Sensor Selection and Stage & Result Classifications for Automated Miniature Screwdriving

Hundreds of billions of small screws are assembled in consumer electronics industry every year, yet reliably automating the screwdriving process remains one of the most challenging tasks. Two barriers to further adoption of robotic threaded fastening systems are system cost and technical challenges, especially for small screws. An affordable intelligent screwdriving system that can support online stage and result classification is the first step to bridge the gap. To this end, starting from a state transition graph of screwdriving processes and a labeled screwdriving dataset (1862 runs of M1.4 screws) on multiple sensor signals, we develop classification algorithms and perform sensor reduction. Fast and accurate result classifiers are developed using linear discriminant analysis, while a wrapper method for feature subset selection is used to identify the optimal feature subset and corresponding sensor signals to reduce cost. A stage classifier based on decision tree is developed using the optimal sensor subset. The stage classifier achieves high accuracy in realtime prediction of various stages when augmented with the state transition graph.

I. Introduction

Threaded fastening is one of the most commonly used methods in industrial assembly [1]. Around 1/4 to 1/3 of typical assembly operations can be classified as bolt and nut insertions [2]–[4]. Unfortunately, screwdriving remains one of the most difficult tasks to automate, despite substantial research in this field. One reason might be due to our incomplete understanding of the underlying process, particularly the initial mating step [5]. Our survey paper [1] summaries various open problems and barriers that confront automated screwdriving systems. Four major improvements need to be made: (1) fast and reliable ways to feed screws with smaller length-to-diameter aspect ratios; (2) strategies for fast and reliable initial thread mating and early fault detection; (3) interactions of multiple objects (screw, driver bit, vaccum adapter, and target); (4) online failure prediction and fault recovery algorithms.