Path Planning for Spot Spraying with UAVs Combining TSP and Area Coverages

TL;DR

This work tackles minimizing UAV flight length for spot spraying inside a defined field while strictly avoiding obstacles and keeping within the bounding contour. It proposes a two-phase approach that decouples a TSP tour across patches from per-patch area-coverage paths, with headland paths to mitigate coverage gaps. Among the tested strategies, a deterministic TSP-refinement heuristic (H$_4$) consistently performs best, and an Optimised area-coverage method yields meaningful total-length savings over the Classic approach. A surprising result is that area-coverage pathlength can account for a large share of the total pathlength (up to ~83%), underscoring the importance of efficient patch-area coverage in UAV spot spraying. The framework aims to enable scalable, efficient, and safe UAV planning for agricultural spraying, with future work on multi-UAV coordination and 3D trajectory considerations.

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.

Figures (14)

• Figure 1: High-level algorithm of this paper as a block diagram. A variety of heuristics are compared for Subproblem 1. Two main approaches are compared for Subproblem 2. Data input comprises one field contour, multiple patches areas contours, potential obstacles areas contours coordinates as well as a working width of the UAV.
• Figure 2: Problem visualisation: Given a set of patches or areas that are meant to be serviced within a field contour calculate a minimal length path plan for an UAV that additionally avoids any obstacles areas (red) and does not leave the field contour area. Three experiment setups of different complexity are displayed.
• Figure 3: Illustration of patch entry and exit point, and an exemplary patch area coverage path plan including a headland path locally in parallel to the patch contour (gray).
• Figure 4: Illustration of a TSP-segment covering three small patches (gray) that do not require an area coverage path plan for a given larger UAV operating width.
• Figure 5: Illustration of a Boustrophedon path. Characteristic is the zigzag-like path and the absence of a headland path.

Theorems & Definitions (1)

• Proposition 1