Coverage path planning for autonomous surveying of plant species using unmanned aerial vehicles (UAVs)

Department of Electrical & Electronic Engineering, University of Stellenbosch, South Africa

^* Corresponding author: altus.cilliers@eilandia.org.za

Abstract

This paper presents the development of a system for autonomous surveying of plant species using one or more unmanned aerial vehicles. A novel coverage path planning algorithm was developed to search disconnected search areas and generate Global Positioning System waypoints that specify the paths that the unmanned aerial vehicle should follow to cover the environment. The system was tested in simulation and with practical flight tests using a physical UAV at a real-world location. Both the simulation results and the practical flight test results showed that the UAV can accurately execute the planned coverage paths. The flight tests proved that the system can survey disconnected vegetation areas, navigate complex environments containing obstacles and no-fly zones, and perform consecutive path generation to enable refuelling or the use of multiple UAVs. The results also show that our proposed system covers the required areas of vegetation more efficiently (travelling shorter distances) than the standard lawnmower patterns provided by commercial systems.