A methods-time-measurement based approach to enable action recognition for multi-variant assembly in Human-Robot Collaboration

Journal
Procedia CIRP  
Volume
106
Start Page
233
End Page
238
Citation
Procedia CIRP 106: 233-238 (2022)
Contribution to Conference
9th CIRP Conference on Assembly Technology and Systems, CATS 2022  
Publisher DOI
10.1016/j.procir.2022.02.184
Scopus ID
2-s2.0-85127473404
Publisher
Elsevier
Action Recognition (AR) has become a popular approach to ensure efficient and safe Human-Robot Collaboration. Current research approaches are mostly optimized for specific assembly processes and settings. This paper introduces a novel approach to extend the field of AR to multi-variant assembly processes. The approach is based on generalized action primitives derived from Methods-Time-Measurement (MTM) analysis that are detected by an AR system using skeletal data. Subsequently a search algorithm combines the information from AR and MTM to provide an estimate of the assembly progress. One possible implementation is shown in a proof of concept and results as well as future work are discussed.
Subjects
Artificial Neural Network
Assembly
Assembly Step Recognition
Azure Kinect
Human Action Recognition
Human-Robot Collaboration
Industry 4.0
Methods-Time-Measurement
Particle Swarm Optimization
Skeleton Based Action Recognition
DDC Class
600: Technik
Publication version
publishedVersion
Lizenz
https://creativecommons.org/licenses/by-nc-nd/4.0/
Loading...
Thumbnail Image
Name

1-s2.0-S2212827122001858-main.pdf

Size

709.62 KB

Format

Adobe PDF