SOURCE-LINKED INTELLIGENCE

TacBPM: A Tactile-conditioned Behavior Prior Model for Dexterous Reorientation

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Dexterous in-hand manipulation requires policies that coordinate high-DoF hand joints through intermittent, contact-rich interaction. Beyond target-orientation tracking, such policies must discover finger gaits that preserve object stability while adapting to geometry, anisotropy, pose, contact, and sensing changes. We propose \method, a tactile-conditioned behavior prior model for dexterous reorientation. \method distills multi-scale sphere specialists into a latent controller and lets downstream policies reuse the fixed tactile prior through residual latent actions, reducing renewed explorat

Read original source ↗ Open in workspace

recordType

paper

region

Global