This dissertation arises from a major project that consists on developing a domestic service robot, named CHARMIE (Collaborative Home Assistant Robot by Minho Industrial Electronics), to cooperate and help on domestic tasks, like grabbing objects. In general, the project aims to implement artificial intelligence in the whole robot.

The main contribution of this dissertation, on the robot, is the development of the vision system, with artificial intelligence, to classify and detect, in real time, the objects represented on the environment that the robot is placed.

This dissertation is within two broad areas that revolutionized the robotics industry, namely the artificial vision and artificial intelligence. Knowing that most of the existent information is presented on the vision and with the evolution of robotics, there was a need to introduce on robots the capacity to acquire and process this kind of information, so the artificial vision algorithms allowed them to acquire information of the environment, namely patterns, objects, formats, and many more, through vision sensors (cameras). Although implementing artificial vision can be very complex if it is pretended to classify images, due to image complexity. 

The introduction of artificial intelligence or neural networks brought the capability of implementing systems that can learn from provided data, without the need of hard coding it, reducing slightly the complexity and the time consumption of implementing complex problems, like artificial vision. For artificial vision problems, like this project, there is a neural network that is specialized in learning from 3dimensional vectors, namely images, named Convolutional neural network (CNN). This network uses image data to learn patterns, edges, formats, and many more, that represents a certain object.

This type of network will be used to classify and detect the objects presented in the image provided by the camera, and will be implemented with the Tensorflow library. All the image acquisition from the camera will be performed by the OpenCv library.

For this dissertation, in the end, is intended to have an algorithm that can detect and classify, that is, that can get the name of the object and its world position with and high precision rate, from images provided by the camera in real time.