With the rapid adoption of automatic guidance systems, automated path planning has great potential to further optimize field operations. Field operations should be done in a manner that minimizes time, travel over field surfaces and is coordinated with specific field operations, machine characteristics and topographical features of arable lands. To reach this goal, intelligent coverage path planning algorithm is key. This dissertation documents our innovative research in optimal field coverage path planning on both 2D and 3D surfaces.

To determine the full coverage pattern of a given 2D planar field by using boustrophedon paths, it is necessary to know whether to and how to decompose a field into sub-regions and how to determine the travel direction within each sub-region. A geometric model was developed to represent this coverage path planning problem, and a path planning algorithm was developed based on this geometric model. The search mechanism of the algorithm was guided by a customized cost function resulting from the analysis of different headland turning types and implemented with a divide-and-conquer strategy. The complexity of the algorithm was analyzed, and methods for reducing the computational time were discussed. Field examples with complexity ranging from a simple convex shape to an irregular polygonal shape that has multiple obstacles within its interior were tested with this algorithm. The results were compared with other reported approaches or farmers' actual driving patterns. These results indicated the proposed algorithm was effective in producing optimal field decomposition and coverage path direction in each sub-region.

In real world, a great proportion of farms have rolling terrains, which have considerable influences to the design of coverage paths. Coverage path planning in 3D space has a great potential to further optimize field operations. To design optimal coverage paths on 3D terrain surfaces, there were five important steps: terrain modeling and representation, topography impacts analysis, terrain decomposition and classification, coverage cost analysis and the development of optimal path searching algorithm. Each of the topics was investigated in this dissertation research. The developed algorithms and methods were successfully implemented in software and tested with practical 3D terrain farm fields with various topographical features. Each field was decomposed into sub-regions based on terrain features. An optimal "seed curve" was found for each sub-region and parallel coverage paths were generated by offsetting the "seed curve" sideways until the whole sub-region was completely covered. Compared with the 2D planning results, the experimental results of 3D coverage path planning showed its superiority in reducing both headland turning cost and soil erosion cost.