vidéo embarquées." Thesis, Paris, ENMP, 2015. http://www.theses.fr/2015ENMP0032/document.
Full textThis thesis deals with sensor fusion between camera and inertial sensors measurements in order to provide a robust motion estimation algorithm for embedded video applications. The targeted platforms are mainly smartphones and tablets. We present a real-time, 2D online camera motion estimation algorithm combining inertial and visual measurements. The proposed algorithm extends the preemptive RANSAC motion estimation procedure with inertial sensors data, introducing a dynamic lagrangian hybrid scoring of the motion models, to make the approach adaptive to various image and motion contents. All these improvements are made with little computational cost, keeping the complexity of the algorithm low enough for embedded platforms. The approach is compared with pure inertial and pure visual procedures. A novel approach to real-time hybrid monocular visual-inertial odometry for embedded platforms is introduced. The interaction between vision and inertial sensors is maximized by performing fusion at multiple levels of the algorithm. Through tests conducted on sequences with ground-truth data specifically acquired, we show that our method outperforms classical hybrid techniques in ego-motion estimation
Castagliola, Philippe. "Un système incrémental pour la fusion multi-capteurs pour un robot mobile." Compiègne, 1991. http://www.theses.fr/1991COMPD391.
Full textValade, Aurelien. "Capteurs intelligents : quelles méthodologies pour la fusion de données embarquées ?" Thesis, Toulouse, INSA, 2017. http://www.theses.fr/2017ISAT0007/document.
Full textThe work detailed in this document is the result of a collaborative effort of the LAAS-CNRS in Toulouse and MEAS-France / TE Connectivity during a period of three years.The goal here is to develop a methodology to design smart embedded sensors with the ability to estimate physical parameters based on multi-physical data fusion. This strategy tends to integrate sensors technologies, currently dedicated to lab measurements, in low powered embedded systems working in imperfects environments. After exploring model oriented methods, parameters estimations and Kalman filters, we detail various existing solutions upon which we can build a valid response to multi-physical data fusion problematics, for linear systems with the Kalman Filter, and for non-linear systems with the Extended Kalman Filter and the Unscented Kalman Filter.Then, we will synthesize a filter for hybrid systems, having a linear evolution model and a non-linear measurement model. For example, using the best of the two worlds in order to obtain the best complexity/precision ratio. Once we selected the estimation method, we detail computing power and algorithm complexity problematics in order to find available optimizations we can use to assess the usability of our system in a low power environment. Then we present the developed methodology application to the UQS sensor, sold by TE Connectivity, study case. This sensor uses near infra-red spectroscopy to determine the urea concentration in a urea/water solution, in order to control the nitrogen-oxyde depolluting process in gasoline engines. After a design principles presentation, we detail the model we created in order to represent the system, to simulate its behavior and to combine the measurement data to extract the desired concentration. During this step, we focus on the obstacles of our model calibration and the deviation compensation, due toworking conditions or to components aging process. Based on this development, we finally designed the hybrid models addressing the nominal working cases and the model re-calibration during the working duration of the product. After this, we presented obtained results, on simulated data, and on real-world measured data. Finally, we enhanced the methodology based on tabulated “black box” models which are easier to calibrate and cheaper to process. In conclusion, we reapplied our methodology to a different motion capture sensor, to compile all possible solutions and limits
Nguyen, Thanh Long. "Fusion d'informations multi-capteurs pour la commande du robot humanoïde NAO." Thesis, Université Grenoble Alpes (ComUE), 2017. http://www.theses.fr/2017GREAA010/document.
Full textBeing interested in the important role of robotics in human life, we do a research about the improvement in reliability of a humanoid robot NAO by using multi-sensor fusion. In this research, we propose two scenarios: the color detection and the object recognition. In these two cases, a camera of the robot is used in combination with external cameras to increase the reliability under non-ideal working conditions. For the color detection, the NAO robot is requested to find an object whose color is described in human terms such as: red, yellow, brown, etc. The main problem to be solved is how the robot recognizes the colors as well as the human perception does. To do that, we propose a Fuzzy Sugeno system to decide the color of a detected target. For simplicity, the chosen targets are colored balls, so that the Hough transformation is employed to extract the average pixel values of the detected ball, then these values are used as the inputs for the Fuzzy system. The membership functions and inference rules of the system are constructed based on perceptual evaluation of human. The output of the Fuzzy system is a numerical value indicating a color name. Additionally, a threshold value is introduced to define the zone of decision for each color. If the Fuzzy output falls into a color interval constructed by the threshold value, that color is considered to be the output of the system. This is considered to be a good solution in an ideal condition, but not in an environment with uncertainties and imprecisions such as light variation, or sensor quality, or even the similarity among colors. These factors really affect the detection of the robot. Moreover, the introduction of the threshold value also leads to a compromise between uncertainty and reliability. If this value is small, the decisions are more reliable, but the number of uncertain cases are increases, and vice versa. However, the threshold value is preferred to be small after an experimental validation, so the need for a solution of uncertainty becomes more important. To do that, we propose adding more 2D cameras into the detection system of the NAO robot. Each camera applies the same method as described above, but their decisions are fused by using the Dempster-Shafer theory in order to improve the detection rate. The threshold value is taken into account to construct mass values from the Sugeno Fuzzy output of each camera. The Dempster-Shafer's rule of combination and the maximum of pignistic probability are chosen in the method. According to our experimens, the detection rate of the fusion system is really better than the result of each individual camera. We extend this recognition process for colored object recognition. These objects are previously learned during the training phase. To challenge uncertainties and imprecisions, the chosen objects look similar in many points: geometrical form, surface, color, etc. In this scenario, the recognition system has two 2D cameras: one of NAO and one is an IP camera, then we add a 3D camera to take the advantages of depth information. For each camera, we extract feature points of the objects (SURF descriptor for 2D data, and the SHOT descriptor for 3D data). To combine the cameras in the recognition system, the Dempster-Shafer theory is again employed for the fusion. Based on the correspondence to trained models stored in the learning base, each feature point of the detected object votes for one or several classes i.e. a hypothesis in the power set. We construct a mass function after a normalization step. In this case, the Dempster-Shafer's rule of combination and the maximum of pignistic probability are employed to make the final decision. After doing three experiments, we conclude that the recognition rate of the fusion system is much better than the rate of each individual camera, from that we confirm the benefits of multi-sensor fusion for the robot's reliability
Mazouni, Karim. "Fusion de capteurs radars et infrarouge pour l'aide au pilotage d'hélicoptère." Phd thesis, Université de Nice Sophia-Antipolis, 2011. http://tel.archives-ouvertes.fr/tel-00832147.
Full textAhmed, Bacha Adda Redouane. "Localisation multi-hypothèses pour l'aide à la conduite : conception d'un filtre "réactif-coopératif"." Thesis, Evry-Val d'Essonne, 2014. http://www.theses.fr/2014EVRY0051/document.
Full text“ When we use information from one source,it's plagiarism;Wen we use information from many,it's information fusion ”This work presents an innovative collaborative data fusion approach for ego-vehicle localization. This approach called the Optimized Kalman Particle Swarm (OKPS) is a data fusion and an optimized filtering method. Data fusion is made using data from a low cost GPS, INS, Odometer and a Steering wheel angle encoder. This work proved that this approach is both more appropriate and more efficient for vehicle ego-localization in degraded sensors performance and highly nonlinear situations. The most widely used vehicle localization methods are the Bayesian approaches represented by the EKF and its variants (UKF, DD1, DD2). The Bayesian methods suffer from sensitivity to noises and instability for the highly non-linear cases. Proposed for covering the Bayesian methods limitations, the Multi-hypothesis (particle based) approaches are used for ego-vehicle localization. Inspired from monte-carlo simulation methods, the Particle Filter (PF) performances are strongly dependent on computational resources. Taking advantages of existing localization techniques and integrating metaheuristic optimization benefits, the OKPS is designed to deal with vehicles high nonlinear dynamic, data noises and real time requirement. For ego-vehicle localization, especially for highly dynamic on-road maneuvers, a filter needs to be robust and reactive at the same time. The OKPS filter is a new cooperative-reactive localization algorithm inspired by dynamic Particle Swarm Optimization (PSO) metaheuristic methods. It combines advantages of the PSO and two other filters: The Particle Filter (PF) and the Extended Kalman filter (EKF). The OKPS is tested using real data collected using a vehicle equipped with embedded sensors. Its performances are tested in comparison with the EKF, the PF and the Swarm Particle Filter (SPF). The SPF is an interesting particle based hybrid filter combining PSO and particle filtering advantages; It represents the first step of the OKPS development. The results show the efficiency of the OKPS for a high dynamic driving scenario with damaged and low quality GPS data
Izri-Lahleb, Sonia. "Architecture de fusion de données pour le suivi dynamique de véhicules." Amiens, 2006. http://www.theses.fr/2006AMIE0603.
Full textPeyraud, Sébastien. "Localisation 3D de mobile en milieu urbain par fusion d’informations satellitaires, proprioceptives et cartographiques." Limoges, 2012. https://aurore.unilim.fr/theses/nxfile/default/1bba77a7-475c-406c-83b3-f9c39f532397/blobholder:0/2012LIMO4026.pdf.
Full textThis work joins in the search for the control of land mobiles localization by using jointly informations outcomes from satellite constellations, from Geographical Information Systems and from vehicle motion sensors. It is characterized: -by a description of the environment in 3 dimensions (generally restricted to the 2 dimensions of a flat world). The localization consists then in estimating a 6 dimensional configuration vector instead of 3 in a flat world. This concern allows in particular to consider if, because of the occultation by buildings, satellites are in direct view or not. -by the joint use of raw satellite informations to cartographic data and to proprioceptive measurements, designated by the concept of tight coupling. The tight coupling allows to benefit from situations where the receiver receives information of few satellites as it is the case in urban environments where the sky visibility is restricted. -by the joint use of estimation algorithms based on stochastic (Kalman filtering) or set-membership models of uncertainties. -by the experimentation of the proposed methods on real data sets. In particular, the data processing of the final demonstration of the CityVIP project (ANR-07-TSFA-013-01 ), realized in Paris, brings a lot of credibility to the proposed methods. The presented results establish a technological brick in the constitution of Individual Vehicles Public (VIP). This approach by technological brick was motivated by the fact that this thesis synthesizes a set of works carried out in the CityVIP project
Kmiotek, Pawel. "Fusion multi-capteurs pour la représentation et le suivi des objets dynamiques." Phd thesis, Belfort-Montbéliard, 2009. http://tel.archives-ouvertes.fr/tel-00608155.
Full textNowakowski, Mathieu. "Localisation d'un robot humanoïde en milieu intérieur non-contraint." Thesis, Paris Sciences et Lettres (ComUE), 2019. http://www.theses.fr/2019PSLEM026/document.
Full textAfter the democratization of industrial robots, the current trend is the development of social robots that create strong interactions with their users. The deployment of such platforms in shops, museums or train stations raises various issues including the autonomous localization of mobile robots. This thesis focuses on the localization of Pepper robots in a non-constrained indoor environment. Pepper robots are daily used in many shops in Japan and must be as autonomous as possible. However, localization solutions in the literature suffer from the limitations of the platform. This thesis is split into two main themes. First, the problem of relocalization in a visually redundant environment is studied. The proposed solution combines vision and Wi-Fi in a probabilistic approach based on the appearance. Then, the question of a consistent metrical mapping is examined. In order to compensate the numerous losses of tracking caused by the low acquisition frequency, odometric constraints are added to a bundle adjustment optimization. These solutions have been tested and validated on several Pepper robots, from data collected in different indoor environments over more than 7 km
Selloum, Ahmed. "Localisation multi-capteurs d'un véhicule routier sous contraintes cartographiques : mise en oeuvre d'un filtre particulaire et d'une modélisation multivoies de la route par des clothoïdes." Nantes, 2010. http://www.theses.fr/2010NANT2085.
Full textIn the field of Intelligent Transportation Systems, many Advanced Driver Assistance Systems require reliable and precise location of the vehicle in real time on a digital map. The GPS technology, combined with a standard map, is generally satisfactory for conventional navigation systems, however, it suffers from serious problems when the application requires an accuracy at a road lane level with a confidence indicator associated. The thesis is based on three proposals that bring an innovative solution to the problem : 1) the use of a precise digital map describing all the lanes of the road as a series of clothoïds (spirals), 2) the choice of a discrete-continuous state vector that comprises directly the coordinates of the vehicle on the map, 3) the use of a particle filter that can handle multiple hypotheses, estimate the probabilities associated with each of them and apply easily cartographic constraints. From a practical standpoint, this assignment of the vehicle to a road lane on the map is important because the driving rules and some driver information are tied to the infrastructure at this level of detail. The implementation of this system was conducted in two steps. First, the location of the vehicle is done by a particle filter with space constraints defined by a precise map. The results obtained from simulation and real data show in detail the interests of the proposed method compared to a conventional system. In a second step, the use of the directional constraint of the road and of a vehicle evolution multi-model allows to remedy the possible effects of a bad gyro
Sandu, Popa Iulian. "Modélisation, interrogation et indexation de données de capteurs à localisation mobile dans un réseau routier." Versailles-St Quentin en Yvelines, 2009. http://www.theses.fr/2009VERS0015.
Full textNew technologies such as GPS, sensors and ubiquitous computing are pervading our society. The movement of people and vehicles may be sensed and recorded, thus producing large volumes of mobility data. The state-of-the-art database management systems fail to handle such complex data and their processing. This thesis addresses the problem of managing mobile location sensor data. We analyze the limitations of existing work in modeling, querying and indexing moving objects with sensors on road networks. Then, we propose new solutions to deal with these limitations. The main contributions of the thesis are a data model and a query language for moving sensor data, and an access method for in-network trajectories of moving objects. We have implemented these proposals as a spatio-temporal database management system extension and evaluated them
Kétata, Mohamed. "Capteurs à fibres optiques pour la détection et la localisation des contraintes et déformations." Châtenay-Malabry, Ecole centrale de Paris, 1989. http://www.theses.fr/1989ECAP0094.
Full textGallichand, Mathieu. "Réalisation d'un réseau linéaire de capteurs acoustiques pour la localisation de sources sonores distordues." Master's thesis, Université Laval, 2014. http://hdl.handle.net/20.500.11794/25620.
Full textIn this project, we present the algorithms and the hardware used to locate acoustic sources affected by distortion. The designed acquisition system is a linear array of acoustic sensors. It allows the recording of experimental data and is flexible for the choice of its parameters. Among others, the system uses up to 12 sensors, a variable spacing between them and variable gain amplification. The propagation of the sound waves in air is affected by the environment inhomogeneity, which causes wavefront distortion. Classical algorithms, which don’t take into account the distortion, and other algorithms, recovering distorted wavefronts, are used to locate sources. The effects of wavefront distortion are then observed. Monochromatic signals, using the phase differences, and impact signals, using time difference of arrivals, are both located.
Lamard, Laetitia. "Approche modulaire pour le suivi temps réel de cibles multi-capteurs pour les applications routières." Thesis, Clermont-Ferrand 2, 2014. http://www.theses.fr/2014CLF22477/document.
Full textThis PhD work, carried out in collaboration with Institut Pascal and Renault, is in the field of the Advanced Driving Assisted Systems, most of these systems aiming to improve passenger security. Sensors fusion makes the system decision more reliable. The goal of this PhD work was to develop a fusion system between a radar and a smart camera, improving obstacles detection in front of the vehicle. Our approach proposes a real-time flexible fusion architecture system using asynchronous data from the sensors without any prior knowledge about the application. Our fusion system is based on a multi targets tracking method. Probabilistic multi target tracking was considered, and one based on random finite sets (modelling targets) was selected and tested in real-time computation. The filter, named CPHD (Cardinalized Probability Hypothesis Density), succeed in taking into account and correcting all sensor defaults (non detections, false alarms and imprecision on position and speed estimated by sensors) and uncertainty about the environment (unknown number of targets). This system was improved by introducing the management of the type of the target: pedestrian, car, truck and bicycle. A new system was proposed, solving explicitly camera occlusions issues by a probabilistic method taking into account this sensor imprecision. Smart sensors use induces data correlation (due to pre-processed data). This issue was solved by correcting the estimation of sensor detection performance. A new tool was set up to complete fusion system: it allows the estimation of all sensors parameters used by fusion filter. Our system was tested in real situations with several experimentations. Every contribution was qualitatively and quantitatively validated
Vincke, Bastien. "Architectures pour des systèmes de localisation et de cartographie simultanées." Phd thesis, Université Paris Sud - Paris XI, 2012. http://tel.archives-ouvertes.fr/tel-00770323.
Full textHeurtefeux, Karel. "Protocoles Localisés pour Réseaux de Capteurs." Phd thesis, INSA de Lyon, 2009. http://tel.archives-ouvertes.fr/tel-00449801.
Full textMagnier, Valentin. "Fusion de données multi-capteurs pour l'estimation de la zone navigable pour le véhicule à conduite automatisée." Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLE003/document.
Full textIn this PhD Thesis, we have developed a multi-sensors data-fusion architecture dedicated to the estimation of the free-space zone surrounding the vehicle. This system is modular according the sensors configuration of the vehicle. It provides to the customer applications a reliable representation of the road scene's actors that are perceived by the embedded sensors. It is also able to predict what the road scene will be in a few seconds.Meta information such as speed or type of object are provided to customer applications (in our case, the supervisor part of an autonomous vehicle).The proposed algorithm is able to work with various types of sensors (LiDAR, radar, ...) that can even run at different frequencies. It is based on a model of the road environment using two dedicated algorithms: one for the moving obstacles and another for the static scene
Manerikar, Ninad. "Fusion de capteurs visuels-inertiels et estimation d'état pour la navigation des véhicules autonomes." Thesis, Université Côte d'Azur, 2022. http://www.theses.fr/2022COAZ4111.
Full textAccurate state estimation is a fundamental problem for the navigation of Autonomous vehicles. This is particularly important when the vehicle is navigating through cluttered environments or it has to navigate in close proximity to its physical surroundings in order to perform localization, obstacle avoidance, environmental mapping etc. Although several algorithms were proposed in the past for this problem of state estimtation, they were usually applied to a single sensor or a specific sensor suite. To this end, researchers in the computer vision and control community came up with a visual-inertial framework (Camera + Imu) that exploit the combined properties of this sensor suite to produce precise local estimates (position, orientation, velocity etc). Taking inspiration from this, my thesis focuses on developing nonlinear observers for State Estimation by exploiting the classical Riccati design framework with a particular emphasis on visual-inertial sensor fusion. In the context of this thesis, we use a suite of low-cost sensors consisting of a monocular camera and an IMU. Throughout the thesis, the assumption on the planarity of the visual target has been considered. In the present thesis, two research topics have been considered. Firstly, an extensive study for the existing techniques for homography estimation has been carried out after which a novel nonlinear observer on the SL(3) group has been proposed with application to optical flow estimation. The novelty lies in the linearization approach undertaken to linearize a nonlinear observer on SL(3), thus making it more simplistic and suitable for practical implementation. Then, another novel observer based on deterministic Ricatti observer has been proposed for the problem of partial attitude, linear velocity and depth estimation for planar targets. The proposed approach does not rely on the strong assumption that the IMU provides the measurements of the vehicle’s linear acceleration in the body-fixed frame. Again experimental validations have been carried out to show the performance of the observer. An extension to this observer has been further proposed to filter the noisy optical flow estimates obtained from the extraction of continuous homography. Secondly, two novel observers for tackling the classical problem of homography decomposition have been proposed. The key contribution here lies in the design of two deterministic Riccati observers for addressing the homography decomposition problem instead of solving it on a frame-by-frame basis like traditional algebraic approaches. The performance and robustness of the observers have been validated over simulations and practical experiments. All the observers proposed above are part of the Homography-Lab library that has been evaluated at the TRL 7 (Technology Readiness Level) and is protected by the French APP (Agency for the Protection of Programs) which serves as the main brick for various applications like velocity, optical flow estimation and visual homography based stabilization
Corrêa, Victorino Alessandro. "La commande référencée capteur : une approche robuste au problème de navigation, localisation et cartographie simultanées pour un robot d'intérieur." Nice, 2002. http://www.theses.fr/2002NICE5748.
Full textWelte, Anthony. "Spatio-temporal data fusion for intelligent vehicle localization." Thesis, Compiègne, 2020. http://bibliotheque.utc.fr/EXPLOITATION/doc/IFD/2020COMP2572.
Full textLocalization is an essential basic capability for vehicles to be able to navigate autonomously on the road. This can be achieved through already available sensors and new technologies (Iidars, smart cameras). These sensors combined with highly accurate maps result in greater accuracy. In this work, the benefits of storing and reusing information in memory (in data buffers) are explored. Localization systems need to perform a high-frequency estimation, map matching, calibration and error detection. A framework composed of several processing layers is proposed and studied. A main filtering layer estimates the vehicle pose while other layers address the more complex problems. High-frequency state estimation relies on proprioceptive measurements combined with GNSS observations. Calibration is essential to obtain an accurate pose. By keeping state estimates and observations in a buffer, the observation models of these sensors can be calibrated. This is achieved using smoothed estimates in place of a ground truth. Lidars and smart cameras provide measurements that can be used for localization but raise matching issues with map features. In this work, the matching problem is addressed on a spatio-temporal window, resulting in a more detailed pictur of the environment. The state buffer is adjusted using the observations and all possible matches. Although using mapped features for localization enables to reach greater accuracy, this is only true if the map can be trusted. An approach using the post smoothing residuals has been developed to detect changes and either mitigate or reject the affected features
Samain, Olivier. "Fusion multi-capteurs de données satellitaires optiques pour la restitution de variables biophysiques de surface." Toulouse 3, 2006. http://www.theses.fr/2006TOU30035.
Full textThis work aims at improving the determination of surface biophysical parameters, such as albedo, leaf area index or fraction of vegetation cover, by combining data from different wide field optical sensors like VEGETATION, MERIS, AVHRR, or POLDER. The multi-sensor fusion requires the application of a spectral normalization to compensate the spectral responses of the different sensors, which is validated with airborne hyperspectral measurements and MERIS and VEGETATION datasets. The fusion of measurements at different spatial resolutions is based on the use of a Kalman filter for the downscaling of the low resolution data. The latter also gives the possibility to deliver continuous products, contrarily to standard regressions methods that are limited in the case of cloud coverage
Seba, Ali. "Fusion de données capteurs visuels et inertiels pour l'estimation de la pose d'un corps rigide." Thesis, Versailles-St Quentin en Yvelines, 2015. http://www.theses.fr/2015VERS020V/document.
Full textAbstractThis thesis addresses the problems of pose estimation of a rigid body moving in 3D space by fusing data from inertial and visual sensors. The inertial measurements are provided from an I.M.U. (Inertial Measurement Unit) composed by accelerometers and gyroscopes. Visual data are from cameras, which positioned on the moving object, provide images representative of the perceived visual field. Thus, the implicit measure directions of fixed lines in the space of the scene from their projections on the plane of the image will be used in the attitude estimation. The approach was first to address the problem of measuring visual sensors after a long sequence using the characteristics of the image. Thus, a line tracking algorithm has been proposed based on optical flow of the extracted points and line matching approach by minimizing the Euclidean distance. Thereafter, an observer in the SO(3) space has been proposed to estimate the relative orientation of the object in the 3D scene by merging the data from the proposed lines tracking algorithm with Gyro data. The observer gain was developed using a Kalman filter type M.E.K.F. (Multiplicative Extended Kalman Filter). The problem of ambiguity in the sign of the measurement directions of the lines was considered in the design of the observer. Finally, the estimation of the relative position and the absolute velocity of the rigid body in the 3D scene have been processed. Two observers were proposed: the first one is an observer cascaded with decoupled from the estimation of the attitude and position estimation. The estimation result of the attitude observer feeds a nonlinear observer using measurements from the accelerometers in order to provide an estimate of the relative position and the absolute velocity of the rigid body. The second observer, designed directly in SE (3) for simultaneously estimating the position and orientation of a rigid body in 3D scene by fusing inertial data (accelerometers, gyroscopes), and visual data using a Kalman filter (M.E.K.F.). The performance of the proposed methods are illustrated and validated by different simulation results
Lahrech, Abdelkabir. "Perception multi-capteurs pour la navigation par satellites en milieu urbain." Littoral, 2006. http://www.theses.fr/2006DUNK0165.
Full textThis work deals with the multisensory perception for satellites navigation. The idea is to get a continuous and efficient positioning of the vehicule in urban environment where GPS outages occur. We hybrided a GPS receiver and low-cost dead reckoning sensors. One of the most popular is the odometer which is a sensor available as a standard component in Antilock Brakink System (ABS) of vehicules. When GPS fails, the odometers allow a continuous positioning. We also use a road map database which improves the vehicle positioning. To solve this multisensor fusion problem, we develop a solution based on an “Unscented” Kalman filter and a particle filter that allow a direct integration of the measurements. The originality of this work relies on a modeling of the odometer which is described like a speed sensor. The statistical use of the road map measurements is based on the Mahalanobis metric. Finally, we propose a navigation method when partial GPS outages occur. In this case, the filter also fuses the available pseudo-ranges even if they are not enough to get a GPS positioning