3D Skeletonization of Complex Grapevines for Robotic Pruning
This work addresses the challenge of robotic perception for pruning in commercial vineyards, which is incremental as it builds on existing plant skeletonization methods.
The paper tackled the problem of robotic pruning in complex grapevine structures by extending plant skeletonization techniques, resulting in skeletal models with lower reprojection error and higher connectivity, and enabling improved prediction accuracy for pruning weight in dense vines.
Robotic pruning of dormant grapevines is an area of active research in order to promote vine balance and grape quality, but so far robotic efforts have largely focused on planar, simplified vines not representative of commercial vineyards. This paper aims to advance the robotic perception capabilities necessary for pruning in denser and more complex vine structures by extending plant skeletonization techniques. The proposed pipeline generates skeletal grapevine models that have lower reprojection error and higher connectivity than baseline algorithms. We also show how 3D and skeletal information enables prediction accuracy of pruning weight for dense vines surpassing prior work, where pruning weight is an important vine metric influencing pruning site selection.