Julio Montesdeoca

In modern industry, continuous production systems require the integration of monitoring systems capable of real-time inspection and anomaly detection of final products. This necessitates high-speed capture of product images and rapid information processing to determine the rejection of defective products. To address the challenges of reducing processing time and increasing fault recognition accuracy in products, a novel detection method based on image analysis and subsequent classification is proposed. While the techniques employed, such as image histograms and Principal Component Analysis, are well-established in image and data processing, the innovative integration of these methods in this approach provides a streamlined and highly efficient solution for classification. Specifically, the classification process relies on prior image processing, where the histograms of the 3 color channels of each image are obtained and concatenated, then PCA is applied, resulting in separable clusters. Cluster classification is achieved through a simple SVM. A significant advantage of this method is that it requires a reduced amount of image data for training the SVM, simplifying this stage of the process. The proposed method is benchmarked using a dataset of images aimed at detecting defects in a pill blister pack, which may include missing pills, while a data augmentation process is implemented. The relationship between the image histogram and the presence of faults is demonstrated under controlled lighting and sensor arrangement environments.

This work presents an open-source simulation framework designed to extend the capabilities of the VRX environment for developing and validating control strategies for surface robotic vehicles. The platform features a custom monohull, kayak-type USV with four thrusters in differential configuration, represented with a complete graphical mockup consistent with its physical design and modeled with realistic dynamics and sensor integration. A thrust mapping function was calibrated using manufacturer data, and the vehicle’s behavior was characterized using a simplified Fossen model with parameters identified via Least Squares estimation. Multiple motion controllers, including velocity, position, trajectory tracking, and path guidance, were implemented and evaluated in a variety of wave and wind scenarios designed to test the full vehicle dynamics and closed-loop behavior. In addition to extending the VRX simulator, this work introduces a new USV model, a calibrated thrust response, and a set of model-based controllers validated in high-fidelity marine conditions. The resulting framework constitutes a reproducible and extensible resource for the marine robotics community, with direct applications in robotic education, perception, and advanced control systems.

En este documento se presenta los resultados de simulación del diseño de un controlador cinemático para seguimiento de trayectoria aplicado a un robot móvil tipo auto. Dentro del diseño de la ley de control se considera las limitaciones de giro en el volante y la limitada velocidad del robot. Además de ello se considera el punto de interés en una posición arbitraria dentro o fuera del cuerpo del robot. La trayectoria se obtiene de un proceso de planificación en donde se presta atención a la limitación del giro del volante. Las simulaciones muestran un gran desempeño del controlador.

A complete characterization of the behavior in human-robot interaction (HRI) includes both: the behavior dynamic and the control laws that characterize as the behavior is regulated with the perception information. In this way, the present work proposes a leader-follower coordinated control that allows to include special dynamic behaviors between humans. Additionally these have been supported by social rules of proxemics and dynamic models of human-behavior that guarantee more comfortable interactions. For the detection and following of the human, it is used a Kinect® sensor on board of a Pioneer 3AT® robot (a differential drive robot), which allows the experimental validation of the proposed scheme of control.

Early detection of faults in power lines allows improve the service quality and therefore a reduction in high operating costs that a failure of this type implies. This paper describes a method used to determine the type of failure occurs in a three-phase over time, using tools as Hilbert transform and fuzzy classifier for successful detection is done. The algorithm developed uses each of the power lines phases which are analyzed in its angle of coverage and its variation in time, after this analysis the results classified by a classifier Fuzzy c-means. This classifier makes groups of fault data and no-fault data. The results show a high performance in classified values near to zero as correct.

Previous works in analysis and design of biosignals acquisition have been done in Universidad Politécnica Salesiana, In this context, this paper presents the results of implementation process of biosignals acquisition lessons with Biopac MP45 by undergraduate students. For each biosignals a protocol acquisition are proposed to safety. Different implementation lessons about in Electromyography (EMG), Electrocardiography (ECG), Electroencephalography (EEG) and Electroculography (EOG) are analyzed, including both frequency and temporal domain. To EMG acquisition lessons a characteristics analysis of amplitude and frequency changes by the wrist flexor when, fist is done. In this context, in ECG acquisition, the Einthoven triangle and derivative and temporal intervals analysis are made. The same form, to EEG acquisition an analysis of how change the frequency activity of cortex when induced to alpha state. Finally to EOG acquisition a verified of behavior signals in ocular movements are made. All this process are implemented by undergraduate students under supervision. The results show a good performance and a correct biosignals acquisition method.