If the shape of field plot is not rectangular and if it contains obstacles, the coverage path planning problem is hard to solve for a non-omnidirectional machine. Scientists have developed several algorithms to solve this coverage path planning problem, but all of them have pros and cons. If the machines were omnidirectional and turning times were decreased to insignificant, the problem would be quite easy to solve using known robotic path planning methods. In this paper a new algorithm to solve the path planning problem is presented. This algorithm is designed for real-time usage and it solves the problem recursively: the operated area is removed from the field and the algorithm is repeated until the whole field plot is completed. In the development phase of algorithm, a simulator has been utilized. The underlying idea is to calculate the efficiency for all possibilities to make one trip around the field and to select the best one. It is assumed that every new swath is side-by-side to the some previous one or to the boundary of the field plot. However, even if the underlying idea is simple, the search space explodes when the number of corners of the field plot raises and heuristics is needed in order to restrict the number of possibilities without losing optimality. The algorithm is suited to any kind of vehicle, which is described with a few parameters, like working width and minimum turning radius. Preliminary results are very promising and are presented in the paper.
Recursive online path planning for agricultural machines
Rekursive Online-Wegplanung für Landmaschinen
2006
9 Seiten, 7 Bilder, 1 Tabelle, 17 Quellen
Conference paper
English
Coverage path planning algorithms for agricultural field machines
British Library Online Contents | 2009
|Path Planning for Semi-autonomous Agricultural Vehicles
TIBKAT | 2020
|Path Planning for Semi-autonomous Agricultural Vehicles
Springer Verlag | 2020
|