In the present work it is proposed to identify if a person is distracted or not, when he is driving a vehicle. This can be achieved by classifying images of drivers to determine if they are available or distracted using convolutional neural networks (CNN) and tools to improve the algorithm, which are Learning Transfer and Characteristics Engineering. Kaggle competition images are used to perform the training, in which you can obtain more results and obtain more results. Later the red extractor of characteristics VGG16 was used, which is a pre-trained model, from which it is lowered in its last layers to reduce the overfit and adapt it to our algorithm. The results obtained in the classifier gave us a training efficiency and validation of 99.30% and 99.46% respectively.

In the present work it is proposed to identify if a person is distracted or not, when he is driving a vehicle. This can be achieved by classifying images of drivers to determine if they are available or distracted using convolutional neural networks (CNN) and tools to improve the algorithm, which are Learning Transfer and Characteristics Engineering. Kaggle competition images are used to perform the training, in which you can obtain more results and obtain more results. Later the red extractor of characteristics VGG16 was used, which is a pre-trained model, from which it is lowered in its last layers to reduce the overfit and adapt it to our algorithm. The results obtained in the classifier gave us a training efficiency and validation of 99.30% and 99.46% respectively.

The present project is about the implementation of an autonomous mobile robot designed for logistic tasks in different areas of a company, university, etc. This robot is able to navigate autonomously in real environments, you just need to specify the initial position, the grip map of the world and the target locations, and the robot will generate automatically the optimal path to reach the target positions, and then will follow this path while avoiding obstacles such as persons, trash bins, etc. These characteristics allow that our robot can be used in logistic tasks where the robot needs to carry loads from one place to another. In this project we developed two robot models, the first one called R2d2‐R1 can carry loads of up to 3kg, and the second one called can carry loads of up to 25Kg. The algorithms implemented in this project represent the state‐of‐the‐car methods and its p...

El presente proyecto consistió en la implementación de un robot móvil autónomo capaz de facilitar el flujo de documentos entre las diferentes áreas de una empresa, universidad, etc. Este robot es capaz de navegar de manera completamente autónoma en ambientes reales tal como los ambientes del CTIC, FIM, FIEE, etc. Tan solo especificando el punto inicial, el mapa del ambiente de navegación, y el punto deseado, este robot es capaz de generar el camino óptimo para llegar a dicha meta, y luego seguir este camino con la capacidad de evitar obstáculos si estos se presentan. Dadas estas características, este robot se puede usar en aplicaciones logísticas en donde el robot debe llevar paquetes, cargas, etc., a algún punto especificado por el usuario. En el proyecto se tienen dos modelos, el primer robot llamado R2D2‐R1 puede llevar cargas de hasta 3kg, y el segundo robot llamado R2D...

The present project is about the implementation of an autonomous mobile robot designed for logistic tasks in different areas of a company, university, etc. This robot is able to navigate autonomously in real environments, you just need to specify the initial position, the grip map of the world and the target locations, and the robot will generate automatically the optimal path to reach the target positions, and then will follow this path while avoiding obstacles such as persons, trash bins, etc. These characteristics allow that our robot can be used in logistic tasks where the robot needs to carry loads from one place to another. In this project we developed two robot models, the first one called R2d2‐R1 can carry loads of up to 3kg, and the second one called can carry loads of up to 25Kg. The algorithms implemented in this project represent the state‐of‐the‐car methods and its p...