The Neural Automation Project
Software for Academic Purpose (Matlab)
tau-SEDS, NIVF, and NILC Approaches - Matlab Code
tau-SEDS (SEDS with diffeomorphic transformations), NIVF (Neurally-Imprinted Stable Vector Fields), and NILC (Neurally-Imprinted Lyapunov Candidate).
Accuracy and stability have in recent studies been emphasized as the two major ingredients to learn robot motions from demonstrations with dynamical systems. Several approaches yield stable dynamical systems but are also limited to specific dynamics that can potentially result in a poor reproduction performance. The current work addresses this accuracy-stability dilemma through new approaches that serve as a framework generalizing the class of demonstrations that are learnable by means of provably stable dynamical systems.
tSEDS_NIVF_NILC_v3_20210428.zip
Archivdatei im ZIP Format [9.9 MB]
tau-SEDS (SEDS with diffeomorphic transformations), NIVF (Neurally-Imprinted Stable Vector Fields), and NILC (Neurally-Imprinted Lyapunov Candidate).
Accuracy and stability have in recent studies been emphasized as the two major ingredients to learn robot motions from demonstrations with dynamical systems. Several approaches yield stable dynamical systems but are also limited to specific dynamics that can potentially result in a poor reproduction performance. The current work addresses this accuracy-stability dilemma through new approaches that serve as a framework generalizing the class of demonstrations that are learnable by means of provably stable dynamical systems.
tSEDS_NIVF_NILC_v3_20210428.zip
Archivdatei im ZIP Format [9.9 MB]
Druckversion 