Cette thèse se situe dans le domaine de l'auto-localisation et de la cartographie 3D des caméras RGB-D pour des robots mobiles et des systèmes autonomes avec des caméras RGB-D. Nous présentons des techniques d'alignement et de cartographie pour effectuer la localisation d'une caméra (suivi), notamment pour des caméras avec mouvements rapides ou avec faible cadence. Les domaines d'application possibles sont la réalité virtuelle et augmentée, la localisation de véhicules autonomes ou la reconstruction 3D des environnements.Nous proposons un cadre consistant et complet au problème de localisation et cartographie 3D à partir de séquences d'images RGB-D acquises par une plateforme mobile. Ce travail explore et étend le domaine d'applicabilité des approches de suivi direct dites "appearance-based". Vis-à-vis des méthodes fondées sur l'extraction de primitives, les approches directes permettent une représentation dense et plus précise de la scène mais souffrent d'un domaine de convergence plus faible nécessitant une hypothèse de petits déplacements entre images.Dans la première partie de la thèse, deux contributions sont proposées pour augmenter ce domaine de convergence. Tout d'abord une méthode d'estimation des grands déplacements est développée s'appuyant sur les propriétés géométriques des cartes de profondeurs contenues dans l'image RGB-D. Cette estimation grossière (rough estimation) peut être utilisée pour initialiser la fonction de coût minimisée dans l'approche directe. Une seconde contribution porte sur l'étude des domaines de convergence de la partie photométrique et de la partie géométrique de cette fonction de coût. Il en résulte une nouvelle fonction de coût exploitant de manière adaptative l'erreur photométrique et géométrique en se fondant sur leurs propriétés de convergence respectives.Dans la deuxième partie de la thèse, nous proposons des techniques de régularisation et de fusion pour créer des représentations précises et compactes de grands environnements. La régularisation s'appuie sur une segmentation de l'image sphérique RGB-D en patchs utilisant simultanément les informations géométriques et photométriques afin d'améliorer la précision et la stabilité de la représentation 3D de la scène. Cette segmentation est également adaptée pour la résolution non uniforme des images panoramiques. Enfin les images régularisées sont fusionnées pour créer une représentation compacte de la scène, composée de panoramas RGB-D sphériques distribués de façon optimale dans l'environnement. Ces représentations sont particulièrement adaptées aux applications de mobilité, tâches de navigation autonome et de guidage, car elles permettent un accès en temps constant avec une faible occupation de mémoire qui ne dépendent pas de la taille de l'environnement. / This thesis is in the context of self-localization and 3D mapping from RGB-D cameras for mobile robots and autonomous systems. We present image alignment and mapping techniques to perform the camera localization (tracking) notably for large camera motions or low frame rate. Possible domains of application are localization of autonomous vehicles, 3D reconstruction of environments, security or in virtual and augmented reality. We propose a consistent localization and 3D dense mapping framework considering as input a sequence of RGB-D images acquired from a mobile platform. The core of this framework explores and extends the domain of applicability of direct/dense appearance-based image registration methods. With regard to feature-based techniques, direct/dense image registration (or image alignment) techniques are more accurate and allow us a more consistent dense representation of the scene. However, these techniques have a smaller domain of convergence and rely on the assumption that the camera motion is small.In the first part of the thesis, we propose two formulations to relax this assumption. Firstly, we describe a fast pose estimation strategy to compute a rough estimate of large motions, based on the normal vectors of the scene surfaces and on the geometric properties between the RGB-D images. This rough estimation can be used as initialization to direct registration methods for refinement. Secondly, we propose a direct RGB-D camera tracking method that exploits adaptively the photometric and geometric error properties to improve the convergence of the image alignment.In the second part of the thesis, we propose techniques of regularization and fusion to create compact and accurate representations of large scale environments. The regularization is performed from a segmentation of spherical frames in piecewise patches using simultaneously the photometric and geometric information to improve the accuracy and the consistency of the scene 3D reconstruction. This segmentation is also adapted to tackle the non-uniform resolution of panoramic images. Finally, the regularized frames are combined to build a compact keyframe-based map composed of spherical RGB-D panoramas optimally distributed in the environment. These representations are helpful for autonomous navigation and guiding tasks as they allow us an access in constant time with a limited storage which does not depend on the size of the environment.

Les travaux présentés ici concernent le domaine de la localisation de véhicule par vision artificielle. Dans ce contexte, la trajectoire d’une caméra et la structure3D de la scène filmée sont estimées par une méthode d’odométrie visuelle monoculaire basée sur l’ajustement de faisceaux local. Les contributions de cette thèse sont plusieurs améliorations de cette méthode. L’incertitude associée à la position estimée n’est pas fournie par la méthode d’ajustement de faisceaux local. C’est pourtant une information indispensable pour pouvoir utiliser cette position, notamment dans un système de fusion multi-sensoriel. Une étude de la propagation d’incertitude pour cette méthode d’odométrie visuelle a donc été effectuée pour obtenir un calcul d’incertitude temps réel et représentant l’erreur de manière absolue (dans le repère du début de la trajectoire). Sur de longues séquences (plusieurs kilomètres), les méthodes monoculaires de localisation sont connues pour présenter des dérives importantes dues principalement à la dérive du facteur d’échelle (non observable). Pour réduire cette dérive et améliorer la qualité de la position fournie, deux méthodes de fusion ont été développées. Ces deux améliorations permettent de rendre cette méthode monoculaire exploitable dans le cadre automobile sur de grandes distances tout en conservant les critères de temps réel nécessaire dans ce type d’application. De plus, notre approche montre l’intérêt de disposer des incertitudes et ainsi de tirer parti de l’information fournie par d’autres capteurs. / The present work is about localisation of vehicle using computer vision methods. In this context, the camera trajectory and the 3D structure of the scene is estimated by a monocular visual odometry method based on local bundle adjustment. This thesis contributions are some improvements of this method. The uncertainty of the estimated position was not provided by the local bundle adjustment method. Indeed, this uncertainty is crucial in a multi-sensorial fusion system to use optimally the estimated position. A study of the uncertainty propagation in this visual odometry method has been done and an uncertainty calculus method has been designed to comply with real time performance. By the way, monocular visual localisation methods are known to have serious drift issues on long trajectories (some kilometers). This error mainly comes from bad propagation of the scale factor. To limit this drift and improve the quality of the given position, we proposed two data fusion methods between an odometer and the visual method. Finally, the two improvements presented here allow us to use visual localisation method in real urban environment on long trajectories under real time constraints.

The focus of this thesis is to theoretically design, describe, implement and verify thefunctionality of the selected concept for race track mapping. The theoretical part ofthe thesis describes the ORB-SLAM2 algorithm for vehicle localization. It then furtherdescribes the format of the map - occupancy grid and the method of its creation. Suchmap should be in a suitable format for use by other trajectory planning systems. Severalcameras, as well as computer units, are described in this part, and based on parametersand tests, the most suitable ones are selected. The thesis also proposes the architectureof the mapping system, it describes the individual units that make up the system, aswell as what is exchanged between the units, and in what format the system output issent. The individual parts of the system are first tested separately and subsequently thesystem is tested as a whole. Finally, the achieved results are evaluated as well as thepossibilities for further expansion.

When reconstructing the Earth in 3D, the imagery can come from various mediums, including satellites, planes, and drones. One significant benefit of utilizing drones in combination with a Visual Simultaneous Localization and Mapping (V-SLAM) system is that specific areas of the world can be accurately mapped in real-time at a low cost. Drones can essentially be equipped with any camera sensor, but most commercially available drones use a monocular rolling shutter camera sensor. Therefore, on behalf of Maxar Technologies, multiple monocular V-SLAM systems were studied during this thesis, and ORB-SLAM3 and LDSO were determined to be evaluated further. In order to provide an accurate and reproducible result, the methods were benchmarked on the public datasets EuRoC MAV and TUM monoVO, which includes drone imagery and outdoor sequences, respectively. A third dataset was collected with a DJI Mavic 2 Enterprise Dual drone to evaluate how the methods would perform with a consumer-friendly drone. The datasets were used to evaluate the two V-SLAM systems regarding the generated 3D map (point cloud) and estimated camera trajectory. The results showed that ORB-SLAM3 is less impacted by the artifacts caused by a rolling shutter camera sensor than LDSO. However, ORB-SLAM3 generates a sparse point cloud where depth perception can be challenging since it abstracts the images using feature descriptors. In comparison, LDSO produces a semi-dense 3D map where each point includes the pixel intensity, which improves the depth perception. Furthermore, LDSO is more suitable for dark environments and low-texture surfaces. Depending on the use case, either method can be used as long as the required prerequisites are provided. In conclusion, monocular V-SLAM systems are highly dependent on the type of sensor being used. The differences in the accuracy and robustness of the systems using a global shutter and a rolling shutter are significant, as the geometric artifacts caused by a rolling shutter are devastating for a pure visual pipeline. / <p>Examensarbetet är utfört vid Institutionen för teknik och naturvetenskap (ITN) vid Tekniska fakulteten, Linköpings universitet</p>

<p>  </p> <p>This research is motivated by the potential of autonomous mobile robots (AMRs) in enhancing safety, productivity, and efficiency in the construction industry. The dynamic and complex nature of construction sites presents significant challenges to AMRs, particularly in localization and mapping – a process where AMRs determine their own position in the environment while creating a map of the surrounding area. These capabilities are crucial for autonomous navigation and task execution but are inadequately addressed by existing solutions, which primarily rely on visual Simultaneous Localization and Mapping (SLAM) methods. These methods are often ineffective in construction sites due to their underlying assumption of a static environment, leading to unreliable outcomes. Therefore, there is a pressing need to enhance the applicability of AMRs in construction by addressing the limitations of current localization and mapping methods in addressing the dynamic nature of construction sites, thereby empowering AMRs to function more effectively and fully realize their potential in the construction industry.</p> <p>The overarching goal of this research is to fulfill this critical need by developing a novel visual SLAM framework that is capable of not only detecting and segmenting diverse dynamic objects in construction environments but also effectively interpreting the semantic structure of the environment. Furthermore, it can efficiently integrate these functionalities into a unified system to provide an improved SLAM solution for dynamic, complex, and unstructured environments. The rationale is that such a SLAM system could effectively address the dynamic nature of construction sites, thereby significantly improving the efficiency and accuracy of robot localization and mapping in the construction working environment. </p> <p>Towards this goal, three specific objectives have been formulated. The first objective is to develop a novel methodology for comprehensive dynamic object segmentation that can support visual SLAM within highly variable construction environments. This novel method integrates class-agnostic objectness masks and motion cues into video object segmentation, thereby significantly improving the identification and segmentation of dynamic objects within construction sites. These dynamic objects present a significant challenge to the reliable operation of AMRs and, by accurately identifying and segmenting them, the accuracy and reliability of SLAM-based localization is expected to greatly improve. The key to this innovative approach involves a four-stage method for dynamic object segmentation, including objectness mask generation, motion saliency estimation, fusion of objectness masks and motion saliency, and bi-directional propagation of the fused mask. Experimental results show that the proposed method achieves a highest of 6.4% improvement for dynamic object segmentation than state-of-the-art methods, as well as lowest localization errors when integrated into visual SLAM system over public dataset. </p> <p>The second objective focuses on developing a flexible, cost-effective method for semantic segmentation of construction images of structural elements. This method harnesses the power of image-level labels and Building Information Modeling (BIM) object data to replace the traditional and often labor-intensive pixel-level annotations. The hypothesis for this objective is that by fusing image-level labels with BIM-derived object information, a segmentation that is competitive with pixel-level annotations while drastically reducing the associated cost and labor intensity can be achieved. The research method involves initializing object location, extracting object information, and incorporating location priors. Extensive experiments indicate the proposed method with simple image-level labels achieves competitive results with the full pixel-level supervisions, but completely remove the need for laborious and expensive pixel-level annotations when adapting networks to unseen environments. </p> <p>The third objective aims to create an efficient integration of dynamic object segmentation and semantic interpretation within a unified visual SLAM framework. It is proposed that a more efficient dynamic object segmentation with adaptively selected frames combined with the leveraging of a semantic floorplan from an as-built BIM would speed up the removal of dynamic objects and enhance localization while reducing the frequency of scene segmentation. The technical approach to achieving this objective is through two major modifications to the classic visual SLAM system: adaptive dynamic object segmentation, and semantic-based feature reliability update. Upon the accomplishment of this objective, an efficient framework is developed that seamlessly integrates dynamic object segmentation and semantic interpretation into a visual SLAM framework. Experiments demonstrate the proposed framework achieves competitive performance over the testing scenarios, with processing time almost halved than the counterpart dynamic SLAM algorithms.</p> <p>In conclusion, this research contributes significantly to the adoption of AMRs in construction by tailoring a visual SLAM framework specifically for dynamic construction sites. Through the integration of dynamic object segmentation and semantic interpretation, it enhances localization accuracy, mapping efficiency, and overall SLAM performance. With broader implications of visual SLAM algorithms such as site inspection in dangerous zones, progress monitoring, and material transportation, the study promises to advance AMR capabilities, marking a significant step towards a new era in construction automation.</p>

[pt] Robôs móveis são cada dia mais importantes na sociedade moderna, realizando tarefas consideradas tediosas ou muito repetitivas para humanos, como limpeza ou patrulhamento. A maioria dessas tarefas requer um certo nível de autonomia do robô. Para que o robô seja considerado autônomo, ele precisa de um mapa do ambiente, e de sua posição e orientação nesse mapa. O problema de localização e mapeamento simultâneos (SLAM) é a tarefa de estimar tanto o mapa quanto a posição e orientação simultaneamente, usando somente informações dos sensores, sem ajuda externa. O problema de SLAM visual consiste na tarefa de realizar SLAM usando somente câmeras para o sensoriamento. A maior vantagem de usar câmeras é a possibilidade de resolver problemas de visão computacional que provêm informações de alto nível sobre a cena, como detecção de objetos. Porém a maioria dos sistemas de SLAM visual assume um ambiente estático, o que impõe limitações para a sua aplicabilidade em cenários reais. Esta tese apresenta soluções para o problema de SLAM visual em ambientes dinâmicos e em mudança. Especificamente, a tese propõe um método para ambientes com multidões, junto com um detector de pessoas customizado baseado em aprendizado profundo. Além disso, também é proposto um método de SLAM visual para ambientes altamente dinâmicos contendo objetos em movimento, combinando um rastreador de objetos robusto com um algoritmo de filtragem de pontos. Além disso, esta tese propõe um método de SLAM visual para ambientes em mudança, isto é, em cenas onde os objetos podem mudar de lugar após o robô já os ter mapeado. Todos os métodos propostos são testados com dados públicos e experimentos, e comparados com diversos métodos da literatura, alcançando um bom desempenho em tempo real. / [en] Mobile robots have become increasingly important in modern society, as they can perform tasks that are tedious or too repetitive for humans, such as cleaning and patrolling. Most of these tasks require a certain level of autonomy of the robot. To be fully autonomous and perform navigation, the robot needs a map of the environment and its pose within this map. The Simultaneous Localization and Mapping (SLAM) problem is the task of estimating both map and localization, simultaneously, only using sensor measurements. The visual SLAM problem is the task of performing SLAM only using cameras for sensing. The main advantage of using cameras is the possibility of solving computer vision problems that provide high-level information about the scene, such as object detection. However, most visual SLAM systems assume a static environment, which imposes a limitation on their applicability in real-world scenarios. This thesis presents solutions to the visual SLAM problem in dynamic and changing environments. A custom deep learning-based people detector allows our solution to deal with crowded environments. Also, a combination of a robust object tracker and a filtering algorithm enables our visual SLAM system to perform well in highly dynamic environments containing moving objects. Furthermore, this thesis proposes a visual SLAM method for changing environments, i.e., in scenes where the objects are moved after the robot has already mapped them. All proposed methods are tested in datasets and experiments and compared with several state-of-the-art methods, achieving high accuracy in real time.

This thesis covers the topic of image matching in a visual SLAM or SfM context. These problems are generally based on a vector representation of the keypoints of one image, called a descriptor, which we seek to map to the keypoints of another, using a similarity measure to compare the descriptors. However, it remains difficult to perform this matching successfully, especially for challenging scenes where illumination changes, occlusions, motion, textureless and similar features are present, leading to mis-matched points. In this thesis, we develop a self-supervised contrastive deep learning framework for computing robust descriptors, particularly for these challenging situations.We use the TartanAir dataset built explicitly for this task, and in which these difficult scene cases are present. Our results show that descriptor learning works, improves scores, and that our method is competitive with traditional methods such as ORB. In particular, the invariance built implicitly by training pairs of positive examples through the construction of a trajectory from a sequence of images, as well as the controlled introduction of ambiguous negative examples during training, have a real observable effect on the scores obtained. / Le présent mémoire traite du sujet de mise en correspondance entre deux images dans un contexte de SLAM visuel ou de SfM. Ces problèmes reposent généralement sur une représentation vectorielle de points saillants d’une image, appelée descripteur, et qu’on cherche à mettre en correspondance avec les points saillants d’une autre, en utilisant une mesure de similarité pour comparer les descripteurs. Cependant, il reste difficile de réaliser cette mise en correspondance avec succès, en particulier pour les scènes difficiles où des changements d’illumination, des occultations, des mouvements, des éléments sans texture, et des éléments similaires sont présents, conduisant à des mises en correspondance incorrectes. Nous développons dans ce mémoire une méthode d’apprentissage profond contrastif auto-supervisé pour calculer des descripteurs robustes, particulièrement à ces situations difficiles. Nous utilisons le jeu de données TartanAir construit explicitement pour cette tâche, et dans lequel ces cas de scènes difficiles sont présents. Nos résultats montrent que l’apprentissage de descripteurs fonctionne, améliore les scores, et que notre méthode est compétitive avec les méthodes traditionnelles telles que ORB. En particulier, l’invariance bâtie implicitement en formant des paires d’exemples positifs grâce à la construction d’une trajectoire depuis une séquence d’images, ainsi que l’introduction contrôlée d’exemples négatifs ambigus pendant l’entraînement a un réel effet observable sur les scores obtenus.

Ce mémoire décrit mes travaux de thèse de doctorat menés au sein de l’équipe ComSee (Computers that See) rattachée à l’axe ISPR (Image, Systèmes de Perception et Robotique) de l’Institut Pascal. Celle-ci a été financée par la Région Auvergne et le Fonds Européen de Développement Régional. Les travaux présentés s’inscrivent dans le cadre d’applications de localisation pour la robotique mobile et la Réalité Augmentée. Le framework réalisé au cours de cette thèse est une approche générique pour l’implémentation d’applications de SLAM : Simultaneous Localization And Mapping (algorithme de localisation par rapport à un modèle simultanément reconstruit). L’approche intègre une multitude de contraintes dans les processus de localisation et de reconstruction. Ces contraintes proviennent de données capteurs mais également d’a priori liés au contexte applicatif. Chaque contrainte est utilisée au sein d’un même algorithme d’optimisation afin d’améliorer l’estimation du mouvement ainsi que la précision du modèle reconstruit. Trois problèmes ont été abordés au cours de ce travail. Le premier concerne l’utilisation de contraintes sur le modèle reconstruit pour l’estimation précise d’objets 3D partiellement connus et présents dans l’environnement. La seconde problématique traite de la fusion de données multi-capteurs, donc hétérogènes et asynchrones, en utilisant un unique algorithme d’optimisation. La dernière problématique concerne la génération automatique et efficace d’algorithmes d’optimisation à contraintes multiples. L’objectif est de proposer une solution temps réel 1 aux problèmes de SLAM à contraintes multiples. Une approche générique est utilisée pour concevoir le framework afin de gérer une multitude de configurations liées aux différentes contraintes des problèmes de SLAM. Un intérêt tout particulier a été porté à la faible consommation de ressources (mémoire et CPU) tout en conservant une grande portabilité. De plus, la méta-programmation est utilisée pour générer automatiquement et spécifiquement les parties les plus complexes du code en fonction du problème à résoudre. La bibliothèque d’optimisation LMA qui a été développée au cours de cette thèse est mise à disposition de la communauté en open-source. Des expérimentations sont présentées à la fois sur des données de synthèse et des données réelles. Un comparatif exhaustif met en évidence les performances de la bibliothèque LMA face aux alternatives les plus utilisées de l’état de l’art. De plus, le framework de SLAM est utilisé sur des problèmes impliquant une difficulté et une quantité de contraintes croissantes. Les applications de robotique mobile et de Réalité Augmentée mettent en évidence des performances temps réel et un niveau de précision qui croît avec le nombre de contraintes utilisées. / This report describes my thesis work conducted within the ComSee (Computers That See) team related to the ISPR axis (ImageS, Perception Systems and Robotics) of Institut Pascal. It was financed by the Auvergne Région and the European Fund of Regional Development. The thesis was motivated by localization issues related to Augmented Reality and autonomous navigation. The framework developed during this thesis is a generic approach to implement SLAM algorithms : Simultaneous Localization And Mapping. The proposed approach use multiple constraints in the localization and mapping processes. Those constraints come from sensors data and also from knowledge given by the application context. Each constraint is used into one optimization algorithm in order to improve the estimation of the motion and the accuracy of the map. Three problems have been tackled. The first deals with constraints on the map to accurately estimate the pose of 3D objects partially known in the environment. The second problem is about merging multiple heterogeneous and asynchronous data coming from different sensors using an optimization algorithm. The last problem is to write an efficient and real-time implementation of the SLAM problem using multiple constraints. A generic approach is used to design the framework and to generate different configurations, according to the constraints, of each SLAM problem. A particular interest has been put in the low computational requirement (in term of memory and CPU) while offering a high portability. Moreover, meta-programming techniques have been used to automatically and specifically generate the more complex parts of the code according to the given problem. The optimization library LMA, developed during this thesis, is made available of the community in open-source. Several experiments were done on synthesis and real data. An exhaustive benchmark shows the performances of the LMA library compared to the most used alternatives of the state of the art. Moreover, the SLAM framework is used on different problems with an increasing difficulty and amount of constraints. Augmented Reality and autonomous navigation applications show the good performances and accuracies in multiple constraints context.

To navigate successfully in a previously unexplored environment, a mobile robot must be able to estimate the spatial relationships of the objects of interest accurately. A Simultaneous Localization and Mapping (SLAM) sys- tem employs its sensors to build incrementally a map of its surroundings and to localize itself in the map simultaneously. The aim of this research project is to develop a SLAM system suitable for self propelled household lawnmowers. The proposed bearing-only SLAM system requires only an omnidirec- tional camera and some inexpensive landmarks. The main advantage of an omnidirectional camera is the panoramic view of all the landmarks in the scene. Placing landmarks in a lawn field to define the working domain is much easier and more flexible than installing the perimeter wire required by existing autonomous lawnmowers. The common approach of existing bearing-only SLAM methods relies on a motion model for predicting the robot’s pose and a sensor model for updating the pose. In the motion model, the error on the estimates of object positions is cumulated due mainly to the wheel slippage. Quantifying accu- rately the uncertainty of object positions is a fundamental requirement. In bearing-only SLAM, the Probability Density Function (PDF) of landmark position should be uniform along the observed bearing. Existing methods that approximate the PDF with a Gaussian estimation do not satisfy this uniformity requirement. This thesis introduces both geometric and proba- bilistic methods to address the above problems. The main novel contribu- tions of this thesis are: 1. A bearing-only SLAM method not requiring odometry. The proposed method relies solely on the sensor model (landmark bearings only) without relying on the motion model (odometry). The uncertainty of the estimated landmark positions depends on the vision error only, instead of the combination of both odometry and vision errors. 2. The transformation of the spatial uncertainty of objects. This thesis introduces a novel method for translating the spatial un- certainty of objects estimated from a moving frame attached to the robot into the global frame attached to the static landmarks in the environment. 3. The characterization of an improved PDF for representing landmark position in bearing-only SLAM. The proposed PDF is expressed in polar coordinates, and the marginal probability on range is constrained to be uniform. Compared to the PDF estimated from a mixture of Gaussians, the PDF developed here has far fewer parameters and can be easily adopted in a probabilistic framework, such as a particle filtering system. The main advantages of our proposed bearing-only SLAM system are its lower production cost and flexibility of use. The proposed system can be adopted in other domestic robots as well, such as vacuum cleaners or robotic toys when terrain is essentially 2D.

Made available in DSpace on 2014-12-17T14:55:06Z (GMT). No. of bitstreams: 1 GutembergSS.pdf: 569123 bytes, checksum: 6f85b5ee47010d2d331986f17689304b (MD5) Previous issue date: 2008-05-30 / This work presents a cooperative navigation systemof a humanoid robot and a wheeled robot using visual information, aiming to navigate the non-instrumented humanoid robot using information obtained from the instrumented wheeled robot. Despite the humanoid not having sensors to its navigation, it can be remotely controlled by infra-red signals. Thus, the wheeled robot can control the humanoid positioning itself behind him and, through visual information, find it and navigate it. The location of the wheeled robot is obtained merging information from odometers and from landmarks detection, using the Extended Kalman Filter. The marks are visually detected, and their features are extracted by image processing. Parameters obtained by image processing are directly used in the Extended Kalman Filter. Thus, while the wheeled robot locates and navigates the humanoid, it also simultaneously calculates its own location and maps the environment (SLAM). The navigation is done through heuristic algorithms based on errors between the actual and desired pose for each robot. The main contribution of this work was the implementation of a cooperative navigation system for two robots based on visual information, which can be extended to other robotic applications, as the ability to control robots without interfering on its hardware, or attaching communication devices / Este trabalho apresenta um sistema de navega??o cooperativa de um rob? human?ide e um rob? com rodas usando informa??o visual, com o objetivo de efetuar a navega??o do rob? human?ide n?o instrumentado utilizando-se das informa??es obtidas do rob? com rodas instrumentado. Apesar do human?ide n?o possuir sensores para sua navega??o, pode ser remotamente controlado por sinal infravermelho. Assim, o rob? com rodas pode controlar o human?ide posicionando-se atr?s dele e, atrav?s de informa??o visual, localiz?-lo e naveg?-lo. A localiza??o do rob? com rodas ? obtida fundindo-se informa??es de odometria e detec??o de marcos utilizando o filtro de Kalman estendido. Os marcos s?o detectados visualmente, e suas caracter?sticas s?o extra?das pelo o processamento da imagem. As informa??es das caracter?sticas da imagem s?o utilizadas diretamente no filtro de Kalman estendido. Assim, enquanto o rob? com rodas localiza e navega o human?ide, realiza tamb?m sua localiza??o e o mapeamento do ambiente simultaneamente (SLAM). A navega??o ? realizada atrav?s de algoritmos heur?sticos baseados nos erros de pose entre a pose dos rob?s e a pose desejada para cada rob?. A principal contribui??o desse trabalho foi a implementa??o de um sistema de navega??o cooperativa entre dois rob?s baseados em informa??o visual, que pode ser estendido para outras aplica??es rob?ticas, dado a possibilidade de se controlar rob?s sem interferir em seu hardware, ou acoplar dispositivos de comunica??o