Research on the Application of Rigid-flexible Compound Driven Fruit Picking Robot Design in Realizing Fruit Picking

Abstract This article mainly designs an efficient fruit picking robot that combines rigidity and flexibility. The design of the adopts a mechanical arm with 5 degrees freedom for mecanum wheel. is equipped gripper made using artificial muscle technology. ZED2 binocular vision system used to obtain spatial coordinates realize positioning arm. Video image acquisition. In order automatic recognition strawberries, this paper creates strawberry training set, uses yolov3 algorithm train data obtains model, which has recall rate larger strawberries immature precision reached 90%, detection small target more than 80%. It can Meet requirements in real life.