Skip to main content
Search

# Actuation Shift Adaptation

1 related articles

Subscribe to updates
  1. arXiv

    A robot swaps its body and the frozen VLA still works: ReGround lifts success from 0.16 to 0.90 at 400 ms latency

    When a vision-language-action (VLA) model is deployed on a robot whose actuation has changed, through remounting, mechanical wear or altered command latency, the same action command produces a different physical motion and tasks fail. ReGround keeps the VLA frozen at inference time, reads out the trajectory the policy intends using a forward model of the training body, then tracks that trajectory with a deployed-body model learned from task-agnostic motor babbling, while a trust region keeps actions close to the policy's own plan. Across two VLAs, eight LIBERO tasks and five shift settings it recovers 0.91–1.00 of lost success, for example raising success from 0.16 to 0.90 under 400 ms latency.

You’re all caught up