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
Federal Register API in Python: proposed rules closing for comment in the next 14 days, in a CSV (no API key)
0dev.to
Fixing 90% of MCP pain on Windows in 5 minutes (Unreal, Blender, Unity...)
0dev.to
I tested an AI agent on real API migrations. Green CI was not proof.
0dev.to

Safe, AI-assisted application customizations? Yes please!
0dev.to
EV Charging Software and OCPP: A Plain Guide for Developers
0dev.to
Your analytics export says more than you think (if you read it honestly)
0dev.to OpenSource