The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection

• URL: http://arxiv.org/abs/2607.02322v1
• Date: Thu, 02 Jul 2026 15:30:26 GMT
• Title: The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection
• Abstract summary: Vision-Language-Action (VLA) models have shown remarkable promise in generalized robotic manipulation.<n>We propose a data-centric solution to enhance VLA spatial generalization.
• Score: 5.416023813050294
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language-Action (VLA) models have shown remarkable promise in generalized robotic manipulation. However, their spatial generalization remains fragile. We argue that simply increasing the number of viewpoints is insufficient. Models often fall into the trap of Shortcut Learning, latching onto spurious correlations (e.g., fixed relative poses between objects or between the camera and robot base) rather than learning true spatial relationships. In this work, we propose a data-centric solution to enhance VLA spatial generalization. We utilize a dual-arm setup where one arm performs manipulation while the other serves as a mobile environmental camera. We systematically evaluate three data distribution patterns: Fixed, Multi-Fixed, and Moving Views. Our findings reveal that a hybrid strategy, combining continuous camera motion with diverse static viewpoints, yields the best performance by substantially reducing spurious correlations while maintaining training stability. Our experiments demonstrate that this strategy mitigates spurious correlations, enabling VLAs to generalize to unseen camera poses and object configurations where simply adding more static viewpoints fails. Crucially, we reveal that the susceptibility to shortcut learning and the struggle with spatial generalization are universal characteristics shared across diverse architectures. Consequently, all evaluated models (ACT, Diffusion, and VLA models including Pi0 and Gr00t) benefit significantly from our mixed data strategy.

Related papers

• LAWM-3D: Learning 3D-Aware Latent Actions from Human Videos for Generalizable Robot World Models [64.11117186468533]
  World models enable agents to perform forward rollout and planning without real-world interaction.<n>Most existing LAMs rely on single-view inputs and operate primarily in 2D pixel space.<n>We propose LAWM-3D, which introduces three tightly coupled key designs for learning 3D-aware latent actions.
  arXiv  Detail & Related papers  (2026-08-06T07:47:01Z)
• Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation [52.61098793949261]
  We introduce Pose6DAug, a failure-driven data augmentation framework.<n>We turn a policy's successful episodes into targeted demonstrations for its failure modes.<n>Our method operates directly in 3D, anchoring the target object with an explicit mesh driven by a temporally coherent 6D pose trajectory.
  arXiv  Detail & Related papers  (2026-06-18T11:41:25Z)
• SG-VLA: Learning Spatially-Grounded Vision-Language-Action Models for Mobile Manipulation [43.77409401429281]
  Vision-Language-Action (VLA) models show promise for robotic control, yet performance in complex household environments remains sub-optimal.<n>Mobile manipulation requires reasoning about global scene layout, fine-grained geometry, and high-dimensional continuous actions.<n>We introduce a framework for learning spatially-grounded VLA models that strengthens perception and representation.
  arXiv  Detail & Related papers  (2026-03-24T03:44:25Z)
• Universal Pose Pretraining for Generalizable Vision-Language-Action Policies [83.39008378156647]
  Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency.<n>We propose Pose-VLA, a decoupled paradigm that separates VLA training into a pre-training phase for extracting universal 3D spatial priors.<n>Our framework follows a two-stage pre-training pipeline, establishing fundamental spatial grounding via poses followed by motion alignment.
  arXiv  Detail & Related papers  (2026-02-23T11:00:08Z)
• Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization [65.37179698521766]
  Vision-Language-Action (VLA) models show strong promise for generalist robot control.<n>It remains unclear whether -- and under what conditions -- the standard "scale data" recipe translates to robotics.<n>We present a systematic, controlled study of VLA scaling that revisits core training choices for pretraining across diverse robots.
  arXiv  Detail & Related papers  (2026-02-10T12:25:43Z)
• Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer [40.778996326009185]
  We present the first visual localization framework that performs multi-view spatial integration through an early-fusion mechanism.<n>Our framework is built upon the VGGT backbone, which encodes multi-view 3D geometry.<n>We propose a novel sparse mask attention strategy that reduces computational cost by avoiding the quadratic complexity of global attention.
  arXiv  Detail & Related papers  (2025-12-26T06:12:17Z)
• HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies [83.41714103649751]
  Development of embodied intelligence models depends on access to high-quality robot demonstration data.<n>We present HiMoE-VLA, a novel vision-language-action framework tailored to handle diverse robotic data with heterogeneity.<n>HiMoE-VLA demonstrates a consistent performance boost over existing VLA baselines, achieving higher accuracy and robust generalizations.
  arXiv  Detail & Related papers  (2025-12-05T13:21:05Z)
• Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy [47.51062818231493]
  We introduce the Observation-Centric VLA (OC-VLA) framework, which grounds action predictions directly in the camera observation space.<n>OC-VLA transforms end-effector poses from the robot base coordinate system into the camera coordinate system.<n>This strategy substantially improves model resilience to camera viewpoint variations.
  arXiv  Detail & Related papers  (2025-08-18T17:10:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.