ActiveVLA：将主动感知注入视觉-语言-动作模型以实现精确三维机器人操作
ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation
把主动视角选择与三维区域放大引入 VLA 策略，为视觉研究者提供了一个可复用的思路：在精细操作中动态挑选最优视角与分辨率，而不是依赖固定的腕部相机；其多视图投影定位关键三维区域的做法也可迁移到其他需要空间聚焦的视觉任务。
原文依据 ActiveVLA uses an active view selection strategy to choose optimal viewpoints
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期机器人操作领域的进展借助预训练视觉-语言模型（VLM），并探索将三维空间信号融入这些模型以实现有效的动作预测，从而催生了颇具前景的视觉-语言-动作（VLA）范式。然而，现有大多数方法忽视了主动感知的重要性：它们通常依赖静态的腕部相机，提供以末端执行器为中心的视角。因此，这些模型无法在执行任务过程中自适应地选择最优视角或分辨率，这显著限制了它们在长时程任务和细粒度操作场景中的表现。为解决这些局限，我们提出 ActiveVLA，一种新颖的视觉-语言-动作框架，赋予机器人主动感知能力，以实现高精度、细粒度的操作。ActiveVLA 采用由粗到细的范式，将过程划分为两个阶段：（1）关键区域定位。ActiveVLA 将三维输入投影到多视图二维投影上，识别关键三维区域，并支持动态空间感知。（2）主动感知优化。基于定位到的关键区域，ActiveVLA 使用主动视角选择策略来挑选最优视角。这些视角旨在最大化非模态相关性与多样性，同时最小化遮挡。此外，ActiveVLA 应用三维放大以提升关键区域的分辨率。这些步骤共同实现了更细粒度的主动感知，以支持精确操作。大量实验表明，ActiveVLA 实现了精确的三维操作，并在三个仿真基准上优于最优基线。此外，ActiveVLA 可无缝迁移到真实场景，使机器人能够在复杂环境中学习高精度任务。
英文原文摘要 1817 字符
Recent advances in robot manipulation have leveraged pre-trained vision-language models (VLMs) and explored integrating 3D spatial signals into these models for effective action prediction, giving rise to the promising vision-language-action (VLA) paradigm. However, most existing approaches overlook the importance of active perception: they typically rely on static, wrist-mounted cameras that provide an end-effector-centric viewpoint. As a result, these models are unable to adaptively select optimal viewpoints or resolutions during task execution, which significantly limits their performance in long-horizon tasks and fine-grained manipulation scenarios. To address these limitations, we propose ActiveVLA, a novel vision-language-action framework that empowers robots with active perception capabilities for high-precision, fine-grained manipulation. ActiveVLA adopts a coarse-to-fine paradigm, dividing the process into two stages:(1) Critical region localization. ActiveVLA projects 3D inputs onto multi-view 2D projections, identifies critical 3D regions, and supports dynamic spatial awareness.(2) Active perception optimization. Drawing on the localized critical regions, ActiveVLA uses an active view selection strategy to choose optimal viewpoints. These viewpoints aim to maximize amodal relevance and diversity while minimizing occlusions. Additionally, ActiveVLA applies a 3D zoom-in to improve resolution in key areas. Together, these steps enable finer-grained active perception for precise manipulation.Extensive experiments demonstrate that ActiveVLA achieves precise 3D manipulation and outperforms state-of-the-art baselines on three simulation benchmarks. Moreover, ActiveVLA transfers seamlessly to real-world scenarios, enabling robots to learn high-precision tasks in complex environments.