2026
1.
Luke Strohbehn; Cindy Grimm
Branch pruning alignment using small form factor monocular time-of-flight sensors Journal Article
In: Robotics and Autonomous Systems, vol. 203, pp. 105513, 2026, ISSN: 0921-8890.
Abstract | Links | BibTeX | Tags: Agriculture, Dataset, Pruning, Robotics, Time-of-flight
@article{strohbehn_branch_2026,
title = {Branch pruning alignment using small form factor monocular time-of-flight sensors},
author = {Luke Strohbehn and Cindy Grimm},
url = {https://www.sciencedirect.com/science/article/pii/S0921889026001867},
doi = {10.1016/j.robot.2026.105513},
issn = {0921-8890},
year = {2026},
date = {2026-09-01},
urldate = {2026-09-01},
journal = {Robotics and Autonomous Systems},
volume = {203},
pages = {105513},
abstract = {Fruiting trees need annual pruning to maximize yields, and robotic pruning is gaining traction as labor shortages and costs hinder production and scalability. Pruning properly includes accurate cuts, requiring precise alignment and confirmation that a branch has entered the jaws of the pruner. Vision-based open and closed loop controllers can help robotic arms navigate towards target branches, but both methods are unable to receive feedback to confirm alignment with a branch due to the pruning hardware itself blocking the field of view of the camera. We present a physical prototype with two single-beam time-of-flight sensors horizontally aligned with the cut point of the pruner jaws and a set of high-level controllers to localize, align, and approach the branch. We demonstrate that our system localizes and aligns to the branch with high consistency, failing only in one edge case and under adverse lighting conditions. Our method is usable with any 6 dof+ robotic arm. Finally, we provide a dataset that includes all field and laboratory trials.},
keywords = {Agriculture, Dataset, Pruning, Robotics, Time-of-flight},
pubstate = {published},
tppubtype = {article}
}
Fruiting trees need annual pruning to maximize yields, and robotic pruning is gaining traction as labor shortages and costs hinder production and scalability. Pruning properly includes accurate cuts, requiring precise alignment and confirmation that a branch has entered the jaws of the pruner. Vision-based open and closed loop controllers can help robotic arms navigate towards target branches, but both methods are unable to receive feedback to confirm alignment with a branch due to the pruning hardware itself blocking the field of view of the camera. We present a physical prototype with two single-beam time-of-flight sensors horizontally aligned with the cut point of the pruner jaws and a set of high-level controllers to localize, align, and approach the branch. We demonstrate that our system localizes and aligns to the branch with high consistency, failing only in one edge case and under adverse lighting conditions. Our method is usable with any 6 dof+ robotic arm. Finally, we provide a dataset that includes all field and laboratory trials.
2024
2.
Ranjan Sapkota; Dawood Ahmed; Manoj Karkee
Comparing YOLOv8 and Mask R-CNN for instance segmentation in complex orchard environments Journal Article
In: Artificial Intelligence in Agriculture, vol. 13, pp. 84–99, 2024, ISSN: 2589-7217.
Abstract | Links | BibTeX | Tags: Artificial intelligence, Automation, Deep learning, Machine Learning, Machine vision, Mask R-CNN, Robotics, YOLOv8
@article{sapkota_comparing_2024,
title = {Comparing YOLOv8 and Mask R-CNN for instance segmentation in complex orchard environments},
author = {Ranjan Sapkota and Dawood Ahmed and Manoj Karkee},
url = {https://www.sciencedirect.com/science/article/pii/S258972172400028X},
doi = {10.1016/j.aiia.2024.07.001},
issn = {2589-7217},
year = {2024},
date = {2024-09-01},
urldate = {2024-09-01},
journal = {Artificial Intelligence in Agriculture},
volume = {13},
pages = {84\textendash99},
abstract = {Instance segmentation, an important image processing operation for automation in agriculture, is used to precisely delineate individual objects of interest within images, which provides foundational information for various automated or robotic tasks such as selective harvesting and precision pruning. This study compares the one-stage YOLOv8 and the two-stage Mask R-CNN machine learning models for instance segmentation under varying orchard conditions across two datasets. Dataset 1, collected in dormant season, includes images of dormant apple trees, which were used to train multi-object segmentation models delineating tree branches and trunks. Dataset 2, collected in the early growing season, includes images of apple tree canopies with green foliage and immature (green) apples (also called fruitlet), which were used to train single-object segmentation models delineating only immature green apples. The results showed that YOLOv8 performed better than Mask R-CNN, achieving good precision and near-perfect recall across both datasets at a confidence threshold of 0.5. Specifically, for Dataset 1, YOLOv8 achieved a precision of 0.90 and a recall of 0.95 for all classes. In comparison, Mask R-CNN demonstrated a precision of 0.81 and a recall of 0.81 for the same dataset. With Dataset 2, YOLOv8 achieved a precision of 0.93 and a recall of 0.97. Mask R-CNN, in this single-class scenario, achieved a precision of 0.85 and a recall of 0.88. Additionally, the inference times for YOLOv8 were 10.9 ms for multi-class segmentation (Dataset 1) and 7.8 ms for single-class segmentation (Dataset 2), compared to 15.6 ms and 12.8 ms achieved by Mask R-CNN\'s, respectively. These findings show YOLOv8\'s superior accuracy and efficiency in machine learning applications compared to two-stage models, specifically Mask-R-CNN, which suggests its suitability in developing smart and automated orchard operations, particularly when real-time applications are necessary in such cases as robotic harvesting and robotic immature green fruit thinning.},
keywords = {Artificial intelligence, Automation, Deep learning, Machine Learning, Machine vision, Mask R-CNN, Robotics, YOLOv8},
pubstate = {published},
tppubtype = {article}
}
Instance segmentation, an important image processing operation for automation in agriculture, is used to precisely delineate individual objects of interest within images, which provides foundational information for various automated or robotic tasks such as selective harvesting and precision pruning. This study compares the one-stage YOLOv8 and the two-stage Mask R-CNN machine learning models for instance segmentation under varying orchard conditions across two datasets. Dataset 1, collected in dormant season, includes images of dormant apple trees, which were used to train multi-object segmentation models delineating tree branches and trunks. Dataset 2, collected in the early growing season, includes images of apple tree canopies with green foliage and immature (green) apples (also called fruitlet), which were used to train single-object segmentation models delineating only immature green apples. The results showed that YOLOv8 performed better than Mask R-CNN, achieving good precision and near-perfect recall across both datasets at a confidence threshold of 0.5. Specifically, for Dataset 1, YOLOv8 achieved a precision of 0.90 and a recall of 0.95 for all classes. In comparison, Mask R-CNN demonstrated a precision of 0.81 and a recall of 0.81 for the same dataset. With Dataset 2, YOLOv8 achieved a precision of 0.93 and a recall of 0.97. Mask R-CNN, in this single-class scenario, achieved a precision of 0.85 and a recall of 0.88. Additionally, the inference times for YOLOv8 were 10.9 ms for multi-class segmentation (Dataset 1) and 7.8 ms for single-class segmentation (Dataset 2), compared to 15.6 ms and 12.8 ms achieved by Mask R-CNN's, respectively. These findings show YOLOv8's superior accuracy and efficiency in machine learning applications compared to two-stage models, specifically Mask-R-CNN, which suggests its suitability in developing smart and automated orchard operations, particularly when real-time applications are necessary in such cases as robotic harvesting and robotic immature green fruit thinning.
