Algebraic path tracking to aid the manual harvesting of olives using an automated service unit

Abstract

Service units used in precision agriculture are able to improve processes such as harvesting, sowing, agrochemical application, and manure spreading. This two-part work presents, a path tracking controller based on an algebraic approach for an articulated service unit, suitable for embedded applications, and its implementation to a hierarchical navigation strategy to aid a manual harvesting process. The path tracking controller approach can be scaled to several trailers attached to the service unit. For harvesting, the service unit drives within an olive grove environment following the previously developed path and a trailer is used as a mobile hopper where olives, collected by human labour, are deposited. The service unit also registers and georeferences the amount of olives (mass) collected for the subsequent creation of yield maps. The developed navigation strategy improved the time associated with harvesting olives by approximately 42-45%. The mathematical formulation of the problem, some real time experimental results, the creation of a yield map and the statistical analysis that validated the method are included.

Agricultural service unit motion planning under harvesting scheduling and terrain constraints

“…, where a system of cameras and illumination mounted on a vehicle automatically predicts yield accurately. Then, using GNSS information of the grove, i.e., the position of all harvesting points in the farm, the expected crop production per tree, and the number of field workers assigned to each row as well as the starting harvesting time, the system generates a harvesting schedule as presented in Ref. . Such a schedule only consists of harvesting points and the expected time when the bin will be full. With the previous information, the motion planner system plans the paths, taking into account the terramechanics and environmental constraints. Once the path and its corresponding schedule are generated, the automated service unit starts collecting the beans.…”

“…Yield estimation traditionally requires • Then, using GNSS information of the grove, i.e., the position of all harvesting points in the farm, the expected crop production per tree, and the number of field workers assigned to each row as well as the starting harvesting time, the system generates a harvesting schedule as presented in Ref. 23. Such a schedule only consists of harvesting points and the expected time when the bin will be full.…”

“…The contribution of this work can be summarized in the development of an integrated harvesting and motion‐planning strategy that employs information on plant yields, worker harvesting rates, and terrain traversability, and it follows the results previously published by the authors in Refs. and . The harvesting locations in the planned route are prioritized by formulating the harvest task as a traveling salesman problem (TSP), while the motion planning between harvesting locations is solved using the RRT* algorithm, but including the terrain's traversability unlike the existing methods, which only consider kinodynamic constraints and seek to ensure the path's safety.…”

Forward tracking of complex trajectories with non-Standard N-Trailers of non-minimum-phase kinematics avoiding a jackknife effect

“…For instance, positioning of the urban articulated buses is often prohibited by law in a backward manner when manoeuvering on urban streets and in vicinity of bus stations (Tan & Huang, 2014). Agricultural tasks with tractor-trailers are performed mostly in the forward motion strategy (Auat Cheein et al, 2016;Backman, Oksanen, & Visala, 2012;Karkee & Steward, 2010;Werner, Kormann, & Mueller, 2013). Finally, some loading/unloading tasks require positioning of the trailer(s) when a vehicle is moving forward.…”

Auto-steering based precise coordination method for in-field multi-operation of farm machinery

“…Most of the researches focus on the inter-field coordination algorithm to improve machinery scheduling effectiveness [19][20][21][22] . Master-slave robot system and leader-follower system are the classical in-field coordination cases [23][24][25][26][27] . For the in-field level of farm operation, it can be subdivided into three lower levels, i.e., multi-operation, multi-machinery, and multi-factor.…”