cs.RONov 18, 2026

Towards Pose-Robust Few-Shot Vision-Language-Action Models

Authors: Wenhao Li, Zhongyi Han, Yuhao Wei, Liang Han, Yilong Yin, Liqiang Nie

Organizations: School of Software, Shandong University, Jinan 250101, China · Shenzhen Loop Area Institute, Shenzhen 518038, China · School of Life Science and Technology, Xidian University, Xi’an 710126, China · School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), 518055, China

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: https://peacelwh.github.io/WACO/.

Figures & tables

Explore similar work

CardsList
  1. From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model

    Jul 6, 2026Wenhao Li, Xueying Jiang, Quanhao Qian +4Language-Conditioned Robot ManipulationHand-Eye Calibration

  2. WARP-VLA: Wrist-Camera Adaptation for View-Robust Policy Execution in Vision-Language-Action Models

    Oct 8, 2026Junmyeong Lee, Dongmin Shin, Min-Gyu Park +3Robustness of VLA ModelsVision-Language-Action Models

  3. AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models

    Mar 6, 2026Hyeongjun Heo, Seungyeon Woo, Sang Min Kim +4Test-Time Adaptation of VLA ModelsRobustness of VLA Models