Estimación de distancia con sensores ópticos reflexivos usando redes neuronales con funciones de base radial para aplicaciones embebidas 1 Distance Estimation with Reflective Optical Sensors Using Neural Networks with Radial Basis Functions for Embedded

Abstract Reflective optical sensors that measure distances are characterized by the non-linearity of their output. Pro-cessing units in which these are used must allow for such conditions. This paper aims to reduce computational costs regarding storage capacity and processing times by linearizing sen-sor outputs to be used in low-budget embedded systems. Results from two different sensors show that the esteemed exponential curve can be adjusted using neural networks with radial basis functions, with a reduc-tion of over 50% in processing time. Regarding the design of the network, the paper focused on its efficiency in terms of the size of the network and the distribution of centroids, yield-ing important results. The achieved reduction in time and space allows for the use of the system’s resources in other tasks, while it also allows for an increase of the sampling frequency in data acquisition. Keywords Sensor linearization, distance optical sensors, neural networks with radial basis functions.