Edge-deployable greenhouse tomato cluster harvesting robot integrating YOLOv8n-BiFPN-WIoU and ROS-based autonomous control
4 affiliations
- 1School of Mechanical Engineering, Shandong Huayu University of Technology , ,
- 2School of Advanced Manufacturing, Sun Yat-sen University , ,
- 3Shandong Shansu Robot Technology Co., Ltd. , ,
- 4School of Materials and Chemical Engineering, Hunan Institute of Technology , ,
Abstract
Objective: To develop an edge-deployable greenhouse tomato cluster harvesting robot capable of accurate fruit detection, three-dimensional localization, autonomous navigation, and robotic harvesting under complex greenhouse conditions. The objective was to improve detection performance under fruit occlusion and variable illumination while maintaining real-time inference and stable robotic operation on embedded computing hardware.
Methods: A lightweight YOLOv8n-based tomato detection model, termed YOLOv8n-BiFPN-WIoU, was developed by incorporating a bidirectional feature pyramid network and Wise-IoU loss to improve multiscale feature fusion and localization accuracy. An RGB-D vision system based on the Intel RealSense D435 was used for three-dimensional fruit localization. The robotic system integrated a rail-guided mobile platform, a six-axis manipulator, a dual-claw harvesting end-effector, and a ROS-based distributed control architecture. The vision model was optimized and deployed on an NVIDIA Jetson Nano using ONNX and TensorRT. Robot kinematics, hand-eye transformation, trajectory planning, and autonomous harvesting procedures were integrated to enable station-to-station operation and fruit harvesting.
Results: The proposed YOLOv8n-BiFPN-WIoU model achieved a precision of 88.534%, recall of 89.377%, F1-score of 88.954%, [email protected] of 92.338%, and [email protected]:0.95 of 71.368%. Compared with the baseline YOLOv8n model, these metrics improved by 2.143, 2.779, 2.460, 4.587, and 5.675 percentage points, respectively. The proposed model increased the parameter count from 3.2 million to 3.6 million and computational complexity from 19.6 to 22.4 GFLOPs. After ONNX and TensorRT optimization, the model achieved an inference speed of 21.1 frames per second at an input resolution of 640 × 640 with batch size 1 on the Jetson Nano. The robotic system achieved a mean positioning error of 3.70 ± 0.32 mm across five representative targets, demonstrating the feasibility of accurate visual localization and robotic positioning for greenhouse tomato harvesting.
Conclusion: The proposed edge-deployable greenhouse tomato cluster harvesting robot integrates lightweight deep learning, RGB-D three-dimensional localization, ROS-based autonomous control, rail-guided mobile operation, and robotic harvesting into a unified system. The YOLOv8n-BiFPN-WIoU model improved tomato detection performance while maintaining real-time inference on embedded hardware, and the integrated vision and manipulation system demonstrated accurate positioning suitable for autonomous harvesting. The results indicate that the proposed architecture provides a practical foundation for intelligent greenhouse tomato harvesting under complex visual and operational conditions.
Related
- Robotic Fruit Harvesting Systems: Integration of Perception, Manipulation, and Detachment for Autonomous Harvesting
- A spatially deployable iron redox rheostat tunes root growth under nutritional stress
- From Microbiome Associations to Deployable Precision Probiotics in Animals: A Critical Narrative Review and Proposed Causal Evidence Framework for Next-Generation Probiotic Development
- A lightweight edge-deployable detection method for sugarcane stem nodes in intelligent seed cane cutting equipment
- Field-deployable seed health diagnostic assay: RT-RPA-based detection of turnip mosaic virus in mustard leaf and seed lots
BibTeX
@article{meng2026edgedeployable,
title = {{Edge-deployable greenhouse tomato cluster harvesting robot integrating YOLOv8n-BiFPN-WIoU and ROS-based autonomous control}},
author = {Fanzhao Meng and Zhen Wang and Huan Wang and Xiaohui Li and Xizhen Xu and Ningrong Zeng and Guoqing Wang and Dongpo Wei and Xuan Li and Yunqi Shi},
journal = {Frontiers in plant science},
year = {2026},
month = oct,
doi = {10.3389/fpls.2026.1926482},
url = {https://europepmc.org/article/PMC/PMC13668862},
note = {CC BY},
}
RIS
TY - JOUR
TI - Edge-deployable greenhouse tomato cluster harvesting robot integrating YOLOv8n-BiFPN-WIoU and ROS-based autonomous control
AU - Fanzhao Meng
AU - Zhen Wang
AU - Huan Wang
AU - Xiaohui Li
AU - Xizhen Xu
AU - Ningrong Zeng
AU - Guoqing Wang
AU - Dongpo Wei
AU - Xuan Li
AU - Yunqi Shi
PY - 2026
DA - 2026/10/01
JO - Frontiers in plant science
DO - 10.3389/fpls.2026.1926482
UR - https://europepmc.org/article/PMC/PMC13668862
AB - Objective: To develop an edge-deployable greenhouse tomato cluster harvesting robot capable of accurate fruit detection, three-dimensional localization, autonomous navigation, and robotic harvesting under complex greenhouse conditions. The objective was to improve detection performance under fruit occlusion and variable illumination while maintaining real-time inference and stable robotic operation on embedded computing hardware. Methods: A lightweight YOLOv8n-based tomato detection model, termed YOLOv8n-BiFPN-WIoU, was developed by incorporating a bidirectional feature pyramid network and Wise-IoU loss to improve multiscale feature fusion and localization accuracy. An RGB-D vision system based on the Intel RealSense D435 was used for three-dimensional fruit localization. The robotic system integrated a rail-guided mobile platform, a six-axis manipulator, a dual-claw harvesting end-effector, and a ROS-based distributed control architecture. The vision model was optimized and deployed on an NVIDIA Jetson Nano using ONNX and TensorRT. Robot kinematics, hand-eye transformation, trajectory planning, and autonomous harvesting procedures were integrated to enable station-to-station operation and fruit harvesting. Results: The proposed YOLOv8n-BiFPN-WIoU model achieved a precision of 88.534%, recall of 89.377%, F1-score of 88.954%, [email protected] of 92.338%, and [email protected]:0.95 of 71.368%. Compared with the baseline YOLOv8n model, these metrics improved by 2.143, 2.779, 2.460, 4.587, and 5.675 percentage points, respectively. The proposed model increased the parameter count from 3.2 million to 3.6 million and computational complexity from 19.6 to 22.4 GFLOPs. After ONNX and TensorRT optimization, the model achieved an inference speed of 21.1 frames per second at an input resolution of 640 × 640 with batch size 1 on the Jetson Nano. The robotic system achieved a mean positioning error of 3.70 ± 0.32 mm across five representative targets, demonstrating the feasibility of accurate visual localization and robotic positioning for greenhouse tomato harvesting. Conclusion: The proposed edge-deployable greenhouse tomato cluster harvesting robot integrates lightweight deep learning, RGB-D three-dimensional localization, ROS-based autonomous control, rail-guided mobile operation, and robotic harvesting into a unified system. The YOLOv8n-BiFPN-WIoU model improved tomato detection performance while maintaining real-time inference on embedded hardware, and the integrated vision and manipulation system demonstrated accurate positioning suitable for autonomous harvesting. The results indicate that the proposed architecture provides a practical foundation for intelligent greenhouse tomato harvesting under complex visual and operational conditions.
SN - 1664-462X
ER -