AutoIntervene automatically transfers control between a robot policy and an operator using calibrated visual-action support, then adapts the policy from the retained intervention segments.
Diffeomorphic transforms for generalised imitation learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
AutoIntervene: Calibrated Intervention for Action-Chunking Imitation Learning Policies
AutoIntervene automatically transfers control between a robot policy and an operator using calibrated visual-action support, then adapts the policy from the retained intervention segments.