arXiv cs.AI· Wenhao Li, Zhongyi Han, Yuhao Wei, Liang Han, Yilong Yin, Liqiang Nie·· 10 小时前AI 评分34
WACO:面向姿态鲁棒的少样本视觉-语言-动作模型的世界锚定规范化框架
Towards Pose-Robust Few-Shot Vision-Language-Action Models
AI 导读
WACO 是一个面向 VLA 模型的世界锚定规范化框架,可在无真值外参、无额外数据的情况下,从单帧 RGB-D 图像估计相机与机器人基座的位移,并将图像、状态、动作与起始位姿规范化到标定视角与基座坐标系。
正文 · 原文
Abstract:Fine-tuning a vision-language-action (VLA) model on a few dozen demonstrations is the standard way to put a manipulation policy on a robot, yet the resulting policy silently assumes that the camera and the robot base stay exactly where they were during data collection: a bumped tripod or a base re-docked a few centimetres away makes it reach for the wrong place. We show that both failures are one phenomenon, a change of the camera-to-base extrinsic that the policy has memorised, and that the robot carries everything needed to undo it. We introduce WACO, a world-anchored canonicalization framework for VLA models: the arm, placed by forward kinematics at the measured joint angles, serves as a metric calibration target, and the static scene serves as the world anchor that tells a moved camera from a moved robot. From a single RGB-D frame, WACO estimates both shifts without ground-truth extrinsics or extra data, canonicalises the image to the calibration viewpoint and the state, action and start pose to the calibration base frame, and fine-tunes the unmodified policy under the artefacts of its own estimator. We also introduce LIBERO-PoseShift, the first benchmark for RGB VLAs with graded camera, base and compound shifts. Across LIBERO-PoseShift, the LIBERO-Plus camera track and four real-world tasks on a UR5e robot, WACO consistently outperforms the standard few-shot recipe and prior viewpoint-robust methods, raising shifted success by 13.2 points in simulation and by 36.7 points on the real robot, recovering 90% of the simulation gap to a ground-truth oracle and 87% of the real-robot gap, and establishing a new state of the art among methods that use no perturbed training data, with no test-time calibration. Project page: this https URL.
| Comments: | 17 pages, 13 figures, 17 tables (including supplementary material). Project page: this https URL |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2611.24360 [cs.RO] |
| (or arXiv:2611.24360v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2611.24360 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wenhao Li [view email]
[v1]
Wed, 18 Nov 2026 12:54:16 UTC (8,623 KB)
来源:arXiv cs.AI · arxiv.org