espanolEste articulo propone un sistema de control visual directo basado en imagen para guiar a un manipulador movil. El robot esta compuesto por una plataforma movil diferencial con un brazo de 7 gdl (grados de libertad) y una camara en configuracion eye-in-hand. Como se describe en el documento, la informacion visual se emplea para guiar tanto el robot manipulador como la plataforma base durante el seguimiento de trayectorias definidas en el plano imagen. A diferencia de los enfoques anteriores, el sistema propuesto en este documento emplea un control visual directo para guiar al manipulador movil. De esta forma, el controlador genera directamente los pares (fuerza y momentos) que se aplicaran al manipulador y la plataforma base teniendo en cuenta la dinamica del robot. Este articulo describe los diferentes componentes cinematicos y dinamicos del controlador propuesto y se valida a partir del seguimiento de trayectorias de imagenes repetitivas y no repetitivas. EnglishThis paper proposes a direct image-based visual servoing system for the guidance of a mobile manipulator. The robot is composed of a mobile differential platform with a 7 dof (degrees of freedom) arm and an eye-in-hand camera. As described throughout the paper, the visual information is employed to guide both the robot manipulator and the base platform for the tracking of image trajectories. In contrast with previous approaches, the one proposed in this paper employs a direct visual servoing system for guiding mobile manipulators. In this case, the controller directly generates the torques (force and moments) to be applied to the manipulator and base platform taking into account the robot dynamics. This paper describes the different kinematic and dynamic components of the proposed controller and it is validated during the tracking of repetitive and nonrepetitive image trajectories
This paper describes a whole new framework to quickly develop dynamic visual servoing systems embedded in an FPGA. Parallel design of the algorithms increases the precision of this kind of controllers, whereas minimizes the response time. Embedding dynamic visual servoing algorithms converts these systems into real-time systems. Additionally, an optimal control framework to dynamically visual control robot arms is proposed. The architecture re-configurability is tested with the implementation of two dynamic visual servoing controllers. One of the implemented controllers is derived from the proposed control framework and the other is the well-known image transpose Jacobian controller. From these experiments, FPGA resources utilization and timeline of the pipeline show the optimization of the proposed framework.
El pueblo de Conchillas tiene su origen en la explotación de áridos, arena y piedra triturada para la construcción del puerto de Buenos Aires, durante la presidencia de Julio Roca, en 1880. La actividad de la Empresa Walker y Co. así como el emprendimiento de Ramos Generales de David Evans, generaron en esta parte del territorio uruguayo un centro urbano, una Factory Town, con características socioculturales y edilicias muy particulares, reconocidas como parte del patrimonio histórico nacional. Ya en el siglo XXI, el proyecto de inversión de la empresa ENCE (productora de pasta de celulosa) que no se concretó, dio lugar a un importante estudio de impacto arqueológico, antropológico e histórico en la zona. Más tarde la empresa Montes del Plata, compró los terrenos de ENCE y desarrolló allí el emprendimiento que había quedado trunco. La empresa, operativa desde mediados de 2014, ha constituido un motor de renovación de actividades y de fuentes laborales para Conchillas y alrededores.  
In this paper, a new method to track image trajectories by visual servoing is proposed. This method solves the problem of the previous proposed time-independent tracking systems based on visual servoing. With the proposed method, the robot can track a previously generated trajectory affording a correct tracking not only in the image but also in the 3D space. This new method presents several improvements over the previous ones such as the possibility of specifying the desired tracking velocity, a less oscillating behavior or a correct tracking in the 3D space when high velocities are used. In order to demonstrate the correct behavior of the visual servoing system, an eye-in-hand camera system is used.
The purpose of this paper is to describe a new method for tracking trajectories specified in the image space. This method, called movement flow-based visual servoing system, is applied to an eye-in-hand robot and it is shown that it allows the correct tracking of a trajectory, not only in the image but also in the 3-D space. This method is also extended to the case in which the object from which the features are extracted, is in motion. To do so, the estimations obtained, using several Kalman filters, are integrated in the control action
Traditional visual servoing systems have been widely studied in the last years.These systems control the position of the camera attached to the robot end-effector guiding it from any position to the desired one.These controllers can be improved by using the event-based control paradigm.The system proposed in this paper is based on the idea of activating the visual controller only when something significant has occurred in the system (e.g. when any visual feature can be loosen because it is going outside the frame).Different event triggers have been defined in the image space in order to activate or deactivate the visual controller.The tests implemented to validate the proposal have proved that this new scheme avoids visual features to go out of the image whereas the system complexity is reduced considerably.Events can be used in the future to change different parameters of the visual servoing systems.
The reliance on large-scale datasets and extensive computational resources has become a major barrier to advancing representation learning in vision, especially in data-scarce domains. In this paper, we address the critical question: Can we escape the big data paradigm in self-supervised representation learning from images? We introduce SCOTT (Sparse Convolutional Tokenizer for Transformers), a shallow tokenization architecture that is compatible with Masked Image Modeling (MIM) tasks. SCOTT injects convolutional inductive biases into Vision Transformers (ViTs), enhancing their efficacy in small-scale data regimes. Alongside, we propose to train on a Joint-Embedding Predictive Architecture within a MIM framework (MIM-JEPA), operating in latent representation space to capture more semantic features. Our approach enables ViTs to be trained from scratch on datasets orders of magnitude smaller than traditionally required --without relying on massive external datasets for pretraining. We validate our method on three small-size, standard-resoultion, fine-grained datasets: Oxford Flowers-102, Oxford IIIT Pets-37, and ImageNet-100. Despite the challenges of limited data and high intra-class similarity, frozen SCOTT models pretrained with MIM-JEPA significantly outperform fully supervised methods and achieve competitive results with SOTA approaches that rely on large-scale pretraining, complex image augmentations and bigger model sizes. By demonstrating that robust off-the-shelf representations can be learned with limited data, compute, and model sizes, our work paves the way for computer applications in resource constrained environments such as medical imaging or robotics. Our findings challenge the prevailing notion that vast amounts of data are indispensable for effective representation learning in vision, offering a new pathway toward more accessible and inclusive advancements in the field.
In the last years, 3D-vision systems based on the time-of-flight (ToF) principle have gained more importance in order to obtain 3D information from the workspace. In this paper, an analysis of the use of 3D ToF cameras to guide a robot arm is performed. To do so, an adaptive method to simultaneous visual servo control and camera calibration is presented. Using this method a robot arm is guided by using range information obtained from a ToF camera. Furthermore, the self-calibration method obtains the adequate integration time to be used by the range camera in order to precisely determine the depth information.
