A reinforcement learning‐based approach for modeling and coverage of an unknown field using a team of autonomous ground vehicles

Precision maps are useful in agricultural farm management for providing farmers (and field researchers) with locational information. Having an environmental model that includes geo-referenced data would facilitate the deployment of multi-robot systems, that has emerged in precision agriculture. It further allows developing automated techniques and tools for map reconstruction and field coverage for farming purposes. In this study, a reinforcement learning-based method (and in particular dyna-Q+) is presented for a team of unmanned ground vehicles (UGVs) to cooperatively learn an unknown dynamic field (and in particular, an agricultural field). The problem we address here is to deploy UGVs to map plant rows, find obstacles, whose locations are not known a priori, and define regions of interest in the field (e.g., areas with high water stress). Once an environment model is built, the UGVs are then distributed to provide full coverage of plants and update the reconstructed map simultaneously. Simulation results are finally presented to demonstrate that the proposed method for simultaneous learning and planning can successfully learn a model of the field and monitor the coverage area.