Fernando Ulloa-Vásquez

This work presents a Neuro-Adaptive Model Reference Adaptive Control (NA-MRAC) strategy for trajectory tracking in wheeled mobile robots (WMRs) subject to nonlinear dynamics, load-dependent variations, and unmodeled uncertainties. The proposed approach integrates an inverse-kinematics controller with a dynamic NA-MRAC structure that merges a radial-basis-function neural network and a regressor-based adaptive mechanism, enabling simultaneous compensation of parametric deviations and nonlinear residual dynamics. A complete stability analysis of the cascade kinematic–dynamic architecture is provided, establishing bounded-error behavior under the derived adaptation laws. The method is assessed in simulation using a Pioneer 3DX platform in MobileSim, including scenarios with sudden payload changes, nonsmooth trajectories with directional discontinuities, and a comparative evaluation against a non-adaptive MRAC implementation and a regression-based MRAC controller. The results show that the NA-MRAC provides improved robustness and disturbance rejection, with faster transient response and reduced tracking error in the evaluated scenarios, compared to the other approaches.

The loss of localization in robots navigating GNSS-denied environments poses a critical challenge that can compromise mission success and safe operation. This article presents a method that fuses visual odometry outputs from both direct and feature-based (indirect) methods using Iterated Conditional Modes (ICMs), an efficient iterative optimization algorithm that maximizes the posterior probability in Markov random fields, combined with uncertainty-aware gain adjustment to perform pose estimation and mapping. The proposed method enhances the performance of visual localization and mapping algorithms in low-texture or visually degraded scenarios. The method was validated using the TUM RGB-D benchmark dataset and through real-world tests in both indoor and outdoor environments. Outdoor experiments were conducted on an electric vehicle, where the method maintained stable tracking. These initial results suggest that the technique could be transferable to electric vehicle platforms and applicable in a variety of real-world conditions.

Los incovenientes planteados por el seguimiento de trayectorias usando robots móviles es un tema vigente en la teoría de control, en esta propuesta se presenta el diseño de un controlador de álgebra lineal en combinación con un estimador neuronal. Donde además el robot móvil cuenta con incertidumbres aditívas. Los valores de incertidumbre en cada momento de muestreo se obtienen mediante estimación basada en Redes Neuronales, donde se incluye el diseño de un estimador neuronal del error de modelado junto con la demostración de la convergencia a cero del error de seguimiento. La técnica de control propuesta se valida mediante simulación y resultados experimentales. El controlador de Ágebra Lineal y el estimador neuronal demuestran que se puede utilizar para reducir el efecto de las incertidumbres aditivas en el error de control de seguimiento.

The growing demand for electricity and the constant increase in electricity rates have intensified the interest of residential and non-residential energy consumers to reduce their energy consumption. The introduction of non-conventional renewable energies (photovoltaic and wind, in the residential case) demands new proposals to obtain a home energy management system (HEMS), which allows reducing the use of electrical energy. This article incorporates artificial intelligence techniques to demand response, allowing control, switching, turning on and off of appliances, modifying and reducing consumption, and achieving improvements in the quality of life in the home. In addition, an architecture based on a smart socket and an artificial intelligence model that recognizes the consumption of electrical appliances in high resolution (sampling every 10 s) is proposed. The system uses the Wi-Fi communication protocol, ensuring that the smart sockets wirelessly provide the data obtained to the public cloud. The use of Deep Learning allows us to obtain a central control model of the home, which, when interconnected to the smart electrical distribution networks of companies, could generate a positive impact on the environmental effects and CO₂ reduction.

The introduction of non-conventional renewable energies (photovoltaic and wind, in the residential case) demand new proposals and opportunities to obtain a domestic energy management system (HEMS), which allows reducing the use of electrical energy. The HEMS incorporates artificial intelligence (AI) techniques to respond to energy demand (DR), which can control, switch, turn on and off, modifying the consumption profile, reducing monthly billing, which as a consequence brings improvement. of the quality of life at home. Based on what has been described, a model for identifying electrical appliances and determining consumption patterns for the home is proposed, using intrusive measurement/actuator equipment called Smart Socket. The Smart Socket measures the electrical variables of voltage and current in real time, calculating the powers and active-reactive-apparent energies of each household appliance (or the most relevant ones). The information provided by the Smart Socket is used as a basis to configure the HEMS, with the aim of optimizing energy use using artificial intelligence techniques and tools, thus reducing energy consumption, CO2 emissions and the user's monthly billing. residential.

This work allows characterizing and classifying the consumption profiles of non-residential customers (without distributed generation) based on the consumption curves obtained from the records reported by 934 smart meters in the period from January to December 2019, and which belong to an electric power distribution company in Chile, SAESA Group S.A. To achieve the characterization and classification of the consumption profiles, three typical days are analyzed and determined, which correspond to working days (Monday to Friday), Saturdays, and Sundays or holidays. These three typical days are analyzed for each trimester of 2019. The data processing is carried out on the Power Bi and Matlab^® platforms. In Power Bi, the data provided by the electricity company are worked, obtaining the average consumption curves for each client in each period of study considered, while in Matlab^®, the visualization and classification of the curves is carried out using the K-means algorithm, to finally obtain the results and conclusions. The results show the existence of seven typical profiles representative of the behavior of non-residential clients, which, in some cases, show similar behaviors, despite being from different categories.

The need to determine which wireless IoT technology, currently available on the market, will be able to support a sizeable simultaneous load of information, types of electrical emergency alarms, required bandwidths, delays-latency, area coverage, and economic cost to serve areas of 600 square kilometers of surface and several users of around two million homes. This article compares Sigfox, LoRa, NB-IoT, and WiMAX technologies as possible solutions for last-mile communications. For this purpose, a network of hundreds of smart meters has been simulated, each transmitting different types of information. In conclusion, it has been obtained that, for a context with the priority of alarms and a large amount of information transport in massive last-mile communications in smart grids and for electrical metering traffic, it is highly recommended that it be done through WiMAX, which in the evaluation shows the best result compared to the other technologies.

In this paper, a pricing alternative based on the scheme of Time of Use Pricing (TOUP) is proposed for customers connected to the Cooperativa Eléctrica San Pedro de Atacama (CESPA) microgrid, located in the far north of Chile. With this proposal, the promotion of Demand-Side Management, DSM, aims at optimizing both the use of electric energy and the available infrastructure. The pricing proposal replaces the current tariff scheme based on sections of energy consumption and does not give an incentive for customers to efficiently manage their energy consumption. The proposal considers the creation of time bands and their corresponding tariff formulas, to obtain economic benefits both for customers and the electric company. Study cases consider the operation of a photovoltaic plant of 2 MWp in the electric system of CESPA, which is currently underway. The obtained results report benefits for all parts of the electric market. For customers, favorable pricing up to a 19.1% monthly reduction in electric bills is shown, whereas the company presents an increment in their average monthly income of about 7.7%.

Existen múltiples tecnologías para el transporte de info-comunicaciones, entre objetos y máquinas para internet. Dos de las más robustas y de mayor cobertura y que soportan múltiples usuarios son 4G y WiMax IEEE 802.16x. En este trabajo se presenta una simulación de cobertura terrestre de ambas tecnologías de comunicación inalámbrica, como alternativa de comunicación de banda ancha para nuevos operadores libres, privados o soportados por instituciones públicas como municipalidades o cooperativas regionales. Se estudiaron los casos de las ciudades de Riga, Bucarest, Florianópolis, Santiago, Concepción y Copiapó. El estudio utiliza el software Radio Mobile GLOBE-BIL (Versión 11 -3-7), obteniéndose gráficas de cobertura de propagación sobre mapas digitales de elevación de terreno SRTM liberados por la NASA. Esta simulación determina el número de antenas requerida para millones de usuarios en el contexto del Internet de las Cosas, así como cuantificar los kilómetros cuadrados de cobertura de propagación inalámbrica que se pueden alcanzar técnicamente para cada una de las ciudades del proyecto. Los resultados obtenidos muestran que WiMax soporta mayor cantidad de usuarios conectados, posee mejor cobertura y requiere menor número de antenas. Por otro lado, para el indicador de cobertura de propagación los resultados para 5 ciudades son mejor la tecnología WiMax que 4G, salvo Santiago (Chile) donde se alcanza el mejor rendimiento para 4G sobre WiMax.

For an efficient energy management by residential users, monitoring and control of connected household appliances is required. If the consumption pattern of each of these devices is identified, then the management will be more efficient, reducing both the billing and the CO2 emissions. This paper proposes a model for the recognition of energy consumption patterns in household appliances, based on the capture of electrical parameters in connected appliances, through Smart Socket with an Intrusive Load Monitoring approach. The data acquisition system corresponds to an-Internet of Things (IoT) platform that uses Automatic Meter Reading devices, connected to a IoT-gateway via Wi-Fi to send data to an application on the web. For the recognition of the patterns, machine learning techniques are used. Accuracy results on pattern identification are obtained about 91% after applying a backpropagation method in an Artificial Neural Network in time basis. Through this work, the prediction of consumer categories in household appliances, with high levels of reliability and under multiple operating states, is reached. These results enhance the efficient management of energy in a Smart Home and Smart Cities environment