发表机构
Stanford University（斯坦福大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对VLA策略在信息缺失时失效的问题，提出显式概念记忆ECoMEM，分离记忆维护与行动学习，在16个任务中15个领先，真实任务成功率86.1%，提供可复用可扩展的记忆接口。
AI 中文摘要
机器人可能会丢失其稍后必须取回的物体的视线，需要回忆某人先前演示的内容，或跟踪任务中已完成的步骤。当前的视觉-语言-动作（VLA）策略通常在行动所需的信息从当前观察中消失后失效，这使得记忆对于长时程机器人行为至关重要。现有方法通常提供更长的历史记录或从观察-动作轨迹中学习隐式记忆。但动作监督告诉策略如何行动，而非记住什么：它未指定哪些过去的事实应持续存在，或随着新证据的出现它们应如何变化。因此，我们将维护基于证据的过去记录与学习如何据此行动分开。这一见解促成了显式概念记忆（ECoMEM），它使用可复用的基于证据的概念库来表示任务相关的历史。一个基于证据的写入器选择并更新这些记录，而一个学习的读取器将它们转化为直接调节VLA的记忆标记。在16个RoboMME任务中，ECoMEM在15个任务上领先于所评估的机器人策略。在两个新的真实机器人任务上，相同的记忆库要么直接迁移，要么仅需一个新概念，实现了86.1%的成功率，而无记忆VLA的成功率为8.6%。这些结果表明，显式概念为机器人控制提供了可复用且可扩展的记忆接口。项目网站：此https URL
英文摘要
A robot may lose sight of an object it must later retrieve, need to recall what a person demonstrated earlier, or track which steps of a task it has already completed. Current vision-language-action (VLA) policies often fail once the information needed for action disappears from the current observation, making memory critical for long-horizon robot behavior. Existing approaches typically provide longer histories or learn implicit memory from observation-action trajectories. But action supervision tells a policy how to act, not what to remember: it does not specify which past facts should persist or how they should change as new evidence arrives. We therefore separate maintaining an evidence-grounded account of the past from learning how to act on it. This insight motivates Explicit Concept Memory (ECoMEM), which represents task-relevant history with a reusable library of grounded concepts. An evidence-based Writer selects and updates these records, while a learned Reader turns them into memory tokens that directly condition the VLA. Across 16 RoboMME tasks, ECoMEM leads the evaluated robot policies on 15 tasks. On two new real-robot tasks, the same memory library either transfers directly or requires only one new concept, achieving 86.1% success versus 8.6% for a no-memory VLA. These results show that explicit concepts provide a reusable and extensible memory interface for robot control. Project website: https://ecomem.github.io/
CommentsProject website: https://ecomem.github.io/
