A hypernetwork generates clock-augmented stable neural ODEs (sNODEs) for scalable continual learning from demonstration, achieving O(N) training time via stochastic regularization while outperforming baselines on LfD tasks up to 26 skills and 32 dimensions.
Teacher feedback to scaffold and refine demonstrated motion primitives on a mobile robot,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Scalable and Efficient Continual Learning from Demonstration via a Hypernetwork-generated Stable Dynamics Model
A hypernetwork generates clock-augmented stable neural ODEs (sNODEs) for scalable continual learning from demonstration, achieving O(N) training time via stochastic regularization while outperforming baselines on LfD tasks up to 26 skills and 32 dimensions.