Visual Feedback System Supporting Robotic Manipulation of Hemp Plants
This paper presents an agricultural robotics system designed to automate the detection and manipulation of male hemp plants, addressing the challenge of manually removing these to enhance crop quality. The solution uses an industry-standard, inexpensive RGB-D camera as the input data source to deriv...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | Journal of Natural Fibers |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/15440478.2025.2454261 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591616580255744 |
|---|---|
| author | Marek Kraft Bartosz Ptak Mateusz Piechocki Dominik Pieczyński Kamil Młodzikowski Bartłomiej Kulecki Dominik Belter |
| author_facet | Marek Kraft Bartosz Ptak Mateusz Piechocki Dominik Pieczyński Kamil Młodzikowski Bartłomiej Kulecki Dominik Belter |
| author_sort | Marek Kraft |
| collection | DOAJ |
| description | This paper presents an agricultural robotics system designed to automate the detection and manipulation of male hemp plants, addressing the challenge of manually removing these to enhance crop quality. The solution uses an industry-standard, inexpensive RGB-D camera as the input data source to derive control signals controlling the robotic arm and end effector. Input image data processing is performed by a dedicated neural network model trained using a dataset created specifically for the described task to achieve detection by stalk segmentation and postprocessing. The research involved assessing various neural network models, including UNet, DeepLabV3+, and YOLOv8 in various variants, for their capability to detect stalks accurately and swiftly. Fast operation is necessary for effective real-time feedback in robotic grasping tasks. Among tested architectures, the integration of UNet with ResNet50 was found to provide a good trade-off between detection precision and operational speed on edge AI devices. The resulting solution offers good accuracy and significantly outperforms existing methods in terms of processing speed, promising substantial improvements in agricultural robotics by enabling on-line adaptive grasping using low-cost components. The applications can be extended beyond hemp tending to include various other crops, eliminating tedious manual labor. |
| format | Article |
| id | doaj-art-35948c6f33b34b44b723bbd756f1ab77 |
| institution | Kabale University |
| issn | 1544-0478 1544-046X |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Journal of Natural Fibers |
| spelling | doaj-art-35948c6f33b34b44b723bbd756f1ab772025-01-22T08:20:11ZengTaylor & Francis GroupJournal of Natural Fibers1544-04781544-046X2025-12-0122110.1080/15440478.2025.2454261Visual Feedback System Supporting Robotic Manipulation of Hemp PlantsMarek Kraft0Bartosz PtakMateusz Piechocki1Dominik Pieczyński2Kamil Młodzikowski3Bartłomiej Kulecki4Dominik Belter5Institute of Robotics and Machine Intelligence, Poznań University of Technology, Poznań, PolandInstitute of Robotics and Machine Intelligence, Poznań University of Technology, Poznań, PolandInstitute of Robotics and Machine Intelligence, Poznań University of Technology, Poznań, PolandInstitute of Robotics and Machine Intelligence, Poznań University of Technology, Poznań, PolandInstitute of Robotics and Machine Intelligence, Poznań University of Technology, Poznań, PolandInstitute of Robotics and Machine Intelligence, Poznań University of Technology, Poznań, PolandThis paper presents an agricultural robotics system designed to automate the detection and manipulation of male hemp plants, addressing the challenge of manually removing these to enhance crop quality. The solution uses an industry-standard, inexpensive RGB-D camera as the input data source to derive control signals controlling the robotic arm and end effector. Input image data processing is performed by a dedicated neural network model trained using a dataset created specifically for the described task to achieve detection by stalk segmentation and postprocessing. The research involved assessing various neural network models, including UNet, DeepLabV3+, and YOLOv8 in various variants, for their capability to detect stalks accurately and swiftly. Fast operation is necessary for effective real-time feedback in robotic grasping tasks. Among tested architectures, the integration of UNet with ResNet50 was found to provide a good trade-off between detection precision and operational speed on edge AI devices. The resulting solution offers good accuracy and significantly outperforms existing methods in terms of processing speed, promising substantial improvements in agricultural robotics by enabling on-line adaptive grasping using low-cost components. The applications can be extended beyond hemp tending to include various other crops, eliminating tedious manual labor.https://www.tandfonline.com/doi/10.1080/15440478.2025.2454261Hempcomputer visiondeep learningroboticsmanipulation大麻 |
| spellingShingle | Marek Kraft Bartosz Ptak Mateusz Piechocki Dominik Pieczyński Kamil Młodzikowski Bartłomiej Kulecki Dominik Belter Visual Feedback System Supporting Robotic Manipulation of Hemp Plants Journal of Natural Fibers Hemp computer vision deep learning robotics manipulation 大麻 |
| title | Visual Feedback System Supporting Robotic Manipulation of Hemp Plants |
| title_full | Visual Feedback System Supporting Robotic Manipulation of Hemp Plants |
| title_fullStr | Visual Feedback System Supporting Robotic Manipulation of Hemp Plants |
| title_full_unstemmed | Visual Feedback System Supporting Robotic Manipulation of Hemp Plants |
| title_short | Visual Feedback System Supporting Robotic Manipulation of Hemp Plants |
| title_sort | visual feedback system supporting robotic manipulation of hemp plants |
| topic | Hemp computer vision deep learning robotics manipulation 大麻 |
| url | https://www.tandfonline.com/doi/10.1080/15440478.2025.2454261 |
| work_keys_str_mv | AT marekkraft visualfeedbacksystemsupportingroboticmanipulationofhempplants AT bartoszptak visualfeedbacksystemsupportingroboticmanipulationofhempplants AT mateuszpiechocki visualfeedbacksystemsupportingroboticmanipulationofhempplants AT dominikpieczynski visualfeedbacksystemsupportingroboticmanipulationofhempplants AT kamilmłodzikowski visualfeedbacksystemsupportingroboticmanipulationofhempplants AT bartłomiejkulecki visualfeedbacksystemsupportingroboticmanipulationofhempplants AT dominikbelter visualfeedbacksystemsupportingroboticmanipulationofhempplants |