An extended NCDS framework learns multiple robot skills from a single network by conditioning on task variables and performs obstacle avoidance in the latent space while preserving contraction-based stability.
Expected path length on random manifolds
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Manifold learning seeks a low dimensional representation that faithfully captures the essence of data. Current methods can successfully learn such representations, but do not provide a meaningful set of operations that are associated with the representation. Working towards operational representation learning, we endow the latent space of a large class of generative models with a random Riemannian metric, which provides us with elementary operators. As computational tools are unavailable for random Riemannian manifolds, we study deterministic approximations and derive tight error bounds on expected distances.
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Extended Neural Contractive Dynamical Systems: On Multiple Tasks and Riemannian Safety Regions
An extended NCDS framework learns multiple robot skills from a single network by conditioning on task variables and performs obstacle avoidance in the latent space while preserving contraction-based stability.