Verne Robotics 發布開放權重世界動作模型 V0.5,可從攝影機畫面預測接下來 1 秒的機械手臂、夾爪與移動底座動作。
- - 任務學習:模型可透過不到 2 小時的示範學習新的工業任務。
- 訓練資料超過 1.7M 筆示範。
AI 伴隨問答
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:
V0.5 在 RoboTwin 2.0 的測試顯示,面對未訓練過的雜亂與光線變化,表現降幅小於 π0.5,可供評估模型在環境變動下的穩定性。
Brilliant release by @VerneRobotics
V0.5, an open-weight world action model, that looks through cameras and outputs the next second of arm, gripper and mobile-base motion.
The big deal is that it learned new industrial tasks from under 2 hours of demonstrations.
> Robot models usually stumble when a room changes. With clutter and new lighting that neither model trained on, Verne Robotics’ V0.5 lost 7.6 points in simulation, while Physical Intelligence’s π0.5 lost 24.7.
> On RoboTwin 2.0, randomized clutter, lighting and textures cut V0.5 from 81.0% to 73.4% in Verne’s tests, while Physical Intelligence’s π0.5 fell from 70.7% to 46.0%.
> Built on the Wan2.2 video generator, V0.5 learned from over 1.7M demonstrations to predict upcoming camera frames alongside the motion producing them.