Error prevention in robotic assembly tasks by a machine vision and statistical pattern recognition method

Abstract

Assembly errors can occur in a robotic assembly system. In this paper, a method that predicts an assembly error is proposed. It considers that assembly errors occur under the condition that the geometric trajectory of a mated part and the relational position and orientation of a base part are outside the allowable tolerance. A certain point, which is determined by using a physical light reflectance model of a mated part, is followed with two high-speed cameras. A statistical pattern recognition method in which explanatory variables are tracked points in a three-dimensional space is then employed to predict an assembly error. The proposed method is applied to a peg-in-a-hole assembly by a selective compliance assembly robot arm (SCARA)-type robot and its potential value is discussed.

Robotized Surface Mounting of Permanent Magnets

“…Replacing the small steel plate mounted under the pick-up position on the PM delivery station with an electromagnet (holding down the PMs more effectively) could result in further controlled picking up of the PM. Adding extended sensor supervision to the robot cell, e.g., to confirm that the PM polarization direction is correct, to check the PMs for defects before being mounted and to use a machine vision system to prevent assembly errors during the PM mounting onto the translator could also improve its robustness [17].…”

Computer Vision Techniques in Manufacturing

“…2) Assembly Quality Control: Assembly error detection is also an important application of CV, such as assembly error prediction through statistical pattern recognition of geometric positions between mated parts and base parts [131], and fastener feature recognition [132]. In automotive assembly lines, human errors involved in the bolt securing process can be identified [133].…”

Computer Vision Techniques in Manufacturing

“…2) Assembly error detection: Assembly error detection is another important application of CV in the assembly process. Statistical pattern recognition methods can be applied to predict assembly errors when the geometric trajectory of a mated part and the relational position of a base part are out of the allowable tolerance in a robotic assembly system [139]. Vision-based identification algorithms can also be applied to recognize unique features around fasteners so that the assemble results of fasteners are able to be verified [140].…”