Peg-in-hole assembly of industrial robots based on Object detection and Admittance force control

Abstract

The traditional position control of industrial robot is prone to assembly failure due to the position error of assembly target in the situation of peg-in-hole assembly in unknown environment. Based on this, an assembly scheme of industrial robot is designed, which combines object detection, admittance force control and position error estimation. The results show that the object detection meets the requirements of real-time and accuracy, The admittance force control has a good fine-tuning effect in the assembly process, and the position error estimation accuracy is high. The industrial robot can accurately and quickly complete the round hole assembly task when facing the unknown target position.