Navigeerimine välistingimustes mudelautoga

Abstract

The development of autonomous vehicles is primarily focused on cars operating on roads. The goal of this bachelor’s thesis was to develop a vehicle to navigate in off-road environments. The Donkey Car S1 platform was used as a base, to which custom-designed and 3D-printed frames were added to mount a GNSS device and a LiDAR sensor. Necessary functionality was developed to the Donkey Car project to enable waypoint-based navigation. To evaluate the self-driving capability, various tests were conducted both on asphalt and in a park environment. Navigation between waypoints was successful, even when the waypoint was behind the car. Both GNSS and LiDAR worked as expected, with the GNSS evaluated to the accuracy of 2 cm and LiDAR achieving a measurement accuracy within 5 cm. However, obstacle avoidance proved to be ineffective and the possible reasons for this were analyzed. It was also found that the frame of the chosen platform was not suitable for off-road driving. This thesis concludes with recommendations for further development and suggestions for avoiding similar issues in future implementations.