让机器人记住世界和自身状态，解决视觉盲区与任务遗忘问题
AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models
- 用双记忆架构持久记录环境与自身状态
- 在真实长任务中成功率提升17.5%
- 仅用单手摄像头就能实现顶尖表现
尽管视觉-语言-动作（VLA）模型推动了具身智能发展，但其固有的反应式范式在部分可观测和长时序任务中严重受限。当仅依赖手腕摄像头时，物体离开视野会导致感知遗忘，多步执行中也会出现任务进度遗忘。为此，我们提出AtlasVLA，一种从直接反应式操作转向主动推理的新框架，通过持续的全局世界-自我状态建模克服瓶颈。该框架采用双记忆结构：4D持续世界状态记忆将瞬时2D观测提升为全局更新的体素哈希空间状态，解决视觉盲区；自我的工作状态记忆则追踪历史自我状态与任务进展。通过将扩散Transformer（DiT）基于此联合世界-自我状态进行条件化，实现了鲁棒的空间推理。在LIBERO、RLBench及真实世界基准上的广泛评估表明，AtlasVLA仅使用手腕摄像头即达到当前最佳性能。显著优于多视角基线，在LIBERO-Long上成功率达9.4%绝对提升，在真实世界长任务中提升17.5%。
原文摘要 · Abstract (English)
While Vision-Language-Action (VLA) models have advanced embodied AI, their fundamentally reactive paradigm severely limits performance in partially observable and long-horizon tasks. When restricted to a single wrist-mounted camera, they inevitably suffer from perception forgetting as objects exit the field of view, and temporal task-progress forgetting} during multi-step execution. To overcome these bottlenecks, we propose AtlasVLA, a novel framework that transitions from direct reactive manipulation to proactive reasoning through a persistent world-ego state. AtlasVLA features a dual-memory architecture: a 4D Persistent World State Memory that lifts transient 2D observations into a globally updated, voxel-hashed spatial state to resolve visual blind spots, and an Ego-Working State Memory that tracks historical ego state and task progress. By conditioning a diffusion transformer (DiT) on this joint World-Ego state, AtlasVLA enables robust spatial reasoning. Extensive evaluations across LIBERO, RLBench, and real-world benchmarks demonstrate that AtlasVLA achieves state-of-the-art performance using solely a wrist camera. Remarkably, it decisively outperforms multi-view baselines, yielding absolute success rate improvements of 9.4% on LIBERO-Long and 17.5% in real-world long-horizon tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。