Autonomní řízení

Abstract

The aim of this work is to describe methods for autonomous driving of vehicles and to describe and test the models and simulations that are used for training and verification of control quality. The thesis will discuss the theory needed to understand the development and operation of autonomous driving. We will start with more general information, such as the benefits and challenges of autonomous driving, and then explain more technical things, from the distribution of levels of driving automation to the sensors and methods used in autonomous driving to the current state of autonomous driving. In the second part of the paper, we will discuss four different open source simulators that can be used to develop autonomous driving. Then we will explain the concept of reinforced learning and in the last part of the thesis, we will show how to use this technique in the CARLA simulator to create autonomous vehicle capable to navigate through a race track we have created.