A Novel Strategy for Automatic Error Classification and Error Recovery for Robotic Assembly in Flexible Production

  • PDF / 3,250,207 Bytes
  • 15 Pages / 595.224 x 790.955 pts Page_size
  • 81 Downloads / 230 Views

DOWNLOAD

REPORT


A Novel Strategy for Automatic Error Classification and Error Recovery for Robotic Assembly in Flexible Production Ewa Kristiansen1

· Emil Krabbe Nielsen2 · Lasse Hansen3 · David Bourne4

Received: 12 December 2019 / Accepted: 13 August 2020 © The Author(s) 2020

Abstract In this article, we develop a novel strategy for automatic error classification and recovery in robotic assembly tasks. The strategy does not require error diagnosis. It allows for effective reduction of an undetermined number of error states to 4, without the need for further operator updates of error space. The strategy integrates existing methods for computer vision, active vision and active manipulation. Our solution is implemented in a generic software framework, which is independent from software and hardware for implementing error detection and allows for application in other assembly types and components. The value of our strategy was experimentally validated on a simple case, where we inserted a battery into a cell phone. The experiment was performed on 1500 assembly attempts and included 500 detected errors. The whole experiment ran for 42 hours, with no need for operator assistance or supervision. The resulting classification rate is 99.6% and the resulting recovery rate is 98.8%. The 6 unrecovered errors were successfully resolved in a successive assembly attempt. Keywords Automatic error classification · Automatic error recovery · Robotic assembly · Flexible production · Semi-structured environment · Active vision

1 Introduction Recently, companies must cope with short product lifecycles, which are caused by rapidly changing technologies and intense competition. When automating manufacturing processes companies can invest in dedicated, hard automation. Unfortunately, these production lines must be reconfigured for a new product variant, which is both time consuming and expensive. Alternatively, companies can use robots and programmable equipment to eliminate drastic changes Electronic supplementary material The online version of this article (https://doi.org/10.1007/s10846-020-01248-3) contains supplementary material, which is available to authorized users.  Ewa Kristiansen

[email protected] 1

Department of Materials and Production, Aalborg University, Fibigerstræde 16, 9220, Aalborg Ø, Denmark

2

Department of Electrical Engineering, Technical University of Denmark, Elektrovej 326, 2800, Kgs. Lyngby, Denmark

3

Nel Hydrogen, Fueling and Solutions, Vejlevej 5, 7400 Herning, Denmark

4

Robotics Institute, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA

to an existing manufacturing facility, with the changes being addressed by software adjustments. Increasing the flexibility of industrial robotic setups is an important goal for future production systems [1, 2] to make low volume production cost effective. Flexible robotic assembly is difficult to automate because the variations between different batches and the uncertainties and compliance introduced by flexible fixtures and tools, make the conventional