Analýza překážek pro autonomní řízení

Abstract

This bachelor thesis describes the different detection methods for cones used in the Formula Student Driverless competition. The experimental part is devoted to the use of two methods for localization, the first approach does not use machine learning and the second uses machine learning. The proposed methods are then compared on the basis of detection speed and success rate. An application has also been developed to demonstrate the success of the methods used. The work also includes an evaluation of the results obtained.