② 正式实验：抓贝果，加 / 不加 focus（每组 20 次）

起始状态（腕部相机 / 肩上相机 / 对面相机）。成功在线判定，并要求两次独立重放复现。两组任务说明相同，都要求每次下发动作带一段说明（只为诊断）：

**Every `r.submit(...)` must carry a `note`** (the call is refused without one): one short paragraph on what this motion is for, the numbers it is based on, what you expect to happen, and how you will check it afterwards.

加 focus 组多出的一段（原文）：

## Focus tool (required)
`r.focus(center, radius, note)` returns the triangle mesh of the surfaces your cameras see in the **current** frame within `radius` m (at most 0.15) of `center` ([x, y, z] m, env-local world frame), with the robot's own body removed: `{"vertices": (N,3) m, "faces": (M,3), "path": PLY file, "meta": per-camera counts}`. It is built only from the current depth and camera calibration (the same data as `r.get_obs(depth=True)`); surfaces no camera sees are absent. `note` is required: what this focus is on and what you want to learn from it.
**Before every gripper close you must call `r.focus(...)` on the region the fingers will touch**, and base the approach and the close on that mesh.

focus 工具的精度见 ① 工具精度。