Crop-harvesting operations are typically carried out with combine harvesters. The harvested product istransferred to one or more tractors every time the combine harvester’s storage capacity is reached. Theefficiency of the process can be significantly improved by computing optimal routes and interactionsfor the harvest vehicles in the field. Furthermore, an automated method for generating itineraries forthe harvest vehicles facilitates the planning for autonomous agricultural vehicles. The infield logisticsproblem is formulated as an integer linear programming vehicle routing problem with additional turnpenalty constraints, but, because of the high number of decision variables, it is not possible to solvecases of realistic field size. The solution time of the infield logistics problem is considerably reduced byreformulating it as a modified minimum-cost network flowproblem. This specific structure allows the exactsolution of intermediate-size planning problems in a much shorter time period. The result of solving theinfield logistics problem with the proposed modelling approaches is a set of itineraries (‘tours’), coveringthe entire field. Each ‘tour’ is characterized by the combine harvester’s start and end points and the positionswhere the combine harvester needs to be unloaded. The planning models minimize non-productivity (i.e. thetime when a combine harvester travels in a field without harvesting). The results indicate that coordinationbetween combine harvesters and tractors is also improved.
展开▼
