Abstract
Investigators discuss new findings in Robotics. According to news reporting originating from Nanjing, People's Republi c of China, by NewsRx correspondents, research stated, "Camellia oleifera is an oilseed crop with high economic value. The short optimum harvest period and high labour costs of C. oleifera harvesting have prompted research on intelligent ro botic harvesting." Funders for this research include National Forestry and Grassland Administration of the Emergency Science and Technology Project of China, National Natural Scie nce Foundation of China (NSFC). Our news editors obtained a quote from the research from Nanjing Forestry Univer sity, "This study focused on the determination of grabbing points for the roboti c harvesting of C. oleifera fruits, providing a basis for the decision making of the fruit-picking robot. A relatively simple 2D convolutional neural network (C NN) and stereoscopic vision replaced the complex 3D CNN to realise the 3D positi oning of the fruit. Apple datasets were used for the pretraining of the model an d knowledge transfer, which shared a certain degree of similarity to C. oleifera fruit. In addition, a fully automatic coordinate conversion method has been pro posed to transform the fruit position information in the image into its 3D posit ion in the robot coordinate system. Results showed that the You Only Look Once ( YOLO)v8x model trained using 1012 annotated samples achieved the highest perform ance for fruit detection, with mAP50 of 0.96 on the testing dataset. With knowle dge transfer based on the apple datasets, YOLOv8x using few-shot learning realis ed a testing mAP50 of 0.95, reducing manual annotation. Moreover, the error in t he 3D coordinate calculation was lower than 2.1 cm on the three axes. The propos ed method provides the 3D coordinates of the grabbing point for the target fruit in the robot coordinate system, which can be transferred directly to the robot control system to execute fruit-picking actions."
NETL
NSTL