A flow-matching model maps planned actions to randomly-sampled 'intended' actions, conditioned on prediction error, and this accelerates online dynamics model alignment in simulated UGV and quadrotor tasks.
Prov- able lifelong learning of representations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Action Flow Matching for Continual Robot Learning
A flow-matching model maps planned actions to randomly-sampled 'intended' actions, conditioned on prediction error, and this accelerates online dynamics model alignment in simulated UGV and quadrotor tasks.