Thèses sur le sujet « Slam LiDAR »
Pour voir les autres types de publications sur ce sujet consultez le lien suivant : Slam LiDAR.
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les 32 meilleures thèses pour votre recherche sur le sujet « Slam LiDAR ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Parcourez les thèses sur diverses disciplines et organisez correctement votre bibliographie.
1
Nava, Chocron Yoshua. « Visual-LiDAR SLAM with loop closure ». Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-265532.
Texte intégralRésumé :
State-of-the-art LIDAR odometry techniques are exceptionally precise. However, while they solve the localization problem, they perform mapping on-the-run, not being able to close loops, neither re-localize in previously visited environments. This study is concerned with the development of a system that combines an accurate laser odometry estimator, with algorithms for place recognition in order to detect trajectory loops. This project uses widely available datasets from urban driving scenarios and outdoor areas for development and evaluation of the system The results obtained confirm that loop closure detection can significantly improve the accuracy and robustness of laser SLAM pipelines, with detectors based on point cloud segments and visual features displaying very strong performance during the evaluation phase.Spjutspetsen inom Lidar-baserade teknik för fordonsodometri har den senaste tiden uppnått exceptionella nivåer av noggrannhet. Med det sagt har de metoder som presenterats fokuserat på att lösa lokaliseringsproblemet och därför gjort förenklande antaganden såsom att de sköter kartläggning av miljön löpande utan platsåterkoppling, och att de inte kan återlokalisera i tidigare kända miljöer. Således utvecklar vi i detta arbete ett system som kombinerar dessa noggranna lidarodometriska tekniker med algoritmer för platsigenkänning för att möjliggöra loopdetektion. Vi använder vitt tillgängliga dataset av körning i stadstrafik samt i utomhusområden för utveckling och utvärdering av systemet. Resultaten visar att platsåterkoppling förbättrar noggrannheten hos Lidar-baserade lokaliseringsmetoder och gör dem mer robusta, samt att man med hjälp av detektorer baserade på punktmolnssegmentering och visuella särdrag erhåller ett system som uppvisar mycket goda resultat under utvärderingsfasen.
2
Contreras, Samamé Luis Federico. « SLAM collaboratif dans des environnements extérieurs ». Thesis, Ecole centrale de Nantes, 2019. http://www.theses.fr/2019ECDN0012/document.
Texte intégralRésumé :
Cette thèse propose des modèles cartographiques à grande échelle d'environnements urbains et ruraux à l'aide de données en 3D acquises par plusieurs robots. La mémoire contribue de deux manières principales au domaine de recherche de la cartographie. La première contribution est la création d'une nouvelle structure, CoMapping, qui permet de générer des cartes 3D de façon collaborative. Cette structure s’applique aux environnements extérieurs en ayant une approche décentralisée. La fonctionnalité de CoMapping comprend les éléments suivants : Tout d’abord, chaque robot réalise la construction d'une carte de son environnement sous forme de nuage de points.Pour cela, le système de cartographie a été mis en place sur des ordinateurs dédiés à chaque voiture, en traitant les mesures de distance à partir d'un LiDAR 3D se déplaçant en six degrés de liberté (6-DOF). Ensuite, les robots partagent leurs cartes locales et fusionnent individuellement les nuages de points afin d'améliorer leur estimation de leur cartographie locale. La deuxième contribution clé est le groupe de métriques qui permettent d'analyser les processus de fusion et de partage de cartes entre les robots. Nous présentons des résultats expérimentaux en vue de valider la structure CoMapping et ses métriques. Tous les tests ont été réalisés dans des environnements extérieurs urbains du campus de l’École Centrale de Nantes ainsi que dans des milieux rurauxThis thesis proposes large-scale mapping model of urban and rural environments using 3D data acquired by several robots. The work contributes in two main ways to the research field of mapping. The first contribution is the creation of a new framework, CoMapping, which allows to generate 3D maps in a cooperative way. This framework applies to outdoor environments with a decentralized approach. The CoMapping's functionality includes the following elements: First of all, each robot builds a map of its environment in point cloud format.To do this, the mapping system was set up on computers dedicated to each vehicle, processing distance measurements from a 3D LiDAR moving in six degrees of freedom (6-DOF). Then, the robots share their local maps and merge the point clouds individually to improve their local map estimation. The second key contribution is the group of metrics that allow to analyze the merging and card sharing processes between robots. We present experimental results to validate the CoMapping framework with their respective metrics. All tests were carried out in urban outdoor environments on the surrounding campus of the École Centrale de Nantes as well as in rural areas
3
Dellenbach, Pierre. « Exploring LiDAR Odometries through Classical, Deep and Inertial perspectives ». Electronic Thesis or Diss., Université Paris sciences et lettres, 2023. http://www.theses.fr/2023UPSLM069.
Texte intégralRésumé :
Les LiDARS 3D se sont largement démocratisés ces dernières années, poussés notamment par le développement des véhicules automones, et la nécessité de redondance et de sécurité. Contrairement aux caméras, les LiDAR 3D fournissent des mesures 3D de l'environnement très précises. Cela a conduit au développement de différents algorithmes de cartographie et de SLAM (Simultaneous Localization and Mapping), utilisant ces nouvelles modalités. Ces algorithmes ont vite dépassé les capacités des systèmes basés sur les caméras. Un élément crucial de ces systèmes est le problèmed'odométrie LiDAR, qui désigne le problème d'estimation de trajectoire du capteur, en utilisant uniquement le flux continu de mesures de LiDAR. Ce travail se concentre sur ce problème. Plus précisément, dans ce manuscrit nous visons à repousser les performances des odométries LiDAR.Pour atteindre cet objectif, nous explorons d'abord les méthodes classiques (ou géométriques) d'odométrie LiDAR. Nousproposons notamment deux nouvelles méthodes d'odométrie LiDAR dans le chapitre 3. Nous en montrons les forces etles faiblesses. Pour tâcher de répondre à ces limites, nous regardons de plus près les méthodes d'odométrie utilisant leDeep Learning dans le chapitre 4, en nous concentrant notamment sur les méthodes de type "boîte noires". Finalement,dans le chapitre 5 nous fusionnons les mesures LiDAR et les mesures inertielles pour rechercher encore plus de précisionet de robustesse3D LiDARs have become increasingly popular in the past decade, notably motivated by the safety requirements of autonomous driving requiring new sensor modalities. Contrary to cameras, 3D LiDARs provide direct, and extremely precise 3D measurements of the environment. This has led to the development of many different mapping and Simultaneous Localization And Mapping (SLAM) solutions leveraging this new modality. These algorithms quickly performed much better than their camera-based counterparts, as evidenced by several open-source benchmarks. One critical component ofthese systems is LiDAR odometry. A LiDAR odometry is an algorithm estimating the trajectory of the sensor, given only the iterative integration of the LiDAR measurements. The focus of this work is on the topic of LiDAR Odometries. More precisely, we aim to push the boundaries of LiDAR odometries, both in terms of precision and performance.To achieve this, we first explore classical LiDAR odometries in depth, and propose two novel LiDAR odometries, in chapter 3. We show the strength, and limitations of such methods. Then, to address to improve them we first investigate Deep Learning for LiDAR odometries in chapter 4, notably focusing on end-to-end odometries. We show again the limitations of such approaches and finally investigate in chapter 5 fusing inertial and LiDAR measurements
4
Bruns, Christian. « Lidar-based Vehicle Localization in an Autonomous Valet Parking Scenario ». The Ohio State University, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=osu1461236677.
Texte intégral
5
Ekström, Joakim. « 3D Imaging Using Photon Counting Lidar on a Moving Platform ». Thesis, Linköpings universitet, Reglerteknik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-153297.
Texte intégralRésumé :
The problem of constructing high quality point clouds based on measurements from a moving and rotating single-photon counting lidar is considered in this report. The movement is along a straight rail while the lidar sensor rotates side to side. The point clouds are constructed in three steps, which are all studied in this master’s thesis. First, point clouds are constructed from raw lidar measurements from single sweeps with the lidar. In the second step, the sensor transformation between the point clouds constructed in the first step are obtained in a registration step using iterative closest point (ICP). In the third step the point clouds are combined to a coherent point cloud, using the full measurement. A method using simultaneous localization and mapping (SLAM) is developed for the third step. It is then compared to two other methods, constructing the final point cloud only using the registration, and to utilize odometric information in the combination step. It is also investigated which voxel discretization that should be used when extracting the point clouds. The methods developed are evaluated using experimental data from a prototype photon counting lidar system. The results show that the voxel discretization need to be at least as large as the range quantization in the lidar. No significant difference between using registration and SLAM in the third step is observed, but both methods outperform the odometric method.
6
Zhang, Erik. « Integration of IMU and Velodyne LiDAR sensor in an ICP-SLAM framework ». Thesis, KTH, Optimeringslära och systemteori, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-193653.
Texte intégralRésumé :
Simultaneous localization and mapping (SLAM) of an unknown environment is a critical step for many autonomous processes. For this work, we propose a solution which does not rely on storing descriptors of the environment and performing descriptors filtering. Compared to most SLAM based methods this work with general sparse point clouds with the underlying generalized ICP (GICP) algorithm for point cloud registration. This thesis presents a modified GICP method and an investigation of how and if an IMU can assist the SLAM process by different methods of integrating the IMU measurements. All the data in this thesis have been sampled from a LiDAR scanner mounted on top of an UAV, a car or on a backpack. Suggested modification on GICP have shown to improve robustness in a forest environment. From urban measurements the result indicates that IMU contributes by reducing the overall angular drift, which in a long run is contributing most to the loop closure error.Lokalisering och kartläggning (SLAM) i en okänd miljö är ett viktigt steg för många autonoma system. Den föreslagna lösningen är inte beroende på att hitta nyckelpunkter eller nyckelobjekt. Till skillnad från många andra SLAM baserade metoder så arbetar denna metod med glesa punktmoln där 'generalized ICP' (GICP)algoritmen används för punktmolns registrering. I denna uppsats så föreslås en variant av GICP och undersöker, ifall en tröghetssensor (IMU) kan hjälpa till med SLAM-processen. LiDAR-data som har använts i denna uppsats har varit uppmätta från en Velodyne LiDAR monterat på en ryggsäck, en bil och på en UAV. Resultatet tyder på att IMU-data kan göra algoritmen robustare och från mätningar i stadsmiljö så visar det sig att IMU kan hjälpa till att minska vinkeldrift, vilket är det största felkällan för noggrannhet i det globala koordinat systemet.
7
Gonzalez, Cadenillas Clayder Alejandro. « An improved feature extractor for the lidar odometry and mapping algorithm ». Tesis, Universidad de Chile, 2019. http://repositorio.uchile.cl/handle/2250/171499.
Texte intégralRésumé :
Tesis para optar al grado de Magíster en Ciencias de la Ingeniería, Mención EléctricaLa extracción de características es una tarea crítica en la localización y mapeo simultáneo o Simultaneous Localization and Mapping (SLAM) basado en características, que es uno de los problemas más importantes de la comunidad robótica. Un algoritmo que resuelve SLAM utilizando características basadas en LiDAR es el algoritmo LiDAR Odometry and Mapping (LOAM). Este algoritmo se considera actualmente como el mejor algoritmo SLAM según el Benchmark KITTI. El algoritmo LOAM resuelve el problema de SLAM a través de un enfoque de emparejamiento de características y su algoritmo de extracción de características detecta las características clasifican los puntos de una nube de puntos como planos o agudos. Esta clasificación resulta de una ecuación que define el nivel de suavidad para cada punto. Sin embargo, esta ecuación no considera el ruido de rango del sensor. Por lo tanto, si el ruido de rango del LiDAR es alto, el extractor de características de LOAM podría confundir los puntos planos y agudos, lo que provocaría que la tarea de emparejamiento de características falle. Esta tesis propone el reemplazo del algoritmo de extracción de características del LOAM original por el algoritmo Curvature Scale Space (CSS). La elección de este algoritmo se realizó después de estudiar varios extractores de características en la literatura. El algoritmo CSS puede mejorar potencialmente la tarea de extracción de características en entornos ruidosos debido a sus diversos niveles de suavizado Gaussiano. La sustitución del extractor de características original de LOAM por el algoritmo CSS se logró mediante la adaptación del algoritmo CSS al Velodyne VLP-16 3D LiDAR. El extractor de características de LOAM y el extractor de características de CSS se probaron y compararon con datos reales y simulados, incluido el dataset KITTI utilizando las métricas Optimal Sub-Pattern Assignment (OSPA) y Absolute Trajectory Error (ATE). Para todos estos datasets, el rendimiento de extracción de características de CSS fue mejor que el del algoritmo LOAM en términos de métricas OSPA y ATE.
8
Paiva, mendes Ellon. « Study on the Use of Vision and Laser Range Sensors with Graphical Models for the SLAM Problem ». Thesis, Toulouse, INSA, 2017. http://www.theses.fr/2017ISAT0016/document.
Texte intégralRésumé :
La capacité des robots mobiles à se localiser précisément par rapport à leur environnement est indispensable à leur autonomie. Pour ce faire, les robots exploitent les données acquises par des capteurs qui observent leur état interne, tels que centrales inertielles ou l’odométrie, et les données acquises par des capteurs qui observent l’environnement, telles que les caméras et les Lidars. L’exploitation de ces derniers capteurs a suscité le développement de solutions qui estiment conjointement la position du robot et la position des éléments dans l'environnement, appelées SLAM (Simultaneous Localization and Mapping). Pour gérer le bruit des données provenant des capteurs, les solutions pour le SLAM sont mises en œuvre dans un contexte probabiliste. Les premiers développements étaient basés sur le filtre de Kalman étendu, mais des développements plus récents utilisent des modèles graphiques probabilistes pour modéliser le problème d’estimation et de le résoudre grâce à techniques d’optimisation. Cette thèse exploite cette dernière approche et propose deux techniques distinctes pour les véhicules terrestres autonomes: une utilisant la vision monoculaire, l’autre un Lidar. L’absence d’information de profondeur dans les images obtenues par une caméra a mené à l’utilisation de paramétrisations spécifiques pour les points de repères qui isolent la profondeur inconnue dans une variable, concentrant la grande incertitude sur la profondeur dans un seul paramètre. Une de ces paramétrisations, nommé paramétrisation pour l’angle de parallaxe (ou PAP, Parallax Angle Parametrization), a été introduite dans le contexte du problème d’ajustement de faisceaux, qui traite l’ensemble des données en une seule étape d’optimisation globale. Nous présentons comment exploiter cette paramétrisation dans une approche incrémentale de SLAM à base de modèles graphiques, qui intègre également les mesures de mouvement du robot. Les Lidars peuvent être utilisés pour construire des solutions d’odométrie grâce à un recalage séquentiel des nuages de points acquis le long de la trajectoire. Nous définissons une couche basée sur les modèles graphiques au dessus d’une telle couche d’odométrie, qui utilise l’algorithme ICP (Iterative Closest Points). Des repères clefs (keyframes) sont définis le long de la trajectoire du robot, et les résultats de l’algorithme ICP sont utilisés pour construire un graphe de poses, exploité pour résoudre un problème d’optimisation qui permet la correction de l’ensemble de la trajectoire du robot et de la carte de l’environnement à suite des fermetures de boucle.Après une introduction à la théorie des modèles graphiques appliquée au problème de SLAM, le manuscrit présente ces deux approches. Des résultats simulés et expérimentaux illustrent les développements tout au long du manuscrit, en utilisant des jeux des données classiques et obtenus au laboratoireA strong requirement to deploy autonomous mobile robots is their capacity to localize themselves with a certain precision in relation to their environment. Localization exploits data gathered by sensors that either observe the inner states of the robot, like acceleration and speed, or the environment, like cameras and Light Detection And Ranging (LIDAR) sensors. The use of environment sensors has triggered the development of localization solutions that jointly estimate the robot position and the position of elements in the environment, referred to as Simultaneous Localization and Mapping (SLAM) approaches. To handle the noise inherent of the data coming from the sensors, SLAM solutions are implemented in a probabilistic framework. First developments were based on Extended Kalman Filters, while a more recent developments use probabilistic graphical models to model the estimation problem and solve it through optimization. This thesis exploits the latter approach to develop two distinct techniques for autonomous ground vehicles: oneusing monocular vision, the other one using LIDAR. The lack of depth information in camera images has fostered the use of specific landmark parametrizations that isolate the unknown depth in one variable, concentrating its large uncertainty into a single parameter. One of these parametrizations, named Parallax Angle Parametrization, was originally introduced in the context of the Bundle Adjustment problem, that processes all the gathered data in a single global optimization step. We present how to exploit this parametrization in an incremental graph-based SLAM approach in which robot motion measures are also incorporated. LIDAR sensors can be used to build odometry-like solutions for localization by sequentially registering the point clouds acquired along a robot trajectory. We define a graphical model layer on top of a LIDAR odometry layer, that uses the Iterative Closest Points (ICP) algorithm as registration technique. Reference frames are defined along the robot trajectory, and ICP results are used to build a pose graph, used to solve an optimization problem that enables the correction of the robot trajectory and the environment map upon loop closures. After an introduction to the theory of graphical models applied to SLAM problem, the manuscript depicts these two approaches. Simulated and experimental results illustrate the developments throughout the manuscript, using classic and in-house datasets
9
Chghaf, Mohammed. « Towards a Multimodal Loop Closure System for Real-Time Embedded SLAM Applications ». Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPAST133.
Texte intégralRésumé :
Les algorithmes multimodaux de SLAM améliorent sa robustesse et sa précision dans des environnements complexes et dynamiques. Cependant, ces améliorations se font au prix d’une augmentation des exigences en matière de calcul. L’étude systémique du problème SLAM est cruciale pour concevoir une solution pratique, stable et polyvalente, adaptable aux systèmes embarqués et temps réel. Nous avons étudié les différentes étapes de traitement du système afin d’apporter des contributions au niveau de fermeture de boucle multimodale pour des applications SLAM et de son architecture de calcul. Cette étude a commencé par une analyse approfondie de l’impact des différentes modalités de représentation de l’information sur la précision de la fermeture de boucle et son influence sur la réduction de la dérive de trajectoire. Nous avons développé une méthode de fusion à base d’un filtre particulaire guidé par la similarité, qui a été évaluée à l’aide de divers ensembles de données. Les résultats obtenus ont montré une amélioration de la localisation. Nous avons proposé un modèle d’architecture hétérogène (CPU-GPU et CPU-FPGA) pour le calcul d’un descripteur de scène inter-modal. Cette architecture a pu offrir des performances supérieures en termes de temps de traitementMultimodal SLAM algorithms improve its robustness and accuracy in complex and dynamic environments. However, these improvements come at the cost of increased computational requirements. The systemic-level study of the SLAM problem is crucial to designing a practical, stable and versatile solution, adaptable to embedded and real-time systems. We have studied the various processing stages of the system in order to propose contributions to the multimodal loop closure level for SLAM applications, and its computational architecture. This study began with an in-depth analysis of the impact of multimodal information representation on loop closure accuracy and its influence on trajectory drift reduction. We developed a fusion method based on a similarity-guided particle filter, which was evaluated using various dataset. The results obtained showed an improvement in localization’s accuracy. We proposed a heterogeneous architecture model (CPU-GPU and CPU-FPGA) for inter-modal scene descriptor computation. This architecture was able to deliver superior performance in terms of processing time
10
Karlsson, Oskar. « Lidar-based SLAM : Investigation of environmental changes and use of road-edges for improved positioning ». Thesis, Linköpings universitet, Reglerteknik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-165288.
Texte intégralRésumé :
The ability to position yourself and map the surroundings is an important aspect for both civilian and military applications. Global navigation satellite systems are very popular and are widely used for positioning. This kind of system is however quite easy to disturb and therefore lacks robustness. The introduction of autonomous vehicles has accelerated the development of local positioning systems. This thesis work is done in collaboration with FOI in Linköping, using a positioning system with LIDAR and IMU sensors in a EKF-SLAM system using the GTSAM framework. The goal was to evaluate the system in different conditions and also investigate the possibility of using the road surface for positioning. Data available at FOI was used for evaluation. These data sets have a known sensor setup and matches the intended hardware. The data sets used have been gathered on three different occasions in a residential area, a country road and a forest road in sunny spring weather on two occasions and one occasion in winter conditions. To evaluate the performance several different measures were used, common ones such as looking at positioning error and RMSE, but also the number of found landmarks, the estimated distance between landmarks and the drift of the vehicle. All results pointed towards the forest road providing the best positioning, the country road the worst and the residential area in between. When comparing different weather conditions the data set from winter conditions performed the best. The difference between the two spring data sets was quite different which indicates that there may be other factors at play than just weather. A road edge detector was implemented to improve mapping and positioning. Vectors, denoted road vectors, with position and orientation were adapted to the edge points and the change between these road vectors were used in the system using GTSAM in areas with few landmarks. The clearest improvements to the drift in the vehicle direction was in the longer country area where the error was lowered with 6.4 % with increase in the error sideways and in orientation as side effects. The implemented method has a significant impact on the computational cost of the system as well as requiring precise adjustment of uncertainty to have a noticeable improvement and not worsen the overall results.
11
Schubert, Jack. « Development of a ground robot for indoor SLAM using Low‐Cost LiDAR and remote LabVIEW HMI ». Thesis, Schubert, Jack (2018) Development of a ground robot for indoor SLAM using Low‐Cost LiDAR and remote LabVIEW HMI. Honours thesis, Murdoch University, 2018. https://researchrepository.murdoch.edu.au/id/eprint/44801/.
Texte intégralRésumé :
The simultaneous localization and mapping problem (SLAM) is crucial to autonomous navigation and robot mapping. The main purpose of this thesis is to develop a ground robot that implements SLAM to test the performance of the low‐cost RPLiDAR A1M8 by DFRobot. The HectorSLAM package, available in ROS was used with a Raspberry Pi to implement SLAM and build maps. These maps are sent to a remote desktop via TCP/IP communication to be displayed on a LabVIEW HMI where the user can also control robot. The LabVIEW HMI and the project in its entirety is intended to be as easy to use as possible to the layman, with many processes being automated to make this possible.
The quality of the maps created by HectorSLAM and the RPLiDAR were evaluated both qualitatively and quanitatively to determine how useful the low‐cost LiDAR can be for this application. It is hoped that the apparatus developed in this project will be used with drones in the future for 3D mapping.
12
Correa, Silva Joan Li Guisell, et Sofia Jönsson. « Investigation of Increased Mapping Quality Generated by a Neural Network for Camera-LiDAR Sensor Fusion ». Thesis, KTH, Mekatronik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-297463.
Texte intégralRésumé :
This study’s aim was to investigate the mapping part of Simultaneous Localisation And Mapping (SLAM) in indoor environments containing error sources relevant to two types of sensors. The sensors used were an Intel Realsense depth camera and an RPlidar Light Detection AndRanging (LiDAR). Both cameras and LiDARs are frequently used as exteroceptive sensors in SLAM. Cameras typically struggle with strong light in the environment, and LiDARs struggle with reflective surfaces. Therefore, this study investigated the possibility of using a neural network to detect an error in either sensors’ data caused by mentioned error sources. The network identified which sensor produced erroneous data. The sensor fusion algorithm momentarily excluded said sensor’s data, consequently, improving the mapping quality when possible. The quantitative results showed no significant difference in the measured mean squared error and structural similarity between the final maps generated with and without the network, when compared to the ground truth. However, the qualitative analysis showed some advantages with using the network. Many of the camera’s errors were filtered out with the neural network, and led to a more accurate continuous mapping than without the network implemented. The conclusion was that a neural network can to a limited extent recognise the sensors’ data errors, but only the camera data benefited from the proposed solution. The study also produced important findings from the implementation which are presented. Future work recommendations include neural network optimisation, sensor selection, and sensor fusion implementation.Denna studie undersökte kartläggningen i Simultaneous Localisation And Mapping (SLAM) problem, i kontexten av två sensorers felkällor. Sensorerna som användes var en Intel Realsense djupseende kamera samt en LiDAR fran RPlidar. Både kameror och LiDARs är vanliga sensorer i SLAM system, och båda har olika typer av felkällor. Kameror är typiskt känsliga för mycket starkt ljus, medan LiDARs har svårt med reflekterande ytor. Med detta som bakgrund har denna studie undersökt möjligheten att implementera ett neuralt nätverk för att detektera när varje sensor är utsatt för en felkälla (och därmed ger fel data). Nätverkets klassificering används sedan för att i varje tidssteg exkludera den sensors data som det är fel på för att förbättra kartläggningen. De qvantitativa resultaten visade ingen signifikant skillnad mellan kartorna genererade med nätverket och de utan nätverket. Dock visade den kvalitativa analysen att det finns vissa fördelar med att använda det neutrala nätverket. Manga av kamerans fel blev korrigerade när nätverket var implementerat, vilket ledde till mer korrekta kartor under kontinuerlig körning. Slutsatsen blev att ett nätverk kan bli tränat för att identifiera fel i datan, men att kameran drar mest nytta av det. Studien producerade även sekundara resultat som också redovisas. Slutligen rekommenderas optimering av nätverket, val av sensorer, samt uppdaterad algoritm för sensor fusionen som möjliga områden till fortsatt forskning inom området.
13
Holmqvist, Niclas. « HANDHELD LIDAR ODOMETRY ESTIMATION AND MAPPING SYSTEM ». Thesis, Mälardalens högskola, Inbyggda system, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-41137.
Texte intégralRésumé :
Ego-motion sensors are commonly used for pose estimation in Simultaneous Localization And Mapping (SLAM) algorithms. Inertial Measurement Units (IMUs) are popular sensors but suffer from integration drift over longer time scales. To remedy the drift they are often used in combination with additional sensors, such as a LiDAR. Pose estimation is used when scans, produced by these additional sensors, are being matched. The matching of scans can be computationally heavy as one scan can contain millions of data points. Methods exist to simplify the problem of finding the relative pose between sensor data, such as the Normal Distribution Transform SLAM algorithm. The algorithm separates the point cloud data into a voxelgrid and represent each voxel as a normal distribution, effectively decreasing the amount of data points. Registration is based on a function which converges to a minimum. Sub-optimal conditions can cause the function to converge at a local minimum. To remedy this problem this thesis explores the benefits of combining IMU sensor data to estimate the pose to be used in the NDT SLAM algorithm.
14
Pilch, Tomasz. « Simultalní lokalizace, mapování a vytváření modelu prostředí pro autonomní robotiku ». Master's thesis, Vysoké učení technické v Brně. Fakulta strojního inženýrství, 2016. http://www.nusl.cz/ntk/nusl-254449.
Texte intégral
15
Salem, Marwan. « Building an Efficient Occupancy Grid Map Based on Lidar Data Fusion for Autonomous driving Applications ». Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-263098.
Texte intégralRésumé :
The Localization and Map building module is a core building block for designing an autonomous vehicle. It describes the vehicle ability to create an accurate model of its surroundings and maintain its position in the environment at the same time. In this thesis work, we contribute to the autonomous driving research area by providing a proof-of-concept of integrating SLAM solutions into commercial vehicles; improving the robustness of the Localization and Map building module. The proposed system applies Bayesian inference theory within the occupancy grid mapping framework and utilizes Rao-Blackwellized Particle Filter for estimating the vehicle trajectory. The work has been done at Scania CV where a heavy duty vehicle equipped with multiple-Lidar sensory architecture was used. Low level sensor fusion of the different Lidars was performed and a parallelized implementation of the algorithm was achieved using a GPU. When tested on the frequently used datasets in the community, the implemented algorithm outperformed the scan-matching technique and showed acceptable performance in comparison to another state-of-art RBPF implementation that adapts some improvements on the algorithm. The performance of the complete system was evaluated under a designed set of real scenarios. The proposed system showed a significant improvement in terms of the estimated trajectory and provided accurate occupancy representations of the vehicle surroundings. The fusion module was found to build more informative occupancy grids than the grids obtained form individual sensors.Modulen som har hand om både lokalisering och byggandet av karta är en av huvudorganen i ett system för autonom körning. Den beskriver bilens förmåga att skapa en modell av omgivningen och att hålla en position i förhållande till omgivningen. I detta examensarbete bidrar vi till forskningen inom autonom bilkörning med ett valideringskoncept genom att integrera SLAM-lösningar i kommersiella fordon, vilket förbättrar robustheten hos lokaliserings-kartbyggarmodulen. Det föreslagna systemet använder sig utav Bayesiansk statistik applicerat i ett ramverk som har hand om att skapa en karta, som består av ett rutnät som används för att beskriva ockuperingsgraden. För att estimera den bana som fordonet kommer att färdas använder ramverket RBPF(Rao-Blackwellized particle filter). Examensarbetet har genomförts hos Scania CV, där ett tungt fordon utrustat med flera lidarsensorer har använts. En lägre nivå av sensor fusion applicerades för de olika lidarsensorerna och en parallelliserad implementation av algoritmen implementerades på GPU. När algoritmen kördes mot data som ofta används av ”allmänheten” kan vi konstatera att den implementerade algoritmen ger ett väldigt mycket bättre resultat än ”scan-matchnings”-tekniken och visar på ett acceptabelt resultat i jämförelse med en annan högpresterande RBPFimplementation, vilken tillför några förbättringar på algoritmen. Prestandan av hela systemet utvärderas med ett antal egendesignade realistiska scenarion. Det föreslagna systemet visar på en tydlig förbättring av uppskattningen av körbanan och bidrar även med en exakt representation av omgivningen. Sensor Fusionen visar på en bättre och mer informativ representation än när man endast utgår från de individuella lidarsensorerna.
16
Gillsjö, David. « Moving object detection in urban environments ». Thesis, Linköpings universitet, Reglerteknik, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-84734.
Texte intégralRésumé :
Successful and high precision localization is an important feature for autonomous vehicles in an urban environment. GPS solutions are not good on their own and laser, sonar and radar are often used as complementary sensors. Localization with these sensors requires the use of techniques grouped under the acronym SLAM (Simultaneous Localization And Mapping). These techniques work by comparing the current sensor inputs to either an incrementally built or known map, also adding the information to the map.Most of the SLAM techniques assume the environment to be static, which means that dynamics and clutter in the environment might cause SLAM to fail. To ob-tain a more robust algorithm, the dynamics need to be dealt with. This study seeks a solution where measurements from different points in time can be used in pairwise comparisons to detect non-static content in the mapped area. Parked cars could for example be detected at a parking lot by using measurements from several different days.The method successfully detects most non-static objects in the different test datasets from the sensor. The algorithm can be used in conjunction with Pose-SLAM to get a better localization estimate and a map for later use. This map is good for localization with SLAM or other techniques since only static objects are left in it.
17
Nordin, Fredrik. « Terrain sensor for semi active suspension in CV90 ». Thesis, Luleå tekniska universitet, Datavetenskap, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-64434.
Texte intégralRésumé :
The combat vehicle, CV90 has a semi-active hydraulic suspension system which uses inertial measurements for regulation to improve accessibility. To improve performance further measurements of future terrain can be used to, for example, prepare for impacts. This master's thesis investigates the ability to use existing sensors and new sensors to facilitate these measurements. Two test runs were performed, with very different conditions and outcomes. The results seem to suggest that a sweeping LIDAR was the most accurate and robust solution. However, using a very recent visual odometry algorithm, promising results were achieved using an Infra-red heat camera. Especially given that no efforts were put into adjusting parameters for that particular algorithm.
18
Lin, Ismael. « Combining dense short range sensors and sparse long range sensors for mapping ». Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-223572.
Texte intégralRésumé :
Mapping is one of the main components of autonomous robots, and consist in the construction of a model of their environment based on the information gathered by different sensors over time. Those maps will have different attributes depending on the type of sensor used for the reconstruction. In this thesis we focus on RGBD cameras and LiDARs. The acquired data with cameras is dense, but the range is short and the construction of large scale and consistent maps is more challenging. LiDARs are the exact opposite, they give sparse data but can measure long ranges accurately and therefore support large scale mapping better. The thesis presents a method that uses both types of sensors with the purpose of combine their strengths and reduce their weaknesses. The evaluation of the system is done in an indoor environment, and with an autonomous robot. The result of the thesis shows a map that is robust in large environments and has dense information of the surroundings.Kartläggning är en av huvudkomponenterna för autonoma robotar, och består av att bygga en modell av miljön utifrån informationen som samlats in av olika sensorer över tid. Dessa kartor kommer att ha olika attribut beroende på vilken typ av sensor som används för rekonstruktionen. I denna avhandling är fokus på RGBD-kameror och LiDARs. Datan från kameror är kompakt men kan bara mäta korta sträckor och det är utmanande att konstruera storskaliga och konsistenta kartor. LiDARs är exakt motsatta, de ger gles data men kan mäta långa avstånd noggrant och stödjer därför storskalig kartering bättre. Avhandlingen presenterar en metod som använder båda typerna av sensorer i syfte att kombinera deras styrkor och minska svagheterna. Utvärderingen av systemet sker i en inomhusmiljö och med en autonom robot. Resultatet av avhandlingen visar en karta som är robust i stora miljöer och har tät information om omgivningen.
19
Manhed, Joar. « Investigating Simultaneous Localization and Mapping for an Automated Guided Vehicle ». Thesis, Linköpings universitet, Reglerteknik, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-163075.
Texte intégralRésumé :
The aim of the thesis is to apply simultaneous localization and mapping (SLAM) to automated guided vehicles (AGVs) in a Robot Operating System (ROS) environment. Different sensor setups are used and evaluated. The SLAM applications used is the open-source solution Cartographer as well as Intel's own commercial SLAM in their T265 tracking camera. The different sensor setups are evaluated based on how well the localization will give the exact pose of the AGV in comparison to another positioning system acting as ground truth.
20
Naghi, Nour. « Simultaneous Localization and Mapping Technologies ». Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/17852/.
Texte intégralRésumé :
Il problema dello SLAM (Simultaneous Localization And Mapping) consiste nel mappare un ambiente sconosciuto per mezzo di un dispositivo che si muove al suo interno, mentre si effettua la localizzazione di quest'ultimo.
All'interno di questa tesi viene analizzato il problema dello SLAM e le differenze che lo contraddistinguono dai problemi di mapping e di localizzazione trattati separatamente.
In seguito, si effettua una analisi dei principali algoritmi impiegati al giorno d'oggi per la sua risoluzione, ovvero i filtri estesi di Kalman e i particle filter.
Si analizzano poi le diverse tecnologie implementative esistenti, tra le quali figurano sistemi SONAR, sistemi LASER, sistemi di visione e sistemi RADAR; questi ultimi, allo stato dell'arte, impiegano onde millimetriche (mmW) e a banda larga (UWB), ma anche tecnologie radio già affermate, fra le quali il Wi-Fi.
Infine, vengono effettuate delle simulazioni di tecnologie basate su sistema di visione e su sistema LASER, con l'ausilio di due pacchetti open source di MATLAB. Successivamente, il pacchetto progettato per sistemi LASER è stato modificato al fine di simulare una tecnologia SLAM basata su segnali Wi-Fi.
L'utilizzo di tecnologie a basso costo e ampiamente diffuse come il Wi-Fi apre alla possibilità, in un prossimo futuro, di effettuare localizzazione indoor a basso costo, sfruttando l'infrastruttura esistente, mediante un semplice smartphone. Più in prospettiva, l'avvento della tecnologia ad onde millimetriche (5G) consentirà di raggiungere prestazioni maggiori.
21
SAMMARTANO, GIULIA. « Suitability Of 3D Dense Models For Rapid Mapping Strategies On Cultural Heritage Documentation And Conservation. Validation of metric and non-metric information extraction from integrated solutions ». Doctoral thesis, Politecnico di Torino, 2018. http://hdl.handle.net/11583/2703098.
Texte intégralRésumé :
This dissertation deals with the suitability of digital models for the 3D documentation of built heritage (BH), in terms of its resolution, measure and representation regarding the building’s morphology and state of conservation. Specifically, the research enquires into the 3D models’ consistency and validation, generated by new methodological developments of geomatics-integrated techniques for obtaining geospatial data, by means of rapid mapping solutions in 3D survey, generally with low-cost approaches, to obtain metric and non-metric definition of the historical structures. Starting from the bounding of the concept of user-oriented models in the reality-based modelling issues at the first part of the dissertation, the documentation of cultural heritage (CH) in critical contexts is defined as investigation workspace. The established workflows of the digital metric survey based on range-based and image-based sensors are analyzed in the second part, and the possible integrated acquisition and processing phases on the point clouds data treatment for the surface model definition are proposed and validated. The assessment issues are weighted on employed techniques, well-established and more innovative, and on the initially introduced requirements about scale accuracy and achievable details.
The aim of this research is thus to focus on the 3D model features and their confidence levels to define and classify the extracted multi-scale geometric and radiometric information that can be useful to be addressed toward interdisciplinary interventions on the state of conservation, on the damage mapping and assessment around cultural heritage assets. This content is bound around the 3D model, according to a multi-parameter framework that wants to cover the overall validation attributes, such as: operational efficiency or the practicality and sustainability of data achievement; reliability or the confidence level of the metric contents on the model; contents or the richness of the embedded data; completeness or the comprehensiveness of gatherable information.
The extensive testing, addressed in the fourth part of the discussion, is based on a set of examples regarding the analyzed BH typologies located in the different urban and landscape contexts, featured by increasing levels of critical issues. It aims is the supporting the comparative multi-parameter evaluation and validation in the central part of the dissertation. Herein, the validation of 3D models is proposed from integrated workflows which take into account consolidated approaches (like terrestrial laser scanning or close-range photogrammetry) flanked by rapid mapping strategies with the employment of alternative techniques (such as the UAV photogrammetry, in the nadir and oblique configurations, and the portable Mobile Mapping Systems). The information richness, according to a 3D integration perspective, demonstrates across the dataset presentation and the final discussion, the promising and flexible ability of documenting the morphology and material characterization of complex historical structures, even proving their aptitude to support the mapping of structures consistence and conservation in case of emergency and damage assessment.
22
Landry, Michaël. « Développement d'une nouvelle méthode de calibrage des Systèmes LiDAR Mobiles (SLM) en laboratoire ». Master's thesis, Université Laval, 2017. http://hdl.handle.net/20.500.11794/27871.
Texte intégralRésumé :
Le scanner LiDAR est une technologie de plus en plus populaire auprès des ingénieurs, arpenteurs-géomètres, architectes et autres professionnels qui ont recours à la modélisation 3D dans le cadre de leur travail. L'intégration de ce capteur à un système de navigation (IMU + GNSS) permet de former un Système LiDAR Mobile (SLM). Les SLM ont été initialement développés pour des véhicules aéroportés, mais ont été plus récemment adaptés aux véhicules terrestres. Toutes les observations du SLM sont combinées pour former un nuage de points par géoréférencement direct. De manière à limiter la propagation des erreurs systématiques dues à l'assemblage de ces capteurs, un calibrage du système est nécessaire. Le calibrage d'un SLM implique la détermination des bras de levier et des angles de visée qui correspondent sommairement à la distance et à l'orientation entre le LiDAR et l'IMU. Le fabricant fournit habituellement des valeurs pour ces éléments, mais il est nécessaire de peaufiner ces valeurs qui sont propres à chaque système. Étant donné qu'il est impossible de déterminer précisément les angles de visée avec des mesures manuelles, les observations sur le terrain sont utilisées afin de les estimer (calibrage in situ). Un problème avec le calibrage in situ est que les observations GNSS introduisent des erreurs de plusieurs centimètres dans la solution, ce qui nuit au calibrage. Pour éliminer le recours aux observations GNSS, des méthodes alternatives de calibrage s'imposent. Le but de ce travail de recherche est d'instaurer une procédure de cueillette et de traitement des données acquises par un SLM en laboratoire de façon à développer une méthode de calibrage libre d'erreurs de positionnement GNSS. Cette méthode de calibrage doit permettre d'estimer les angles de visée et les bras de levier d'un SLM à partir des instruments et des infrastructures présentes au laboratoire de métrologie de l’Université Laval.The LiDAR scanner is an increasingly popular technology for engineers, land surveyors, architects and other professionals who use 3D modeling as part of their work. The integration of this sensor with a navigation system (IMU + GNSS) makes it possible to form a Mobile LiDAR System (MLS). MLSs were originally developed for airborne vehicles, but were more recently adapted to land vehicles. All MLS observations are combined to form a point cloud by direct georeferencing. In order to limit the propagation of systematic errors due to the assembly of these sensors, it is necessary to properly calibrate the system. The calibration of an MLS involves the determination of the lever arms and boresight angles that correspond to the distance and orientation between the LiDAR and the IMU. The manufacturer usually provides values for these elements, but it is necessary to fine-tune these values that are unique to each system. Since it is impossible to accurately determine boresight angles with manual measurements, field observations are used to estimate them (in situ calibration). A problem with in situ calibration is that GNSS observations introduce errors of several centimeters into the solution, which is harmful for a proper calibration. In order to eliminate the need for GNSS observations, alternative methods of calibration are required. The aim of this research is to set up a procedure for the collection and processing of data acquired by an MLS in a laboratory in order to develop a calibration method free of GNSS positioning errors. This calibration method should allow estimation of the boresight angles and the lever arms of an MLS with the instruments and infrastructures inside the metrology laboratory of Laval University.
23
Silva, Paulo Rúben Alves. « Optimal Wheelchair Multi-LiDAR Placement for Indoor SLAM ». Master's thesis, 2021. https://hdl.handle.net/10216/135766.
Texte intégralRésumé :
One of the most prevalent technologies used in modern robotics is Simultaneous Localization and Mapping or, SLAM. Modern SLAM technologies usually employ a number of different probabilistic mathematics to perform processes that enable modern robots to not only map an environment but, also, concurrently localize themselves within said environment.
Existing open-source SLAM technologies not only range in the different probabilistic methods they employ to achieve their task but, also, by how well the task is achieved and by their computational requirements. Additionally, the positioning of the sensors in the robot also has a substantial effect on how well these technologies work. Therefore, this dissertation is dedicated to the comparison of existing open-source ROS implemented 2D SLAM technologies and in the maximization of the performance of said SLAM technologies by researching optimal sensor placement in a Intelligent Wheelchair context, using SLAM performance as a benchmark.
24
Silva, Paulo Rúben Alves. « Optimal Wheelchair Multi-LiDAR Placement for Indoor SLAM ». Dissertação, 2021. https://hdl.handle.net/10216/135766.
Texte intégralRésumé :
One of the most prevalent technologies used in modern robotics is Simultaneous Localization and Mapping or, SLAM. Modern SLAM technologies usually employ a number of different probabilistic mathematics to perform processes that enable modern robots to not only map an environment but, also, concurrently localize themselves within said environment.
Existing open-source SLAM technologies not only range in the different probabilistic methods they employ to achieve their task but, also, by how well the task is achieved and by their computational requirements. Additionally, the positioning of the sensors in the robot also has a substantial effect on how well these technologies work. Therefore, this dissertation is dedicated to the comparison of existing open-source ROS implemented 2D SLAM technologies and in the maximization of the performance of said SLAM technologies by researching optimal sensor placement in a Intelligent Wheelchair context, using SLAM performance as a benchmark.
25
Leal, Pedro Miguel Sousa. « Navigation solutions for autonomous mobile robots using lidar ». Master's thesis, 2021. http://hdl.handle.net/10316/96100.
Texte intégralRésumé :
Dissertação de Mestrado Integrado em Engenharia Física apresentada à Faculdade de Ciências e TecnologiaA área da robótica tem feito avanços monumentais e continua a fazê-lo. Durante décadas, robôs têm sido usados para realizar trabalho altamente especializado dentro do mundo industrial. Hoje em dia, enquanto os desenvolvimentos relativos a soluções autónomas continuam a materializar-se, esta tecnologia está a quebrar as fronteiras do mundo industrial e começam a ver-se robôs no nosso dia-a-dia. Desde carros autónomos a robôs de limpeza, a nossa interação com esta tecnologia está a tornar-se comum. Localização, mapeamento e planeamento de rota são conceitos importantes em robótica, e em sistemas de navegação. Executar localização e mapeamento em simultâneo, denominado de SLAM, é uma tarefa incrivelmente complexa, e, em aplicações em que há pessoas no local, estes sistemas têm de ser altamente robustos. A empresa Active Space Technologies está a explorar soluções para robôs móveis autônomos (AMRs) e esta dissertação pretende executar uma implementação baseada em open-source de um sistema de navegação, incluindo SLAM e planeamento de rota. Adicionalmente, um algoritmo de detecção de objectos (baseado em DeepLab) é integrado no sistema juntamente com outras funcionalidades.Mais tarde, uma avaliação de seis soluções (SLAM Toolbox, Cartographer, RTAB-Map, HectorSLAM, Gmapping e LOAM) para a componente SLAM foi feita num ambiente real com dois sensores diferentes: o Intel Realsense L515 e o Velodyne VLP-16. Os resultados demonstram que ambos conseguem efectuar SLAM, sendo que o VLP-16 demonstrou excelentes resultados enquanto que o L515 necessitou de uma fonte robusta de odometria externa.Finalmente, as soluções relativas à remoção de ruido detectado pela L515 em algumas circunstâncias (como uma fonte de luzes directa), e a segmentação de pessoas usando o algoritmo de detecção de objectos foram demonstradas.
The field of robotics has made monumental advancements and continues to do so. For decades, robots have been used for highly specialized work within the industrial world. %in recent Nowadays, as developments regarding autonomous solutions continue to materialize, this technology is breaking the industrial boundaries and robots are starting to be seen in our daily lives. From self-driving cars to cleaning robots, our interaction with this technology is slowly becoming common.Localization, mapping and path planning are major concepts in robotics, and any navigation system. Performing the first two simultaneously, known as SLAM, is an incredibly complex task, and when considering applications where there are people in the vicinity, these systems must be highly reliable.The company Active Space Technologies is exploring solutions regarding autonomous mobile robots (AMRs) and this dissertation aims to come up with an open-source implementation of a navigation system, including SLAM and path planning. Additionally, an object detection algorithm (using DeepLab) is integrated into the system as well as several other features. Afterwards, an evaluation of six solutions (SLAM Toolbox, Cartographer, RTAB-Map, HectorSLAM, Gmapping and LOAM) for the SLAM component is carried out in a real world setting with two separate sensors: the Intel RealSense L515 lidar camera and the Velodyne VLP-16. The results reveal that both can effectively perform SLAM, with the VLP-16 showing excellent results while the L515 requires robust external odometry.Lastly, solutions to remove systemic noise detected in the scans of the L515 under certain circumstances (such as direct light), as well as segmentation of people using the object detection algorithm are demonstrated.
26
Ma, Zeyu. « SLAM research for port AGV based on 2D LIDAR ». Master's thesis, 2019. http://hdl.handle.net/10071/20314.
Texte intégralRésumé :
With the increase in international trade, the transshipment of goods at international container ports is very busy. The AGV (Automated Guided Vehicle) has been used as a new generation of automated container horizontal transport equipment. The AGV is an automated unmanned vehicle that can work 24 hours a day, increasing productivity and reducing labor costs compared to using container trucks. The ability to obtain information about the surrounding environment is a prerequisite for the AGV to automatically complete tasks in the port area. At present, the method of AGV based on RFID tag positioning and navigation has a problem of excessive cost. This dissertation has carried out a research on applying light detection and ranging (LIDAR) simultaneous localization and mapping (SLAM) technology to port AGV. In this master's thesis, a mobile test platform based on a laser range finder is developed to scan 360-degree environmental information (distance and angle) centered on the LIDAR and upload the information to a real-time database to generate surrounding environmental maps, and the obstacle avoidance strategy was developed based on the acquired information. The effectiveness of the platform was verified by the experiments from multiple scenarios. Then based on the first platform, another experimental platform with encoder and IMU sensor was developed. In this platform, the functionality of SLAM is enabled by the GMapping algorithm and the installation of the encoder and IMU sensor. Based on the established environment SLAM map, the path planning and obstacle avoidance functions of the platform were realized.Com o aumento do comércio internacional, o transbordo de mercadorias em portos internacionais de contentores é muito movimentado. O AGV (“Automated Guided Vehicle”) foi usado como uma nova geração de equipamentos para transporte horizontal de contentores de forma automatizada. O AGV é um veículo não tripulado automatizado que pode funcionar 24 horas por dia, aumentando a produtividade e reduzindo os custos de mão-de-obra em comparação com o uso de camiões porta-contentores. A capacidade de obter informações sobre o ambiente circundante é um pré-requisito para o AGV concluir automaticamente tarefas na área portuária. Atualmente, o método de AGV baseado no posicionamento e navegação de etiquetas RFID apresenta um problema de custo excessivo. Nesta dissertação foi realizada uma pesquisa sobre a aplicação da tecnologia LIDAR de localização e mapeamento simultâneo (SLAM) num AGV. Uma plataforma de teste móvel baseada num telémetro a laser é desenvolvida para examinar o ambiente em redor em 360 graus (distância e ângulo), centrado no LIDAR, e fazer upload da informação para uma base de dados em tempo real para gerar um mapa do ambiente em redor. Uma estratégia de prevenção de obstáculos foi também desenvolvida com base nas informações adquiridas. A eficácia da plataforma foi verificada através da realização de testes com vários cenários e obstáculos. Por fim, com base na primeira plataforma, uma outra plataforma experimental com codificador e sensor IMU foi também desenvolvida. Nesta plataforma, a funcionalidade do SLAM é ativada pelo algoritmo GMapping e pela instalação do codificador e do sensor IMU. Com base no estabelecimento do ambiente circundante SLAM, foram realizadas as funções de planeamento de trajetória e prevenção de obstáculos pela plataforma.
27
ChenLei et 雷晨. « Reconstructing Environment Model with SLAM on UV-LiDAR System ». Thesis, 2016. http://ndltd.ncl.edu.tw/handle/14620692565643685598.
Texte intégralRésumé :
碩士國立成功大學
工程科學系
104
As UV researches and marketing have delivered an explosive growth in the recent decades, more and more demands have been raised by users. A number of developments and researches of sensors, peripherals, and ability for UVs have been prompted to solve a variety of problems and missions for fulfilling these demands. The most common one among these desired abilities mentioned above is the “vision”. The proposed system of this study first collects odometry data with LiDARs, which is mounted on a rotatory platform, then the data are collected and gathered into a map by an embedded device with SLAM package, also, the pose estimation of LiDARs is finished at the same time. Finally, these information of pose and map are published via Wi-Fi. With this system, UVs are able to know its orientation and “see” the surroundings without the aid of IMU, GPS and other sensors, and give an real-time information to the user to know the situation of UV at the same time.
28
Li-HsinChen et 陳立昕. « Development of SLAM and Loop Closure Algorithm Based on 2D LiDAR ». Thesis, 2018. http://ndltd.ncl.edu.tw/handle/u5c535.
Texte intégral
29
Sarmento, Luís Pedro Esteves. « Navegação assistida e semi-autónoma da plataforma ROBONUC ». Master's thesis, 2018. http://hdl.handle.net/10773/29466.
Texte intégralRésumé :
A manipulação móvel é uma área com uma importância crescente a nível
industrial que permite a execução de tarefas complexas em ambientes
dinâmicos.
A presente dissertação insere-se no projeto ROBONUC que é constituído
por uma plataforma móvel e por um manipulador FANUC. Tem por objetivo
a implementação de um sistema de controlo remoto para a plataforma, de
modo que esta tenha autonomia suficiente para corrigir a trajetória evitando
colisões.
O trabalho está a ser desenvolvido em ambiente Robotic Operating System
(ROS), que apresenta uma estrutura modular. Este ambiente permite a
integração de programas desenvolvidos por terceiros, assim como a distribuição de processos em diversas máquinas.
A primeira tarefa consistiu em implementar a hodometria, ou seja, determinar
o deslocamento da plataforma recorrendo à informação proveniente
dos encoders das rodas. Foi introduzido o HectorSlam, um programa desenvolvido
em ROS, que permite realizar a construção do mapa do espaço
envolvente recorrendo ao laser Hokuyo instalado na plataforma.
Para garantir a segurança foram definidas zonas de risco de colisão, que são
variáveis em função da velocidade da plataforma. Foi considerado existir
risco de colisão se um dos dois lasers Hokuyo, presentes na plataforma, detetar
um objeto na zona de risco. Desenvolveu-se um programa ROS que
permite a navegação segura e autónoma da plataforma. Caso seja determinado
risco de colisão o modo autónomo é acionado, permitindo o contorno
do obstáculo.
A realização de testes experimentais foi essencial para realizar a calibração
da hodometria, assim como a calibração das áreas de risco.Mobile manipulation is a field with increasing importance in the industry which allows to execute complex tasks in dynamic environment. The current dissertation is inserted in the ROBONUC project which is composed by a mobile platform and a FANUC manipulator. The objective of this work is to implement a remote control system on the platform in such a way that allows it to navigate with enough autonomy to correct the trajectory imposed by the user in order to avoid a collision. The work is being developed in a modular structured environment called Robotic Operating System (ROS). This software allows to integrate third party programs as well as the distribution of multiple processes in different machines. The first task consisted of the implementation of the odometry or in other words, the calculation of the distance travelled by the platform using the information provided by the wheel encoders. HectorSLAM was introduced, an open source program developed in ROS, that allows to reconstruct the map of the involving environment using the Hokuyo laser installed on the platform. To ensure safety, several collision risk areas were defined that are variable in size depending on the platform's velocity. There is the existence of collision risk if one of the two Hokuyo lasers on the platform detects an objective in the risk area. An open source ROS program that allows a safely autonomous navigation was implemented in the platform. In case that a rick of collision is detected the autonomous mode is activated allows to avoid the obstacle. The execution of experimental tests was essencial to calibrate the odometry, as well as adjusting the risk areas.
Mestrado em Engenharia Mecânica
30
« Modeling and Control for Vision Based Rear Wheel Drive Robot and Solving Indoor SLAM Problem Using LIDAR ». Master's thesis, 2016. http://hdl.handle.net/2286/R.I.40236.
Texte intégralRésumé :
abstract: To achieve the ambitious long-term goal of a feet of cooperating Flexible Autonomous
Machines operating in an uncertain Environment (FAME), this thesis addresses several
critical modeling, design, control objectives for rear-wheel drive ground vehicles.
Toward this ambitious goal, several critical objectives are addressed. One central objective of the thesis was to show how to build low-cost multi-capability robot platform
that can be used for conducting FAME research.
A TFC-KIT car chassis was augmented to provide a suite of substantive capabilities.
The augmented vehicle (FreeSLAM Robot) costs less than $500 but offers the capability
of commercially available vehicles costing over $2000.
All demonstrations presented involve rear-wheel drive FreeSLAM robot. The following
summarizes the key hardware demonstrations presented and analyzed:
(1)Cruise (v, ) control along a line,
(2) Cruise (v, ) control along a curve,
(3) Planar (x, y) Cartesian Stabilization for rear wheel drive vehicle,
(4) Finish the track with camera pan tilt structure in minimum time,
(5) Finish the track without camera pan tilt structure in minimum time,
(6) Vision based tracking performance with different cruise speed vx,
(7) Vision based tracking performance with different camera fixed look-ahead distance L,
(8) Vision based tracking performance with different delay Td from vision subsystem,
(9) Manually remote controlled robot to perform indoor SLAM,
(10) Autonomously line guided robot to perform indoor SLAM.
For most cases, hardware data is compared with, and corroborated by, model based
simulation data. In short, the thesis uses low-cost self-designed rear-wheel
drive robot to demonstrate many capabilities that are critical in order to reach the
longer-term FAME goal.Dissertation/Thesis
Defense Presentation
Masters Thesis Electrical Engineering 2016
31
Betrabet, Siddhant S. « Data Acquisition and Processing Pipeline for E-Scooter Tracking Using 3d Lidar and Multi-Camera Setup ». Thesis, 2020. http://hdl.handle.net/1805/24776.
Texte intégralRésumé :
Indiana University-Purdue University Indianapolis (IUPUI)Analyzing behaviors of objects on the road is a complex task that requires data from various sensors and their fusion to recreate the movement of objects with a high degree of accuracy. A data collection and processing system are thus needed to track the objects accurately in order to make an accurate and clear map of the trajectories of objects relative to various coordinate frame(s) of interest in the map. Detection and tracking moving objects (DATMO) and Simultaneous localization and mapping (SLAM) are the tasks that needs to be achieved in conjunction to create a clear map of the road comprising of the moving and static objects. These computational problems are commonly solved and used to aid scenario reconstruction for the objects of interest. The tracking of objects can be done in various ways, utilizing sensors such as monocular or stereo cameras, Light Detection and Ranging (LIDAR) sensors as well as Inertial Navigation systems (INS) systems. One relatively common method for solving DATMO and SLAM involves utilizing a 3D LIDAR with multiple monocular cameras in conjunction with an inertial measurement unit (IMU) allows for redundancies to maintain object classification and tracking with the help of sensor fusion in cases when sensor specific traditional algorithms prove to be ineffectual when either sensor falls short due to their limitations. The usage of the IMU and sensor fusion methods relatively eliminates the need for having an expensive INS rig. Fusion of these sensors allows for more effectual tracking to utilize the maximum potential of each sensor while allowing for methods to increase perceptional accuracy. The focus of this thesis will be the dock-less e-scooter and the primary goal will be to track its movements effectively and accurately with respect to cars on the road and the world. Since it is relatively more common to observe a car on the road than e-scooters, we propose a data collection system that can be built on top of an e-scooter and an offline processing pipeline that can be used to collect data in order to understand the behaviors of the e-scooters themselves. In this thesis, we plan to explore a data collection system involving a 3D LIDAR sensor and multiple monocular cameras and an IMU on an e-scooter as well as an offline method for processing the data to generate data to aid scenario reconstruction.
32
Muresan, Alexandru Camil. « Analysis and Definition of the BAT-ME (BATonomous Moon cave Explorer) Mission ». Thesis, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-247507.
Texte intégralRésumé :
Humanity has always wanted to explore the world we live in and answer different questions about our universe. After the International Space Station will end its service one possible next step could be a Moon Outpost: a convenient location for research, astronaut training and technological development that would enable long-duration space. This location can be inside one of the presumed lava tubes that should be present under the surface but would first need to be inspected, possibly by machine capable of capturing and relaying a map to a team on Earth.In this report the past and future Moon base missions will be summarized considering feasible outpost scenarios from the space companies or agencies. and their prospected manned budget. Potential mission profiles, objectives, requirements and constrains of the BATonomous Moon cave Explorer (BAT-ME) mission will be discussed and defined. Vehicle and mission concept will be addressed, comparing and presenting possible propulsion or locomotion approaches inside the lava tube.The Inkonova “Batonomous™” system is capable of providing Simultaneous Localization And Mapping (SLAM), relay the created maps, with the possibility to easily integrate the system on any kind of vehicle that would function in a real-life scenario.Although the system is not fully developed, it will be assessed from a technical perspective, and proper changes for a viable system transition for the space-Moon environment will be devised. The transition of the system from the Batonomous™ state to the BAT-ME required state will be presented from the requirement, hardware, software, electrical and operational point of view.The mission will be devised into operational phases, with key goals in mind. Two different vehicles will be presented and designed on a high engineering level. A risk analysis and management system will be made to understand the possible negative outcomes of different parts failure on the mission outcome.