Bumblebee: A Path Towards Fully Autonomous Robotic Vine Pruning

TL;DR

This paper introduces a fully autonomous robotic system for grapevine pruning that aims to improve consistency, reduce labor dependency, and lower costs in vineyard management through advanced perception and manipulation technologies.

Contribution

The paper presents a novel autonomous robot with advanced perception and manipulation capabilities specifically designed for grapevine pruning, demonstrating effective field performance.

Findings

Robot prunes vines in 213 seconds per vine with 87% accuracy.

Autonomous pruning reduces variability compared to mechanical methods.

System shows promise for commercial vineyard deployment.

Abstract

Dormant season grapevine pruning requires skilled seasonal workers during the winter season which are becoming less available. As workers hasten to prune more vines in less time amid to the short-term seasonal hiring culture and low wages, vines are often pruned inconsistently leading to imbalanced grapevines. In addition to this, currently existing mechanical methods cannot selectively prune grapevines and manual follow-up operations are often required that further increase production cost. In this paper, we present the design and field evaluation of a rugged, and fully autonomous robot for end-to-end pruning of dormant season grapevines. The proposed design incorporates novel camera systems, a kinematically redundant manipulator, a ground robot, and novel algorithms in the perception system. The presented research prototype robot system was able to spur prune a row of vines from both sides completely in 213 sec/vine with a total pruning accuracy of 87%. Initial field tests of the autonomous system in a commercial vineyard have shown significant variability reduction in dormant season pruning when compared to mechanical pre-pruning trials. The design approach, system components, lessons learned, future enhancements as well as a brief economic analysis are described in the manuscript.