重新思考机器人操作中记忆状态的演进：以对象为中心的视角
Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective
AI总结：
本文提出Embodied-SlotSSM框架，用于解决机器人操作中非马尔可夫推理问题，通过槽位状态空间建模和关系编码器实现时间可扩展的视觉-语言-动作推理。
摘要：
随着具身智能体在日益复杂的环境中运行，能够感知、跟踪并在时间上推断单个物体实例的能力变得至关重要，尤其是在需要与视觉相似物体进行序列交互的任务中。在这些非马尔可夫设置中，关键决策线索往往隐藏在物体特定的历史中，而不是当前场景。没有对先前交互的持久记忆（已交互的物体、其位置或其变化方式），视觉-运动政策可能会失败，重复过去的行为或忽略已完成的行为。为了揭示这一挑战，我们引入了LIBERO-Mem，一个非马尔可夫任务集，用于在物体层面部分可观测的情况下测试机器人操作。它结合了短和长视界物体跟踪与时间序列子目标，要求在当前帧之外进行推理。然而，视觉-语言-动作（VLA）模型在这种设置中往往表现不佳，即使对于仅跨越几百帧的任务，标记扩展也很快变得不可行。我们提出了Embodied-SlotSSM，一种基于槽位的VLA框架，旨在实现时间可扩展性。它维护空间-时间一致的槽位身份，并通过两种机制利用它们：（1）槽位状态空间建模用于重建短期历史，以及（2）一个关系编码器将输入标记与动作解码对齐。这些组件共同使时间感知、上下文感知的动作预测成为可能。实验显示，Embodied-SlotSSM在LIBERO-Mem和一般任务上的基线性能，提供了一种适用于对象中心机器人策略中非马尔可夫推理的可扩展解决方案。
英文摘要：
As embodied agents operate in increasingly complex environments, the ability to perceive, track, and reason about individual object instances over time becomes essential, especially in tasks requiring sequenced interactions with visually similar objects. In these non-Markovian settings, key decision cues are often hidden in object-specific histories rather than the current scene. Without persistent memory of prior interactions (what has been interacted with, where it has been, or how it has changed) visuomotor policies may fail, repeat past actions, or overlook completed ones. To surface this challenge, we introduce LIBERO-Mem, a non-Markovian task suite for stress-testing robotic manipulation under object-level partial observability. It combines short- and long-horizon object tracking with temporally sequenced subgoals, requiring reasoning beyond the current frame. However, vision-language-action (VLA) models often struggle in such settings, with token scaling quickly becoming intractable even for tasks spanning just a few hundred frames. We propose Embodied-SlotSSM, a slot-centric VLA framework built for temporal scalability. It maintains spatio-temporally consistent slot identities and leverages them through two mechanisms: (1) slot-state-space modeling for reconstructing short-term history, and (2) a relational encoder to align the input tokens with action decoding. Together, these components enable temporally grounded, context-aware action prediction. Experiments show Embodied-SlotSSM's baseline performance on LIBERO-Mem and general tasks, offering a scalable solution for non-Markovian reasoning in object-centric robotic policies.
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。
