Research on Target Recognition and Grasping of Dual-arm Cooperative Mobile Robot Based on Vision

For the problems of recognition, low grasping accuracy and insufficient stability of service robots in home life. An object recognition and capture method of home scene using deep learning algorithm is proposed. The target detection algorithm based on YOLOv8 is adopted to identify 4 types of object, and the object is grasped by the flexible gripper of the dual-arm cooperative mobile robot. The kinematics of the robot is solved by D-H method, and the grasping experiment is carried out. The experimental results show that the target detection algorithm based on YOLOv8 has a recognition accuracy of more than 85% for the 4 types of target objects, and the capture success rate is more than 80%. It has high positioning accuracy and grasping success rate, which can meet the needs of actual home service robots. The research results lay a foundation for the research of home service robots.