Joseph R. Davidson

Eva Krueger, Marcus Rosette, Joseph R. Davidson

Robotic fruit harvesting often fails to reliably detect whether a fruit has been successfully picked, limiting efficiency and increasing crop damage. This problem is difficult due to compliant fruit and grippers, variable stem attachment, and occlusions in orchard environments. Prior work has explored vision-based perception and multi-sensor learning approaches for pick state estimation. However, minimal sensor sets and phase-dependent sensing strategies for accurate pick and slip detection remain largely unexplored. In this work, we design and evaluate a multimodal sensing suite integrated into a compliant suction-based apple gripper. Our approach is unique because it identifies which sensors are most informative at different phases of the pick, enabling predictive detection of failures before they occur. The contributions of this paper are a phase-dependent evaluation of multimodal sensors and the identification of minimal sensor sets for reliable pick state classification. Experiments in a real apple orchard show that Random Forest and Multilayer Perceptron classifiers detect successful picks and impending failures with over 90% accuracy, and Random Forest predicts pick/slip events within 0.09 s of human-annotated ground truth.

Jostan Brown, Cindy Grimm, Joseph R. Davidson

Accurate localization is an important functional requirement for precision orchard management. However, there are few off-the-shelf commercial solutions available to growers. In this paper, we present SeeTree, a modular, open source embedded system for tree trunk detection and orchard localization that is deployable on any vehicle. Building on our prior work on vision-based in-row localization using particle filters, SeeTree includes several new capabilities. First, it provides capacity for full orchard localization including out-of-row headland turning. Second, it includes the flexibility to integrate either visual, GNSS, or wheel odometry in the motion model. During field experiments in a commercial orchard, the system converged to the correct location 99% of the time over 800 trials, even when starting with large uncertainty in the initial particle locations. When turning out of row, the system correctly tracked 99% of the turns (860 trials representing 43 unique row changes). To help support adoption and future research and development, we make our dataset, design files, and source code freely available to the community.

Alexander You, Cindy Grimm, Abhisesh Silwal et al.

Dormant pruning for fresh market fruit trees is a relatively unexplored application of agricultural robotics for which few end-to-end systems exist. One of the biggest challenges in creating an autonomous pruning system is the need to reconstruct a model of a tree which is accurate and informative enough to be useful for deciding where to cut. One useful structure for modeling a tree is a skeleton: a 1D, lightweight representation of the geometry and the topology of a tree. This skeletonization problem is an important one within the field of computer graphics, and a number of algorithms have been specifically developed for the task of modeling trees. These skeletonization algorithms have largely addressed the problem as a geometric one. In agricultural contexts, however, the parts of the tree have distinct labels, such as the trunk, supporting branches, etc. This labeled structure is important for understanding where to prune. We introduce an algorithm which produces such a labeled skeleton, using the topological and geometric priors associated with these labels to improve our skeletons. We test our skeletonization algorithm on point clouds from 29 upright fruiting offshoot (UFO) trees and demonstrate a median accuracy of 70% with respect to a human-evaluated gold standard. We also make point cloud scans of 82 UFO trees open-source to other researchers. Our work represents a significant first step towards a robust tree modeling framework which can be used in an autonomous pruning system.

Achyut Paudel, Jostan Brown, Priyanka Upadhyaya et al.

Apple(\textit{Malus domestica} Borkh.) trees are deciduous, shedding leaves each year. This process is preceded by a gradual change in leaf color from green to yellow as chlorophyll is degraded prior to abscission. The initiation and rate of this color change are affected by many factors including leaf nitrogen (N) concentration. We predict that leaf color during this transition may be indicative of the nitrogen status of apple trees. This study assesses a machine vision-based system for quantifying the change in leaf color and its correlation with leaf nitrogen content. An image dataset was collected in color and 3D over five weeks in the fall of 2021 and 2023 at a commercial orchard using a ground vehicle-based stereovision sensor. Trees in the foreground were segmented from the point cloud using color and depth thresholding methods. Then, to estimate the proportion of yellow leaves per canopy, the color information of the segmented canopy area was quantified using a custom-defined metric, \textit{yellowness index} (a normalized ratio of yellow to green foliage in the tree) that varied from -1 to +1 (-1 being completely green and +1 being completely yellow). Both K-means-based methods and gradient boosting methods were used to estimate the \textit{yellowness index}. The gradient boosting based method proposed in this study was better than the K-means-based method (both in terms of computational time and accuracy), achieving an $R^2$ of 0.72 in estimating the \textit{yellowness index}. The metric was able to capture the gradual color transition from green to yellow over the study duration. Trees with lower leaf nitrogen showed the color transition to yellow earlier than the trees with higher nitrogen. Keywords: Fruit Tree Nitrogen Management, Machine Vision, Point Cloud Segmentation, Precision Nitrogen Management

Alexander You, Cindy Grimm, Joseph R. Davidson

Machine vision is a critical subsystem for enabling robots to be able to perform a variety of tasks in orchard environments. However, orchards are highly visually complex environments, and computer vision algorithms operating in them must be able to contend with variable lighting conditions and background noise. Past work on enabling deep learning algorithms to operate in these environments has typically required large amounts of hand-labeled data to train a deep neural network or physically controlling the conditions under which the environment is perceived. In this paper, we train a neural network system in simulation only using simulated RGB data and optical flow. This resulting neural network is able to perform foreground segmentation of branches in a busy orchard environment without additional real-world training or using any special setup or equipment beyond a standard camera. Our results show that our system is highly accurate and, when compared to a network using manually labeled RGBD data, achieves significantly more consistent and robust performance across environments that differ from the training set.

Alexander You, Hannah Kolano, Nidhi Parayil et al.

Robotic tree pruning requires highly precise manipulator control in order to accurately align a cutting implement with the desired pruning point at the correct angle. Simultaneously, the robot must avoid applying excessive force to rigid parts of the environment such as trees, support posts, and wires. In this paper, we propose a hybrid control system that uses a learned vision-based controller to initially align the cutter with the desired pruning point, taking in images of the environment and outputting control actions. This controller is trained entirely in simulation, but transfers easily to real trees via a neural network which transforms raw images into a simplified, segmented representation. Once contact is established, the system hands over control to an interaction controller that guides the cutter pivot point to the branch while minimizing interaction forces. With this simple, yet novel, approach we demonstrate an improvement of over 30 percentage points in accuracy over a baseline controller that uses camera depth data.