@article{williams_modelling_2023,
  title = {Modelling wine grapevines for autonomous robotic cane pruning},
  author = {Williams, Henry and Smith, David and Shahabi, Jalil and Gee, Trevor and Nejati, Mahla and McGuinness, Ben and Black, Kale and Tobias, Jonathan and Jangali, Rahul and Lim, Hin and others},
  journal = {Biosystems Engineering},
  volume = {235},
  pages = {31--49},
  year = {2023},
  publisher = {Elsevier},
  doi = {https://doi.org/10.1016/j.biosystemseng.2023.09.006},
  url = {https://www.sciencedirect.com/science/article/pii/S1537511023001897},
  freepdf = {https://doi.org/10.1016/j.biosystemseng.2023.09.006},
  tldr = {Systems paper concerning the 3D modeling of grape vines, for cane pruning. Uses learned methods for panoptic segmentation and stereo inference. (Detectron 2 for panoptic segmentation, HSMnet for stereo inference.) Uses an over-the-row unit with two UR5 arms to acquire camera data.}
}

Aotearoa (New Zealand) has a strong and growing winegrape industry struggling to access workers to complete skilled, seasonal tasks such as pruning. Maintaining high-producing vines requires training agricultural workers that can make quality cane pruning decisions, which can be difficult when workers are not readily available. A novel vision system for an autonomous cane pruning robot is presented that can assess a vine to make quality pruning decisions like an expert. The vision system is designed to generate an accurate digital 3D model of a vine with skeletonised cane structures to estimate key pruning metrics for each cane. The presented approach has been extensively evaluated in a real-world vineyard as a commercial platform would be expected to operate. The system is demonstrated to perform consistently at extracting dimensionally accurate digital models of the vines. Detailed evaluation of the digital models shows that 51.45% of the canes were modelled entirely, with a further 35.51% only missing a single internode connection. The quantified results demonstrate that the robotic platform can generate dimensionally accurate metrics of the canes for future decision-making and automation of pruning.

Publisher: http://doi.org/https://doi.org/10.1016/j.biosystemseng.2023.09.006
pdf: https://doi.org/10.1016/j.biosystemseng.2023.09.006