Robot Training and Navigation through the Deep Q-Learning Algorithm

Abstract

The paper aims to present the results of an assessment of adherence to the Deep Q-learning algorithm, applied to a vehicular navigation robot. The robot's job was to transport parts through an environment, for this purpose, a decision system was built based on the Deep Q-learning algorithm, with the aid of an artificial neural network that received data from the sensors as input and allowed autonomous navigation in an environment. For the experiments, the mobile robot-maintained communication via the network with other robotic components present in the environment through the MQTT protocol.