A Systematic Analysis of Scan Matching Techniques for Machinery Localization in Dense Orchards

In the last years, different methods have been studied for determining machinery position within a grove, as an alternative for complementing GNSS (global navigation satellite system) information in cases where GNSS signal is occluded. Such situation can be observed when agricultural machinery travels under dense foliage or at the slopes of mountains. Scan matching techniques arise as a possible solution for localizing the machinery, complementing the absence of the GNSS signal when necessary. However, since key points are difficult to obtain in heterogeneous, unstructured and non-rigid environments (such as orchard plants), the performance of scan matching techniques often decreases in agricultural environments. This work proposes a methodology to enhance the performance of scan matching techniques in agricultural orchards by splitting the point clouds into different horizontal and vertical segments, along with an analysis of the optimum overlap between registered frames. We validate the analysis with an extensive experimentation in a Fuji apple orchard. The results show that the cumulative localization error in scan matching techniques can be notoriously decreased with selective parts of the orchard. The experimentation performed herein suggests that the proposed methodology can complement the GNSS navigation in a middle-long path.