Dragon fruit detection in natural environments remains challenged by limited accuracy and deployment difficulties, primarily due to variable lighting and occlusions from branches. To enhance detection accuracy and satisfy the deployment constraints of edge devices, we propose YOLOv10n-CGD, a lightweight and efficient dragon fruit detection method designed for robotic harvesting applications. The method builds upon YOLOv10 and integrates Gated Convolution (gConv) into the C2f module, forming a novel C2f-gConv structure that effectively reduces model parameters and computational complexity. In addition, a Global Attention Mechanism (GAM) is inserted between the backbone and the feature fusion layers to enrich semantic representations and improve the detection of occluded fruits. Furthermore, the neck network integrates a Dynamic Sample (DySample) operator to enhance the spatial restoration of high-level semantic features. The experimental results demonstrate that YOLOv10n-CGD significantly improves performance while reducing model size from 5.8 MB to 4.5 MB—a 22.4% decrease. The mAP improves from 95.1% to 98.1%, with precision and recall reaching 97.1% and 95.7%, respectively. The observed improvements are statistically significant (p < 0.05). Moreover, detection speeds of 44.9 FPS and 17.2 FPS are achieved on Jetson AGX Orin and Jetson Nano, respectively, demonstrating strong real-time capabilities and suitability for deployment. In summary, YOLOv10n-CGD enables high-precision, real-time dragon fruit detection while preserving model compactness, offering robust technical support for future robotic harvesting systems and smart agricultural terminals.

Mechanism and experimental study on the fruit detachment of Chinese wolfberry through reciprocating vibration

The real-time and accurate recognition of fruits and vegetables is crucial for the intelligent control of fruit and vegetable robots. In this research, apple picking is selected. This study proposed a lightweight, coupon-product, neural-net terminal YOLO algorithm for apple image recognition. Compared with the YOLO series algorithm, the tiny algorithm shows a strong relationship with the calculation speed. In traditional red fruit detection, the recognition time is generally several seconds, which is unacceptable in the real-time system. In this research, a total of 2000 apple images from different environments are used as a dataset for training and testing. The YOLOv4-tiny model is detailed, instructed, and used for the identification. The indicators, such as F1Score (0.92) and mAP (95.5% average), are analyzed by calculating the loss rate, accuracy rate (96.21%), and recall rate (95.47%). Finally, the algorithm shows good accuracy and high speed (no more than 5 ms) in online real-time detection.

How to ensure the "carbon peaking and carbon neutrality" goal is a crucial problem for China with good performance, low cost and limited time. As a pillar industry, the manufacturing industry need offer more great potential helps. In this paper, for the intelligent workshop, firstly, an energy consumption architecture, based on mutual inductance sensing technology & a multi-granularity production line energy consumption modeling, is put forward. Secondly, the device-level sensing technology demonstrates the detailed implementation for the multi working condition machines whose power is unknown. And then, the research devoted the basic aspects of the proposed multi-granularity production line energy consumption modeling and summarized the implementation elements of 3-matrix (the attribute attributes, power attributes and cumulative timing attributes). Above the 2 sections, the robot and SMT production lines case studies are presented separately. Results show that the architecture can effectively sense and model the energy consumption of the devices and the workshop, which provides an available method for the fine management and control of energy consumption and energy efficiency. Through this study, we hope to provide some reference ideas for future researchers.

Current status of orchard mechanization technologies and key development priorities in the 15th Five-Year Plan period

Energy consumption mechanism simulation and experimental study of reciprocating vibration for Chinese wolfberry picking