Resumen ResumenEste artículo de investigación ataca el problema de la navegación robótica autónoma basada en sistemas de visión artificial en tiempo real. Como una primera aproximación a un sistema de visión artificial que permita la navegación del robot, se ha desacoplado el módulo sensor e implementado como una unidad independiente sobre un pequeño robot diferencial. Sobre él, se han realizado estudios básicos de navegación por identificación visual de landmarks (marcas especiales) en un ambiente desconocido. Los estudios de desempeño, realizados tanto a través de simulación como por evaluación directa sobre prototipos en laboratorio, demuestran la eficacia de las estructuras propuestas, tanto del hardware de identificación en tiempo real como de la estrategia básica de navegación considerada para su evaluación. Palabras claveAndroid, imágenes, procesamiento en tiempo real, sistema embebido.

One of the most important renewable energy sources today is wind power generation. However, this energy source depends on the flow of air in the area where the wind generators are installed, and as with many other renewable resources, this is a natural resource whose magnitude is not directly controlled by man. The prediction of wind speed then becomes a key problem when we want to project the energy performance of a wind farm. The behaviour of the wind, as a climatic variable, can be estimated from various atmospheric parameters such as temperature, humidity and air pressure. In this paper we propose a multivariate wind speed estimation model from the history of these atmospheric parameters using a deep neural network. The performance of the model is then evaluated against the same historical data, which produces a fairly small error. The code is implemented in Keras deep learning library with TensorFlow backend. Keyword-Atmospheric parameters, Deep learning, Forecasting, Kinematics, Multivariate model, Wind speed I. INTRODUCTION Many developing countries such as Colombia must focus their resources correctly in order to support the development of their individuals [1]. Electricity is a fundamental element for the well-being of individuals and the industrial development of a country, therefore it is also widely used as an indicator of development. Colombia has many areas of the country without electricity service [2]. This is mainly due to the costs of bringing the traditional power system to remote areas with low population density. However, these areas are characterized by own resources that can be redirected to favor the population. There are areas of the country with a very good wind resource, which can be used to generate electricity as an energy solution in specific areas [3, 4, 5]. However, the implementation of this strategy entails many challenges. One of them is related to the projection of wind energy available in the areas. The planning, projection and operation of a wind power plant needs to quantify a priori the available wind resource [6]. This is also important in cases of interconnection with the traditional power grid. However, predicting wind speed is a fairly complex problem due to its fluctuating behaviour and the number of variables that affect it [7, 8]. Most of the strategies currently used to predict wind speed have faults, and even sometimes incur large errors. Among the conventional strategies used to estimate wind speed is the Numerical Weather Prediction (NWP) method [9]. This method consists in an interpolation of values from known data in nearby places. In order to improve the behaviour of these methods a correction strategy is usually used, one of the best results are recurrent neural networks given their natural ability to learn time series [10]. Another conventional method applied uses the Persistence model [11, 12]. In this case the method is able to provide very good short-term values due to its short-term prediction capability. However, when we want to make projections with a ...

This article details the development and evaluation of an autonomous acoustic localization system for robots based on Time Delay Estimation (TDE) and signal intensity, principally aimed at robotic service applications. Time Delay Estimation is carried out through an arrangement of two microphones. The time delay criteria are supported with the signal intensity of a third microphone (coplanar arrangement), which permits discerning precisely the location of the source. This third microphone also feeds a voice identification system, which lets the system respond only to specific voice commands. The prediction algorithm operates by comparing the sensed TDE against the theoretical values of the acoustic propagation model, results that are then weighted according to the signal's mean intensity. A broad set of laboratory experiments is reported on a real prototype that support the system's performance, showing average errors of Azimuth of 18.1 degrees and elevation of 7.6 degrees. Particularly, the analysis conducted for the estimation permits defining the necessary and sufficient conditions to establish in real time a single position in the space of origin, with sufficient precision for autonomous navigation applications ResumenEste artículo detalla el desarrollo y evaluación de un sistema de localización acústico autónomo para robots basado en TDE e intensidad de la señal, principalmente orientado hacia aplicaciones de robótica de servicios. La estimación del tiempo de retardo se realiza mediante un arreglo de dos micrófonos. El criterio del tiempo de retardo se apoya con la intensidad de la señal de un tercer micrófono (arreglo coplanar) que permite discernir de forma precisa la localización de la fuente. Este tercer micrófono alimenta también un sistema de identificación vocal, que permite que el sistema responda sólo a comandos vocales específicos. El algoritmo de predicción opera comparando el TDE sensado frente a los valores teóricos del modelo de propagación acústica, resultados que luego son ponderados de acuerdo a la intensidad promedio de la señal. Se reporta un amplio conjunto de experimentos en laboratorio sobre un prototipo real que soportan el desempeño del sistema, mostrando errores promedio en azimut de 18.1 grados y de elevación de 7.6 grados. En particular, el análisis desarrollado a partir de la estimación permite definir las condiciones necesarias y suficientes para establecer en tiempo real una posición única en el espacio de origen, con suficiente precisión para aplicaciones de navegación autónoma.Palabras clave: Identificación vocal, localización acústica, tiempo estimado de retardo

The development of autonomous motion capability by robotic systems, particularly in dynamic environments, is strongly related to the sensor systems installed in the robot. An important feature of these sensors should be their ability to detect the world in the same way as humans do. This paper focuses on the design of a prototype of a robotic eye, or optical sensor, which has functional characteristics similar to those of the human eye and complies with two Degrees of Freedom (DOF) in its movement. In addition to this, the entire design process of the parts is documented with computer-aided design (CAD) support, the manipulation software, and the programming structure used to control it. The performance tests performed and the analysis of the results obtained demonstrate the total fulfillment of the proposed objectives, which were even surpassed.