A vision-language-action robot policy that recursively refines its predicted future tactile latents from live tactile feedback improves measured success on seven real-robot dexterous tasks by 18 to 24 points over baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ReTouch: Empowering Contact-Rich Dexterous Manipulation with Online-Refined Tactile Prediction
A vision-language-action robot policy that recursively refines its predicted future tactile latents from live tactile feedback improves measured success on seven real-robot dexterous tasks by 18 to 24 points over baselines.