Koch, JulianJulianKochBüsch, LukasLukasBüschGomse, MartinMartinGomseSchüppstuhl, ThorstenThorstenSchüppstuhl2022-05-032022-05-032022-03-10Procedia CIRP 106: 233-238 (2022)http://hdl.handle.net/11420/12418Action 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.en2212-82712022233238Elsevierhttps://creativecommons.org/licenses/by-nc-nd/4.0/Artificial Neural NetworkAssemblyAssembly Step RecognitionAzure KinectHuman Action RecognitionHuman-Robot CollaborationIndustry 4.0Methods-Time-MeasurementParticle Swarm OptimizationSkeleton Based Action RecognitionTechnikConference Paper10.15480/882.432310.1016/j.procir.2022.02.18410.15480/882.4323Conference Paper