arXiv Artificial Intelligence

Outcome-Conditioned End-Effector Geometry Across Vision-Language-Action Policies

2 hours ago 21.09.2026 07:00 👁 2 views
Outcome-Conditioned End-Effector Geometry Across Vision-Language-Action Policies

Quick summary

arXiv:2609.21659v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies solve the same manipulation task through different action interfaces, but task success alone does not establish whether their physical executions agree. We study cross-policy end-effector geometry in 15,000 closed-loop LIBERO rollouts from four policies. The primary clean-condition analysis forms 3,600 configuration-matched, and therefore dependent, policy pairs. Both-success pairs have a median normalized dynamic time warping distance of 0.0120 m versus 0.0380 m when exactly one policy succeeds. This order

Key takeaways

  • arXiv:2609.21659v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies solve the same manipulation task through different action interfaces, but task success alone does not establish whether their physical executions agree.
  • We study cross-policy end-effector geometry in 15,000 closed-loop LIBERO rollouts from four policies.
  • The primary clean-condition analysis forms 3,600 configuration-matched, and therefore dependent, policy pairs.

Why it matters

The significance is not only the legal text but how it changes product design. Decisions around “Outcome-Conditioned End-Effector Geometry Across Vision-Language-Action Policies” may reshape data collection, model training, output accountability and market access.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗