3D Skeletonization of Complex Grapevines for Robotic Pruning

TL;DR

This paper develops a 3D skeletonization method for complex grapevines to improve robotic pruning, enabling better perception and pruning weight prediction in dense, realistic vineyard conditions.

Contribution

It introduces an advanced 3D skeletonization pipeline that outperforms baseline methods and enhances pruning weight prediction accuracy for complex grapevine structures.

Findings

Lower reprojection error compared to baseline algorithms

Higher connectivity in skeletal models

Improved pruning weight prediction accuracy

Abstract

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.