外观
论文arXiv 2610.2015714 天前
Atomic-WAM：面向 World Action Models 的执行扎根原子运动推理
Atomic-WAM用原子运动描述连接任务推理与动作生成，并在RoboLab real-to-sim评估中验证默认和模糊指令任务。
Franka FR3原文链接：Atomic-WAM: Execution-Grounded Atomic-Motion Reasoning for World Action Models（arXiv 2610.20157 · 发布日期：2026-10-14）
Atomic-WAM: Execution-Grounded Atomic-Motion Reasoning for World Action Models
Atomic-WAM用原子运动描述连接任务推理与动作生成，并在RoboLab real-to-sim评估中验证默认和模糊指令任务。
核心要点
- 任务级指令可能未充分指定下一步物理交互，需要语义扎根和依状态选择运动。
- 视觉语言推理器根据指令和视觉上下文描述局部运动，引导WAM预测视频与动作片段。
- 自动标注流程从多视角DROID演示中整理时间对齐、富含接触的监督信号。
- 在RoboLab real-to-sim评估中，默认指令成功率39.6%，模糊指令成功率31.6%；项目页已给出。
验证范围与局限：验证范围为RoboLab上的real-to-sim评估，包含默认指令和模糊指令任务。
英文摘要 (Abstract)
World Action Models (WAMs) typically adapt video foundation models to robotic control through joint video and action prediction. However, task-level instructions may leave the next physical interaction underspecified, requiring semantic grounding and state-dependent motion selection. To this end, we introduce Atomic-WAM, an understand-then-execute framework that connects task reasoning to action generation through atomic-motion descriptions. Specifically, a vision-language reasoner describes the next local motion from the task instruction and visual context, guiding a WAM to predict future video and an action chunk. Furthermore, an automatic annotation pipeline curates temporally aligned, contact-enriched supervision from multi-view DROID demonstrations. To make atomic-motion predictions executable by the WAM, we post-train the reasoner with Execution-Grounded GRPO (EG-GRPO). With the WAM fixed, EG-GRPO adapts the reasoner through rewards for motion appropriateness and execution success. Finally, Atomic-WAM achieves 39.6% task success under default instructions and 31.6% under vague instructions in a real-to-sim evaluation on RoboLab. Project page: https://ssj9596.github.io/Atomic-WAM-project
作者：Shijun Shi, Zhe Liu, Zhi Hou, Yinan Chen, Tao Zhang, Kai Hu, Yong Liu, Jiangning Zhang
来源
本页事实对应的公开页面，以原文为准。