PosA-VLA: 通过姿态条件化锚点注意力增强动作生成
PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention
AI总结：
PosA-VLA通过姿态条件化锚点注意力机制提升动作生成的精度和效率，适用于多样化的机器人任务和复杂环境。
摘要：
视觉-语言-动作（VLA）模型在具身任务中展现了显著的性能，并展示了在现实应用中的巨大潜力。然而，当前的VLA仍然难以产生一致且精确的目标导向动作，因为它们常常在轨迹上生成冗余或不稳定的运动，限制了它们在时间敏感场景中的应用。在本工作中，我们将这些冗余动作归因于现有VLA的空间均匀感知场，这导致它们被目标无关的物体所干扰，尤其是在复杂环境中。为了解决这个问题，我们提出了一个高效的PosA-VLA框架，通过姿态条件化监督来锚定视觉注意力，一致地引导模型的感知向任务相关区域。姿态条件化锚点注意力机制使模型能够更好地对齐指令语义与可操作的视觉线索，从而提高动作生成的精度和效率。此外，我们的框架采用轻量级架构，并不需要辅助感知模块（如分割或接地网络），确保了高效的推理。广泛的实验验证了我们的方法在多样化的机器人操作基准上能够以精确且时间高效的行为执行具身任务，并在各种具有挑战性的环境中表现出稳健的泛化能力。
英文摘要：
The Vision-Language-Action (VLA) models have demonstrated remarkable performance on embodied tasks and shown promising potential for real-world applications. However, current VLAs still struggle to produce consistent and precise target-oriented actions, as they often generate redundant or unstable motions along trajectories, limiting their applicability in time-sensitive scenarios.In this work, we attribute these redundant actions to the spatially uniform perception field of existing VLAs, which causes them to be distracted by target-irrelevant objects, especially in complex environments.To address this issue, we propose an efficient PosA-VLA framework that anchors visual attention via pose-conditioned supervision, consistently guiding the model's perception toward task-relevant regions. The pose-conditioned anchor attention mechanism enables the model to better align instruction semantics with actionable visual cues, thereby improving action generation precision and efficiency. Moreover, our framework adopts a lightweight architecture and requires no auxiliary perception modules (e.g., segmentation or grounding networks), ensuring efficient inference. Extensive experiments verify that our method executes embodied tasks with precise and time-efficient behavior across diverse robotic manipulation benchmarks and shows robust generalization in a variety of challenging environments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
