GloVLA: Let Geometry Move and Local VLA Interact for Robust Object-Centric Manipulation in Unstructured Environments

Abstract

Vision-language-action (VLA) models have shown promising generalization for language-conditioned robot manipulation, but deploying them in unstructured environments remains challenging. A single end-to-end VLA policy must simultaneously solve long-range transport of the end effector to task-relevant regions and short-horizon, contact-rich interaction upon arrival. This formulation is inefficient and brittle: small visual shifts, distractors, clutter, occlusions, or unfavorable initial gripper poses can push the policy outside the local state distribution in which it was trained. We introduce GloVLA, a hybrid framework that explicitly separates object-centric manipulation into two complementary regimes: a geometric transport controller moves the end-effector into interaction-centric handoff regions, and local VLA policies handle only the short-horizon interaction phases. GloVLA is model-agnostic and integrates with different VLA backbones with no additional demonstrations and no changes to the action space or success predicate. Experiments on standard LIBERO and LIBERO-Plus Object tasks, a newly introduced LIBERO-Challenge benchmark, and real-world unstructured settings show that GloVLA improves task success and substantially lowers VLA inference cost compared with full end-to-end VLA execution. On LIBERO-Challenge, full-trajectory GR00T N1.6 execution degrades to 20.9% average success while GloVLA retains 88.5%; on a physical UR10e, overall success improves from 35.6% to 90.0% while mean inference time is more than halved.

BibTeX

@article{glovla2026,
  title   = {GloVLA: Let Geometry Move and Local VLA Interact for Robust
             Object-Centric Manipulation in Unstructured Environments},
  author  = {Anonymous Authors},
  journal = {Under review},
  year    = {2026}
}