Online Coverage Planning for an Autonomous Weed Mowing Robot with Curvature Constraints

The area used for grazing cattle takes up about one-third of the land in United States. These areas can be highly rugged. Yet, they need to be maintained to prevent weeds from taking over the nutritious grassland. In this paper, we present the design of Cowbot, an autonomous weed mowing robot for cow pastures. Cowbot is designed to operate in rugged environments and provides a cost-effective method for weed control in cow pastures. Path planning for the Cowbot is challenging since weed distribution on pastures is unknown. Given a limited field of view, online planning is necessary to detect weeds and plan paths to mow them. We study the general online coverage planning problem for an autonomous mower with curvature and field of view constraints. We develop two algorithms that are able to utilize new information on weed detection to optimize path length and ensure coverage. We deploy our algorithms on the Cowbot and perform field experiments to validate the suitability of our methods for real-time path planning. We also perform extensive simulation experiments which show that our algorithms result in up to 60 % reduction in path length as compared to boustrophedon and random-search based coverage paths.