Human Manipulation Segmentation and Characterization Based on Instantaneous Work
This paper is related to the observation of human operator manipulating objects for teaching a robot to reproduce the action. Assuming the robotic system is equipped with basic manipulation skills, we focus here on the automatic segmentation of the observed manipulation, for extracting the relevant key frames in which the manipulation is best described. The segmentation method proposed is based on the instantaneous work, and presents the advantage of not depending on the force and pose sensing locations. The proposed approach is experimented with two different manipulation skills, sliding and folding, under different settings.
KeywordsTeaching by demonstration Manipulation segmentation
Supported by the Elkartek MALGUROB and the SARAFun project under the European Union’s Horizon 2020 research & innovation programme, grant agreement No. 644938. The authors would like to thank Dr. Pierre Barralon for the fruitfull discussions that led to the segmentation approach presented here.
- 1.Almeida, D., Karayiannidis, Y.: Folding assembly by means of dual-arm robotic manipulation. In: IEEE ICRA, pp. 3987–3993, May 2016Google Scholar
- 2.Billard, A., Calinon, S., Dillmann, R., Schaal, S.: Robot Programming by Demonstration, pp. 1371–1394. Springer, Berlin (2008)Google Scholar
- 3.Calinon, S.: Robot Programming by Demonstration. A Probabilistic Approach. EPFL Press, Lausanne (2009)Google Scholar
- 6.Kovács, E.: Rotation about an arbitrary axis and reflection through an arbitrary plane. In: Annales Mathematicae et Informaticae, vol. 40, pp. 175–186, January 2012Google Scholar
- 7.Kragic, D., Gustafson, J., Karaoguz, H., Jensfelt, P., Krug, R.: Interactive, collaborative robots: challenges and opportunities. In: IJCAI-18, pp. 18–25 (2018)Google Scholar
- 10.Perez-D’Arpino, C., Shah, J.A.: C-learn: learning geometric constraints from demonstrations for multi-step manipulation in shared autonomy. In: IEEE ICRA, pp. 4058–4065, May 2017Google Scholar