Backend
Right Goal, Wrong Body: Re-grounding Frozen VLAs under Actuation Shift
arXiv cs.RO0 views
arXiv:2611.20244v1 Announce Type: new Abstract: Vision-language-action (VLA) models are capable of producing desired robotic behaviors in ideal settings. However, they often fail when the robot's actuation changes at deployment. For example, remounting, mechanical wear, or command latency changes can lead to failed tasks and unsafe behaviors. To address the inevitable actuation shift, we propose ReGround, an inference-time method that keeps the VLA frozen and re-grounds its intended motion. ReGround learns the deployed robot's dynamics from task-agnostic motor babbling, and then tracks the policy's intended motion while staying close to the policy's own plan. ReGround activates only upon detecting a shift, and needs no rewards, demonstrations, or retraining. We show via two VLAs, eight LIBERO tasks, and five shift settings that ReGround can restore near-oracle success, such as raising $\pi_{0.5}$'s success from 0.16 to 0.90 under 400 ms latency, while remaining safer than a linear-calibration baseline. Project website and open-source code: https://umersiddique94.github.io/ReGround/.
Source:https://arxiv.org/abs/2611.20244PreviousDAPPT: Domain-Aware Policies from Procedural Trajectories for Sim-to-Real Dexterous Tool UseNextDexFormer 2.0: Towards a Cross-Embodiment Foundation Policy for Dexterous Grasping
Related posts
Signature Webhook HMAC-SHA256 Tidak Cocok? Hex vs Base64 dan 4 Jebakan yang Sering Terjadi
0dev.to
How do I make sure my agent drops outdated instructions instead of getting confused?
0dev.to

Klastro Walkthrough: Real Kubernetes Labs, in Your Browser
0dev.to
Part 2: The Main Problem - My Kali Download Was Too Small
0dev.to

Where the human gate goes: designing autonomy for coding agents
0dev.to
Nine clocks in one Next.js app, and the copyright year on 109 of our 111 pages was decided at 18:52 on 16 November
0dev.to