Extending extrapolation capabilities of probabilistic motion models learned from human demonstrations using shape-preserving virtual demonstrations
Riccardo Burlizzi,Maxim Vochten,Joris De Schutter,Erwin Aertbeliën,Riccardo Burlizzi,Maxim Vochten,Joris De Schutter,Erwin Aertbeliën
Learning from Demonstration (LfD) requires methodologies able to generalize tasks in new situations. This paper studies the use of virtual demonstrations to extend the extrapolation capabilities of probabilistic motion models such as the traPPCA method. Similarly to other LfD methods, traPPCA is able to calculate new trajectories very fast, but does not generalize well outside the area covered by ...
