arXiv ·
This paper introduces a convolutional transformer model for classifying tomato maturity, along with a new UAE-sourced dataset, KUTomaData, for training segmentation and classification models. The model combines CNNs and transformers and was tested against two public datasets. Results showed state-of-the-art performance, outperforming existing methods by significant margins in mAP scores across all three datasets.
arXiv ·
Researchers developed a force-data-driven robotic harvesting system for cherry tomatoes, integrating six-axis force/torque sensing, a bio-inspired compliant gripper, and a mobile robotic platform. Manual trials informed the design of a novel Finray gripper and a hybrid grip-twist-pull strategy, applying specific forces and torques to detach the fruit gently. Validated at a commercial greenhouse in Abu Dhabi, UAE, the system achieved an 86.0% picking success rate with only 2.3% fruit damage and an 8.4-second cycle time per fruit. Why it matters: This development demonstrates a practical and efficient solution for delicate robotic harvesting in controlled agricultural environments, with direct relevance to food security initiatives in the Middle East.
arXiv ·
YOLO26-RipeLoc Lite is a new lightweight deep learning architecture designed for simultaneous detection, ripeness classification, and center-point localization of greenhouse tomatoes for robotic harvesting. The model incorporates a Lightweight Feature Pyramid Network, a Ripeness-Aware Attention Module, and a Compact Detection Head for efficient and precise operation. Evaluated on a custom dataset from the SILAL greenhouse in Abu Dhabi, UAE, it achieved a [email protected] of 92.9% with only 2.38 million parameters, outperforming existing YOLO models in accuracy-efficiency. Why it matters: This research provides an efficient and accurate solution for automating a critical agricultural process, enhancing food security and technological capabilities in the region's greenhouse farming.