让机器人在新环境中复用关键空间位置，实现高精度、高频动作生成。
OpenSPM: An Environment-Transferable Robotic Key Spatial Pose Memory and Closed-Loop High-Frequency Flow-Matching Action Generation Model
- 构建可迁移的物体中心空间记忆，结合语义指令检索与SE(3)变换适配新场景。
- 在10个LIBERO-GOAL任务上达85.6%成功率，控制频率高达1033.3 Hz。
- 适合需要快速适应新环境的机器人操作任务，尤其适用于算力受限场景。
开放环境下的桌面机器人操作需具备语义理解、精确几何位姿估计及高频动作生成能力。尽管端到端视觉-语言-动作（VLA）模型在语义泛化方面表现优异，但往往缺乏细粒度任务的显式几何约束，且训练成本高昂。为弥合高层语义与底层物理执行之间的差距，我们提出OpenSPM——一个包含空间位姿记忆与流匹配动作生成模型的开放环境空间持久记忆框架。OpenSPM首先利用语义条件化的3D感知与卡尔曼滤波跟踪连续6D位姿；随后从人类示范中提取关键空间位姿，作为可迁移的、以物体为中心的空间持久记忆条目。推理时，系统根据自然语言指令检索相关记忆条目，通过SE(3)变换将空间位姿迁移到新场景，并采用轻量级条件流匹配模型生成高频动作片段。结合实时本体感觉状态反馈与终端残差校正，有效抑制轨迹误差累积。在10个LIBERO-GOAL任务上的评估显示，OpenSPM达到85.6%的成功率，等效控制频率为1033.3 Hz，且仅需极少的推理计算资源。大量消融实验表明，结构化的空间持久记忆与闭环残差校正对可靠、高频的机器人操作至关重要。
原文摘要 · Abstract (English)
Open-environment tabletop robotic manipulation requires systems to possess semantic understanding, precise geometric pose estimation, and high-frequency action generation. While end-to-end vision-language-action (VLA) models excel at semantic generalization, they often lack explicit geometric constraints for fine-grained tasks and require costly training. To bridge the gap between high-level semantics and low-level physical execution, we propose OpenSPM, an open environment spatial persistent memory framework consisting of spatial pose memory and flow-matching action generation model. OpenSPM first leverages semantically conditioned 3D perception and Kalman filtering to track continuous 6D poses. It then extracts key spatial poses from human demonstrations, keeping them as transferable, object-centric spatial persistent memory entries. During inference, OpenSPM retrieves relevant memory entries in terms of natural language instructions, transfers the spatial poses to new scenes using SE(3) transformations, and generates high-frequency action chunks via a lightweight conditional flow-matching model. Combined with real-time proprioceptive state feedback and terminal residual correction, the system effectively suppresses trajectory error accumulation. Evaluated on ten LIBERO-GOAL tasks, OpenSPM achieves an 85.6% success rate and an equivalent control frequency of 1033.3 Hz, while requiring minimal inference AI computing power. Extensive ablations illustrate that structured spatial persistent memory and closed-loop residual correction play a crucial role in reliable, high-frequency robotic manipulation.
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。