Autonomous Robot Navigation with Signaling Based on Objects Detection Techniques and Deep Learning Networks

The autonomous navigation of robots is one of the main problems of robots due to its complexity and level of dynamics, as it depends on environmental conditions and the environment. Deep learning has become an interesting line of research in the area of robotics and computer vision. In this work, we have proposed the application of neural networks with deep learning applying the Single Shot Detector algorithm that provides robustness in speed and precision that mainly allows the detection of persons, objects through the use of the neural network trained for autonomous navigation of robots. The objective of this research is to achieve that a robot is able to make a route in an unknown environment and that by means of the parameterization of a signal at the moment of the detection of an object to have a visible mark in the map, allowing this way the acquisition of information that will help in the future explorations of the robot in the same environment.