Current Lycium barbarum L. vibration harvesting equipment exhibits low levels of intelligence and precision, often resulting in a trade-off between efficiency and fruit damage. This study proposed a ripe fruit region detection model, YOLO-RFR, specifically for precision vibration harvesting of L. barbarum. First, the ADown downsampling module was introduced to replace part of the conventional convolution layers. Then, the C3k2-AP module, inspired by the asymmetric padding strategy, was designed to replace the C3k2 module. Additionally, the GCHead detection head was constructed using group convolution. Finally, the EMA-Slide Loss function was developed to optimize the classification performance by combining the slide weighting function with Exponential Moving Average (EMA). The experimental results showed that the model achieved precision, recall, and mAP of 93.7%, 92.0%, and 97.0%, respectively, representing improvements of 4.0%, 4.4%, and 2.6% over the baseline. The parameter, floating-point operations (FLOPs), and model size were 1.7 M, 4.1 G, and 3.8 MB, respectively, corresponding to decreases of 34.6%, 34.9%, and 30.9% compared with the baseline. To further validate its practical feasibility, the improved model was deployed on an NVIDIA Jetson AGX Xavier embedded device, achieving an inference speed of 163 fps with TensorRT acceleration. In conclusion, the YOLO-RFR model demonstrated excellent performance in detection accuracy, model lightweighting, and deployment on embedded devices, providing strong technical support for the precision vibration harvesting of L. barbarum.

To enable efficient and low-cost automated apple harvesting, this study presented a multi-class instance segmentation model, SCAL (Star-CAA-LADH), which utilizes a single RGB sensor for image acquisition. The model achieves accurate segmentation of fruits, fruit-bearing branches, and main branches using only a single RGB image, providing comprehensive visual inputs for robotic harvesting. A Star-CAA module was proposed by integrating Star operation with a Context-Anchored Attention mechanism (CAA), enhancing directional sensitivity and multi-scale feature perception. The Backbone and Neck networks were equipped with hierarchically structured SCA-T/F modules to improve the fusion of high- and low-level features, resulting in more continuous masks and sharper boundaries. In the Head network, a Segment_LADH module was employed to optimize classification, bounding box regression, and mask generation, thereby improving segmentation accuracy for small and adherent targets. To enhance robustness in adverse weather conditions, a Chain-of-Thought Prompted Adaptive Enhancer (CPA) module was integrated, thereby increasing model resilience in degraded environments. Experimental results demonstrate that SCAL achieves 94.9% AP_M and 95.1% mAP_M, outperforming YOLOv11s by 6.6% and 4.6%, respectively. Under multi-weather testing conditions, the CPA-SCAL variant consistently outperforms other comparison models in accuracy. After INT8 quantization, the model size was reduced to 14.5 MB, with an inference speed of 47.2 frames per second (fps) on the NVIDIA Jetson AGX Xavier. Experiments conducted in simulated orchard environments validate the effectiveness and generalization capabilities of the SCAL model, demonstrating its suitability as an efficient and comprehensive visual solution for intelligent harvesting in complex agricultural settings.

The production of Lycium barbarum L. is a labor-intensive industry. Multiple manual harvests are required during the harvesting season, which contributes to the high harvesting costs. The cultivation conditions of L. barbarum were investigated to increase efficiency and mitigate harvesting damage. A torsion harvester was designed according to the characteristic of infinite inflorescence and the distribution of detachment force, and the kinematics model of the harvester was established. The vibration responses of ripe and unripe fruit were obtained through ADAMS simulation of the branch model, and the influencing factors and value range of the torsion harvester were also determined. The mathematical models of ripe fruit harvesting rate, unripe fruit harvesting rate, ripe fruit damage rate and torsion angle, vibration rods distance, and vibration frequency were established by the Box-Behnken test. The influences of various factors on ripe fruit harvesting rate, unripe fruit harvesting rate, and ripe fruit damage rate were analyzed, and the best parameter combination was obtained: torsion angle 73.66°, vibration rods distance 35.51 mm and vibration frequency 19.12 Hz. Field experiment showed that the harvesting rate of ripe fruit is 95.67%, the harvesting rate of unripe fruit is 4.68%, and the damage rate of ripe fruit is 3.70%. The research results can promote the mechanization process of L. barbarum harvest, and provide a reference for vibration harvest of berries.