En el presente artículo se expone el entrenamiento de una Red Neuronal Convolucional (RNC) para discriminación de herramientas de uso común en tareas de mecánica, electricidad, carpintería y similares. Para el caso, se toman como objetivos de entrenamiento pinzas, destornilladores, tijeras y alicates, los cuales puedan ser identificados por la red, y permite dotarle a un brazo robótico la facultad de identificar una herramienta deseada - de entre las anteriores - para su posible entrega a un usuario. La arquitectura neuro convolucional empleada para la red presenta un porcentaje de acierto del 96% en la identificación de las herramientas entrenadas.
This paper presents training of novel hybrid network based on three deep convolutional neural network architectures applied to object recognition, based on the depth information supplied for a RGBD camera. For this case, the depth information allows to set the dataset of training images of each network, its architecture and its characteristics, generating a dynamic recognition application by variation of the image capture point, whose final layer is determined by a diffuse inference system. The general architecture designed allows an efficient object recognition applicable to robotic mobile agents, whose perspective of the object varies when approaching or moving away from them, showing an overall performance of 90.19%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.