Towards a Semiautonomous Young Spruce Forest Late Cleaning

Cleaning a seedling spruce stand is an important silvicultural task required to help the young spruce trees thrive. It is usually manual work with a clearing saw. Mechanized solutions have been proposed, but they have not worked out well, since the driver has challenges in seeing the seedling trees that should be left growing. Instead, we demonstrate that a semiautonomous forest machine could do the cleaning operation using a suitable map of the environment. We propose using a low-cost unmanned aerial vehicle (UAV) to map the area beforehand, and a real-time perception system onboard the forest machine performing the semiautonomous late cleaning of a seedling spruce stand with the help of a driver using a dedicated human–machine interface (HMI). In the proposed solution, overlapping color images are collected by a UAV to build a map that integrates both color and depth information. This map is used to detect the young spruce trees, among other species. We also propose a graph-based point-cloud matching method, which can precisely locate the forest machine on the map using forest machine-mounted sensors. An HMI is developed to improve the situational awareness of the operator in the forest machine cabin during the cleaning process. The proposed integrated solution has been demonstrated in a real seedling spruce forest.