Robotic Autonomous Snap-Fit Assembly of Flexible Printed Circuit: Mahalanobis Distance-Based Force-Tactile Contact State Perception

Autonomous robotic assembly of flexible printed circuit (FPC) for electronic devices requires accurate characterization of contact states between terminals and slots. This task becomes particularly challenging in scenarios with limited visibility and high precision demands. While visual methods often fail in such conditions, tactile sensing effectively captures contact states between the sensor and target object. Consequently, this paper considers the FPC assembly task as one of representing the relative offset and snap-fit states of terminals and slots based on tactile signals. 1) This paper proposes a contact state perception and representation model combining Mahalanobis distance with a forward difference processing mechanism. The model utilizes Mahalanobis distance to characterize and predict the offset of FPC terminals and slots from tactile data and employs the forward difference mechanism for real-time snap-fit state monitoring. 2) A robot autonomous snap-fit method for FPC assembly is proposed, where the sensed contact state serves as closed-loop feedback to guide the robot in autonomous decisionmaking and action resolution to complete efficient and real-time FPC assembly. Experiments conducted on the iPhone 12 assembly platform validate the effectiveness of the proposed method.