Trajectory creation towards fast skill deployment in plug-and-produce assembly systems: A Gaussian-Mixture Model approach
conference contributionposted on 21.03.2019 by Melanie Zimmer, Ali Al-Yacoub, Pedro Ferreira, Niels Lohse
Any type of content contributed to an academic conference, such as papers, presentations, lectures or proceedings.
In this paper, a technique that reduces the changeover time in industrial workstations is presented. A Learning from Demonstration-based algorithm is used to acquire a new skill through a series of real-world human demonstrations in which the human shows the desired task. Initially, the collected data are filtered and aligned applying Fast Dynamic Time Warping (FastDTW). Then the aligned trajectories are modelled with a Gaussian Mixture Model (GMM), which is used as an input to generate a generalisation of the motion through a Gaussian Mixture Regression (GMR). The proposed approach is set into the context of the openMOS framework to efficiently add new skills that can be performed on different workstations. The main benefit of this work in progress is providing an intuitive, simple technique to add new robotics skills to an industrial platform which accelerates the changeover phase in manufacturing scenarios.
The research leading to these results has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 680735, project openMOS (Open Dynamic Manufacturing Operating System for Smart Plug-and-Produce Automation Components). Funding from the Engineering and Physical Science Research Council Centre for Doctoral Training in Embedded Intelligence (grant no. EP/L014998/1) is also acknowledged.
- Mechanical, Electrical and Manufacturing Engineering