Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

For autonomous field robots path planning is needed for automatic operation. In robotics path planning usually means that an algorithm has to find a path from place A to place B in order to avoid collisions with obstacles. In agricultural robotics, the task is usually to cover the whole field, not only going from point A to point B. The shape and size of fields varies a lot, especially in Finland fields are usually small, bounded by other terrain types, e.g. lakes or forests, and shapes are far from orthogonal and convex. A good path planning algorithm can solve the problem for any kind of field. In this paper the path planning problem is divided into two levels. In the higher level the complex shaped field is split into smaller parts and in the lower level the path is planned to smaller parts separately. The higher level splitting algorithm is presented in detail in this paper. The algorithm can handle any field, including obstacles. The algorithm is based on trapetzoidal split, merge and search. The input to the algorithm is the boundary of the field as polygons both interior and exterior, plus the main vehicle parameters. The output of the algorithm are a collection of subfield, which can be driven in parallel driving lines.