Verne Robotics 开源世界动作模型 V0.5
Verne Robotics 放出了开源世界动作模型 V0.5，机器人换个房间、光照一变也不太掉性能，比 Physical Intelligence 的 π0.5 稳不少，学新任务只要 2 小时演示。
Verne Robotics 发布开源权重世界动作模型 V0.5，通过摄像头输入输出下一秒的机械臂、夹爪和移动底盘动作。模型基于 Wan2.2 视频生成器，用超过 170 万条演示数据训练，能同时预测未来相机画面和对应运动。在 RoboTwin 2.0 基准上，面对随机杂物、光照和纹理变化，V0.5 的成功率从 81.0% 降到 73.4%，而 Physical Intelligence 的 π0.5 从 70.7% 降到 46.0%。新工业任务只需不到 2 小时的演示数据即可学会。
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.
https://t.co/BaTwYMcNsj
https://t.co/8WKzZHXJIw
