原子运动坐标：用于语言可引导与力响应操作
Atomic Motion Coordinate for Language-Steerable and Force-Responsive Manipulation
AI总结：
提出原子运动坐标，通过几何坐标和力响应调制，实现语言引导的机器人操作，显著提升干预分离度和真实任务成功率。
AI中文摘要：
仅改变语言指令能否重定向VLA策略的末端执行器，还是视觉驱动的运动先验占主导？我们提出原子运动坐标（Atomic Motion Coordinate），一种基于几何的坐标，用于可引导和力响应的操作。每个机械臂拥有十三个带符号的平移、旋转和保持原子，这些原子从文本和前向运动学中提取，且不依赖视觉；该坐标通过加权码本对齐注入到每个动作专家模块中。接触历史通过一个有界的球面残差调制同一坐标，该残差从固定名义潜变量重新计算，仅再生未执行的水平线后缀。在7,520次离线水平线干预中，相反原子分离度达到92.5/83.1%（单/双臂），而LA4VLA风格仅为39.1/24.0%。在每个任务50次真实机器人试验中，AMC将OOD水果进度从60.5%提升至87.8%；力适应将插头/花瓶任务从59.0/71.5%提升至78.5/75.2%。
英文摘要：
Can changing only the language instruction redirect a VLA policy's end effector, or does the visually driven motion prior dominate? We present Atomic Motion Coordinate, a geometry-grounded coordinate for steerable and force-responsive manipulation. Each arm owns thirteen signed translation, rotation, and hold atoms grounded from text and forward kinematics with vision withheld, and the coordinate is injected into every action-expert block via weighted codebook alignment. Contact history modulates the same coordinate through a bounded spherical residual that is recomputed from a fixed nominal latent to regenerate only the unexecuted horizon suffix. Across 7,520 offline horizon interventions, opposite-atom separation reaches 92.5/83.1% (single/dual) versus 39.1/24.0% for LA4VLA-style. Across 50 real-robot trials per task, AMC raises OOD fruit progress from 60.5% to 87.8%; force adaptation raises Plug/Vase from 59.0/71.5% to 78.5/75.2%.
