The recently completed AGROS validation trial is taking researchers closer to the realization of a fully autonomous greenhouse. The trial used an Artificial Intelligence algorithm based on Reinforcement Learning to control the climate in a semi-commercial greenhouse, resulting in a productive cucumber crop. The successful deployment of a Digital Twin was also achieved, which controlled greenhouse climate, irrigation strategy, and crop management. The objective of the trial was to reach the highest possible net profit, which was determined by the balance between variable costs and benefits. The last cucumbers were harvested on May 11th.
