PbDlib is a set of tools combining statistical learning, dynamical systems and optimal control approaches for programming-by-demonstration applications
see http://www.idiap.ch/software/pbdlib/ for details.
Set of algorithms and models in GNU Octave/Matlab to facilitate the re-programming of robots, for the automatic analysis and generation of movements, gestures and manipulation skills. The components rise from the cross-fertilization of statistical learning, dynamical systems and optimal control, enabling skill transfer from human demonstrations.
The software acts as companion codes for the journal article: Calinon, S.(2015), "A Tutorial on Task-Parameterized Movement Learning and Retrieval", Intelligent Service Robotics (Springer), DOI 10.1007/s11370-015-0187-9. It aims at growing when further research and functionalities become available.