Agriculture

Agriculture tech has become a highly digitized, high-technology branch involving powerful and expensive machinery. The need for effective and efficient processes has increased due to economic and ecological constraints. In that situation, automation, optimization and planning methods are natural choices, and they can build on existing high levels of digitization at modern farms and contractors.

One problem class is campaign planning for agricultural processes. It consists of various coordination and optimization problems on several levels of detail. Campaign planning is needed in harvesting processes, which involve harvesters, overloading and transport vehicles, and possibly other resources and agents, depending on the type of crop; it is also of help in spraying chemicals or manure.

The harvesting processes for the various crops, e.g., silage maize, wheat, forage, or sugar beet, vary due to different general requirements and machinery. A particularly complex process is silage maize harvesting, which is the focus of this use-case. The chopping, transport, and compaction of the crop in the silo must be coordinated so that the machines are used to full capacity and downtimes are avoided. Efficiency is important here, as there are requirements in terms of time, economy, and sustainability: When the crop is ripe there is only a limited time window to harvest it. Here, weather conditions can lead to further restrictions or deadlines. Efficiency is also important from an economic point of view, as the machines and labour are expensive and limited. Finally, sustainability aspects such as a reduction in fuel consumption or soil compaction risks could also play a role.

In this use case AIPlan4EU aims to use AI planning techniques in order to plan and optimize the overall silage maize harvest campaigns. This also involves monitoring and adapting plans during the harvest in order to react to changed conditions or deviations from the original plan.