Force Policy learns a global vision policy for free space and a local force-feedback policy that recovers an interaction frame to execute stable hybrid force-position control in contact-rich manipulation.
Learning diffusion policies from demonstrations for compliant contact-rich manipulation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.RO 3verdicts
UNVERDICTED 3representative citing papers
Framework generates force-informed sim data from one demo to train compliant visuomotor flow matching policies, showing reliable contact on real-robot block flipping and bi-manual tasks.
SCP integrates diffusion-based imitation learning with Gaussian-encoded surface constraints and dynamic movement primitives to generate actions with improved success rates and contact stability on free-form surfaces.
citing papers explorer
-
Flow with the Force Field: Learning 3D Compliant Flow Matching Policies from Force and Demonstration-Guided Simulation Data
Framework generates force-informed sim data from one demo to train compliant visuomotor flow matching policies, showing reliable contact on real-robot block flipping and bi-manual tasks.