Design and Experimental Investigation of the Grasping System of an Agricultural Soft Manipulator Based on FMDS-YOLOv8

Yu Zhuang^*Kunlin XuZiqi LiuJiayi LiLiuyang ShenJinfeng Wang^*

• Northeast Agricultural University, Harbin, China, Harbin, China

In response to the need for non-destructive sorting and grasping of fruit and vegetables with diverse sizes and shapes, this study presents a novel design for an agricultural manipulator grasping system (MGS). This system includes a variable-structure soft manipulator tailored for grasping fruit and vegetables. The manipulator is equipped with three independently rotatable and distance-adjustable soft actuators and demonstrates remarkable flexibility, grasping objects with a diameter of ≤140 mm in the center grasping configuration and ≤105 mm in the parallel grasping configuration. The improved FMDS-YOLOv8 vision recognition algorithm allows detection of the type, contour and positional coordinates of the target fruit. In addition, a MATLAB-based program was developed in conjunction with the vision system. This program was used to extract the contours of the target fruit and calculate the visualization of the optimal attitude of the soft manipulator, facilitating autonomous structural adjustments and precise control during grasping operations. The proposed variable-structure soft MGS was critically evaluated based on the performance of each component. The experimental results showed that, under the multi-objective conditions, the grasping success rate is 95.83%, the grasping damage rate is only 4.17%, and the grasping time is about 6.36 s. This verifies the effectiveness and adaptability of the MGS. By precisely adjusting the drive pressure and servo angle, the MGS can effectively grasp fruit and vegetables of different sizes and shapes within its working range, while minimizing damage during the grasping process.