🤖 AI Summary
This paper addresses the shortest obstacle-avoiding path planning problem for unmanned aerial vehicles (UAVs) covering multiple irregular weed patches within boundary-constrained farmland, under precision spot-spraying requirements. We propose a novel paradigm integrating Traveling Salesman Problem (TSP)-based path optimization with region coverage planning: abandoning conventional back-and-forth trajectories prone to missed spraying, we model headland-based paths and develop a TSP heuristic framework comprising two initialization strategies and four refinement strategies. We first reveal that intra-patch coverage path length dominates total flight distance—a finding that validates the necessity of joint optimization. Extensive experiments on three real-world farmlands (containing 15, 19, and 197 patches) demonstrate significant reductions in total flight distance, identify the optimal refinement strategy, and quantitatively confirm that coverage-path contribution substantially exceeds conventional assumptions.
📝 Abstract
This paper addresses the following task: given a set of patches or areas of varying sizes that are meant to be serviced within a bounding contour calculate a minimal length path plan for an unmanned aerial vehicle (UAV) such that the path additionally avoids given obstacles areas and does never leave the bounding contour. The application in mind is agricultural spot spraying, where the bounding contour represents the field contour and multiple patches represent multiple weed areas meant to be sprayed. Obstacle areas are ponds or tree islands. The proposed method combines a heuristic solution to a traveling salesman problem (TSP) with optimised area coverage path planning. Two TSP-initialisation and 4 TSP-refinement heuristics as well as two area coverage path planning methods are evaluated on three real-world experiments with three obstacle areas and 15, 19 and 197 patches, respectively. The unsuitability of a Boustrophedon-path for area coverage gap avoidance is discussed and inclusion of a headland path for area coverage is motivated. Two main findings are (i) the particular suitability of one TSP-refinement heuristic, and (ii) the unexpected high contribution of patches areas coverage pathlengths on total pathlength, highlighting the importance of optimised area coverage path planning for spot spraying.