In order to avoid the false extraction of redundant planes in the background when the robot is recognizing goods on the shelf,an improved method for grabbing goods on the shelf is designed.A random sampling consistency algorithm based on normal vector is used to segment the shelf plane,and the European clustering algorithm is used to obtain the location informa-tion of the goods above the shelf plane,and the collected data set is fed back to the upper computer in the system to provide command parameters for the motion planning of robots and mechanical arms.The experimental results show that the robot can effectively avoid the recognition of redundant planes and complete shelf plane recognition and good grabbing task.
维普
万方数据