Vision and Tactile Sensing for DLO Manipulation and Pin Insertion in Robotic Connector Assembly

Automating deformable linear object (DLO) manipulation is vital for advancing manufacturing in industries like automotive, aerospace, and electronics. Among these, connector assembly poses a significant challenge due to the inherent complexity of handling flexible objects and the demand for high precision. This article introduces a novel methodology for automating connector assembly using a robot equipped with a custom mechatronic tool. The system integrates a parallel-jaw gripper with sensorized fingers and a stereo camera setup to ensure accurate pin alignment and insertion. The stereo vision system estimates the pin’s full 6-D pose, while the sensorized fingers monitor the insertion process in real time, reducing failure risks and eliminating reliance on global force measurements. In addition, a pull test validates the assembly. Real-world experiments with two distinct connector assembly tasks demonstrate the proposed approach's effectiveness. The results underscore the system's potential to boost automation, improve assembly quality, and decrease reliance on manual labor in complex connector assembly operations.