跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.26161 · v1

One View, One Action: Spatially Generalizable VLAs through Observation-Aligned Experts and Cross Graph Consistency

首次提交 2026-11-19 22:16
版本更新 2026-11-19 22:16
雷达观测 2026-11-20 16:53
arXiv ↗PDF ↗

摘要

Multi-view vision-language-action (VLA) models still face challenges in spatial generalization, particularly under changes in camera viewpoints and robot initial states. These models typically receive action supervision only in the robot base frame, requiring them to implicitly learn the spatial correspondence between observations from each view and base-frame actions. We propose One View, One Action (OVOA-VLA), which learns to predict actions in each view's camera frame, allowing the same physical motion to provide diverse, observation-aligned supervision across views. OVOA-VLA jointly trains a base-frame expert and view-specific action experts, whose robot-state inputs and action targets are expressed in their respective camera frames. Two complementary directed attention graphs model both directions of interaction between the base and view-specific experts, jointly leveraging view-specific action supervision to improve base-frame prediction. Cross Graph Consistency further encourages agreement between the two graphs' base-frame predictions for the same sample. With the same multi-view inputs, the model supports both full and base-only inference. Experiments across multiple simulation benchmarks demonstrate improved manipulation performance and robustness to camera-viewpoint and robot-initialization perturbations. Full and base-only inference achieve average success rates of 88.1% and 85.7% on LIBERO-Plus, respectively. In real-world evaluations, base-only inference raises the average success rates from π0.5π_{0.5}'s 28.3% to 58.3% across three tasks under spatial distribution shifts.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-19 22:16 · 最新观测版本

One View, One Action: Spatially Generalizable VLAs through Observation-Aligned Experts and Cross Graph Consistency

Multi-view vision-language-action (VLA) models still face challenges in spatial generalization, particularly under changes in camera viewpoints and robot initial states. These models typically receive action supervision only in the robot base frame, requiring them to implicitly learn the spatial correspondence between observations from each view and base-frame actions. We propose One View, One Action (OVOA-VLA), which learns to predict actions in each view's camera frame, allowing the same physical motion to provide diverse, observation-aligned supervision across views. OVOA-VLA jointly trains a base-frame expert and view-specific action experts, whose robot-state inputs and action targets are expressed in their respective camera frames. Two complementary directed attention graphs model both directions of interaction between the base and view-specific experts, jointly leveraging view-specific action supervision to improve base-frame prediction. Cross Graph Consistency further encourages agreement between the two graphs' base-frame predictions for the same sample. With the same multi-view inputs, the model supports both full and base-only inference. Experiments across multiple simulation benchmarks demonstrate improved manipulation performance and robustness to camera-viewpoint and robot-initialization perturbations. Full and base-only inference achieve average success rates of 88.1% and 85.7% on LIBERO-Plus, respectively. In real-world evaluations, base-only inference raises the average success rates from π0.5π_{0.5}'s 28.3% to 58.3% across three tasks under spatial distribution shifts.

查看此版本解读 →查看此版本原文 ↗