Navigation Algorithms for Unmanned Ground Vehicles in Precision Agriculture Applications

Robotics for agriculture and forestry can be considered a very recent application of one of the most ancient and important sectors, where the latest and most advanced innovations have been brought. Over the years, thanks to continous improvement in mechanization and automation, crop output has extremely increased, enabling a large growth in population and enhancing the quality of life around the world. Better living conditions, as a consequence, are leading to a higher demand for agriculture and forestry output. Precision agriculture defined as the correct management of crops for increasing its productivity and maximizing harvest, is considered the answer to this issue. As a matter of fact, thanks to the development of portable sensors and more accessible aerial platforms, the collection of data is allowing a vast development in this field. This thesis adresses in general robotics for agriculture in the form of a solution to be applied in order to improve robot mobility, in particular automated path planning in vineyards, by proposing a method to classify different parcels which make up the vineyard and to assign a precise task to the terrestrial unmanned robot. The first part discusses how to generate a canopy segmentation from the mask obtained by processing images taken from unmanned aerial vehicles (UAVs). The developed algorithm is based on multiple steps: a first clustering of the mask is performed to identify each vine row, then a Least Squares regression is applied in order to be used in the following clustering step to detect each parcel which composes the map. Finally a recombination of the vine rows is carried out for the purpose of avoiding the problem of missing plants and defective rows. The second part focuses its attention on the development of a path planning algorithm that can be integrated in every environment: it combines the A* search algorithm and path smoothing by exploiting the Gradient Descent algorithm. The last part adresses the issue of applying the path planning in order to cover the desired parcel with the cooperation of both path planning and clustering.