StreamingWAM：基于分块阶梯流匹配的流世界动作模型
StreamingWAM: Streaming World Action Modeling via Chunk-Wise Staircase Flow Matching
AI总结：
针对现有WAM机器人控制方法未同时解决推理效率与动作连续性的问题，提出StreamingWAM流扩散框架，在多机器人任务上提升动作连续性，降低重规划延迟并减少对执行 horizon K 的敏感性。
摘要：
世界动作模型（WAMs）通常构建于预训练的视频生成世界模型之上，已成为通用型、开放式机器人控制的有前景框架。然而，其在现实世界部署中常出现执行不连续、动作生硬的问题。现有方法通常仅通过提升推理效率或增强预测分块间的动作连续性来解决该问题，未同时应对这两大挑战。为填补这一空白，我们提出StreamingWAM，一种用于基于WAM的机器人控制的流扩散框架。StreamingWAM结合了用于分块动作预测的噪声阶梯、用于跨分块连续性的前缀回滚模块，以及用于时间一致性条件的密集视频历史记忆。在LIBERO、LIBERO-Plus、RoboTwin 2.0及现实世界机器人任务上的实验表明，StreamingWAM在静态和动态场景下均提升了动作连续性，实现了有竞争力的性能，同时将稳态重规划延迟降至仿真中的72.9毫秒、现实机器人中的57.3毫秒。该方法还产生更平滑的动作过渡，而流阶梯降低了对执行 horizon K 的敏感性。
英文摘要：
World Action Models (WAMs), often built upon pretrained video-generation world models, have emerged as a promising framework for general-purpose and open-ended robot control. However, their real-world deployment often suffers from discontinuous and jerky execution. Existing methods typically address this issue by either improving inference efficiency or enhancing action continuity across prediction chunks, without jointly addressing both challenges. To bridge this gap, we propose StreamingWAM, a streaming-diffusion framework for WAM-based robot control. StreamingWAM combines a noise ladder for chunk-wise action prediction, a prefix rollout module for cross-chunk continuity, and dense video-history memory for temporally consistent conditioning. Experiments on LIBERO, LIBERO-Plus, RoboTwin 2.0, and real-world robotic tasks demonstrate that StreamingWAM improves action continuity across static and dynamic settings, achieving competitive performance while reducing steady-state replanning latency to 72.9 ms in simulation and 57.3 ms on the real robot. The method also produces smoother action transitions, while the streaming staircase reduces sensitivity to the execution horizon K.
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。
