Learning human actions from complex manipulation tasks and their transfer to robots in the circular factory

• DOI: 10.1515/auto-2024-0008
• Publication Date: 2024-09-10T13:34:52Z
• Authors: Manuel Zaremski; Blanca Handwerker; Christian R. G. D...; Fabian Leven; David Schneider; Alina Roitberg; Rainer Stiefelhagen; Gerhard Neumann; Michael Heizmann; Tamim Asfour; Barbara Deml
• Keywords: Factory (object-oriented programming)

Abstract Process automation is essential to establish an economically viable circular factory in high-wage locations. This involves using autonomous production technologies, such as robots, disassemble, reprocess, and reassemble used products with unknown conditions into the original or a new generation of products. complex highly dynamic issue that high degree uncertainty. To adapt robots these conditions, learning from humans necessary. Humans are most flexible resource they can their knowledge skills tasks changing conditions. paper presents interdisciplinary research framework for human action manipulation through observation demonstration. The acquired will be described machine-executable form transferred industrial execution by factory. There two primary objectives. First, we investigate multi-modal capture behavior description knowledge. Second, reproduction generalization learned actions, disassembly assembly actions on studied.