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
Direct Numerical Simulation of Thermoacoustically Unstable Flames Via Non-Drifting Acoustic Delay Characteristic Boundary Conditions
0arXiv cs.NA
On the sharp linear convergence rate of the circumcentered--reflection method on subspaces
0arXiv cs.NA
Quantum Gibbs sampling through the detectability lemma
0arXiv cs.NA
RustMC: Automated Verification of Real-World Concurrent Rust
0arXiv cs.CR
CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios
0arXiv cs.CR
HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption
0arXiv cs.CR