跳到正文
𝕏 Rohan Paul(x.com)·· 13 天前精選品質評分78
重點導讀

Apple 的新論文提出 AMP1,讓通用 AI 模型根據相機畫面、執行程式並直接傳送機械手臂動作指令,在迴圈中操作物體,無須示範資料或任務訓練。

  • RoboLab-120:AMP1 零樣本成功率為 85.6%,高於最佳 VLA 的 49.2% 與最佳 world-action model 的 42.9%。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

推薦理由

AMP1 以相機畫面、程式執行與直接動作指令控制機械手臂,並在 RoboLab-120 與實機試驗中呈現零樣本操作表現,可對照專用策略的基準。

Rohan Paul
Rohan Paul@rohanpaul_ai
·13 天前
𝕏

New Apple paper shows that a general-purpose AI model like Claude Opus 5.5, given camera views and direct control of a robot arm, handled objects more reliably than robot models trained on recorded demonstrations.

New Apple paper shows that a frontier AI model directly controlling a robot arm beats specialist robot policies, with no demonstrations or task training.

Most robot manipulation work trains specialist policies, like vision-language-action models, on demonstrations, and they break easily when instructions change.

Their harness, AMP1, gives a model like Claude Opus 5.5 or Gemini 4 Argon camera views, code execution, and direct motion commands in a loop. It has no built-in grasping or placing skills, so the model invents its own strategies.

On RoboLab-120, AMP1 succeeded in 85.6% of episodes zero-shot, against 49.2% for the best VLA and 42.9% for the best world-action model. On a real Franka arm it succeeded in 104 of 108 trials, though the robot waits much of each episode for the model.

推文來源 · X (Twitter)在 X 參與討論

讀者討論

理性交流 · 即時討論