aifollow.news
Back Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · Original publication time AI score47

Verne Robotics makes V0.5 weights and inference code available for industrial robotsMachine translation

AI introduction

Verne Robotics’ V0.5 predicts the next second of arm, gripper and mobile-base motion from camera views; its weights and inference code are available. A cited account says it learned new industrial tasks from under two hours of demonstrations. In Verne’s RoboTwin 2.0 tests, randomized clutter, lighting and textures reduced its success rate from 81.0% to 73.4%.

Original post · AI translation

@rohanpaul_ai
Translation · refer to the original

你可以在这里使用 V0.5:https://t.co/oUr1uES98r

技术报告: https://t.co/aostNJjbkU

权重和模型可在 Huggingface 上获取: https://t.co/TKLDmETK7q

模型和推理代码:https://t.co/HJGT575x12

ReplyRohan Paul@rohanpaul_ai
Translation
@VerneRobotics 的发布令人赞叹 V0.5 是一个开放权重的世界动作模型,通过摄像头观察,并输出机械臂、夹爪和移动底座接下来 1 秒的运动。 重大之处在于,它仅用不到 2 小时的演示就学会了新的工业任务。 > 房间环境变化时,机器人模型通常会表现不佳。在两款模型训练时都未见过的杂物和新光照条件下,Verne Robotics 的 V0.5 在仿真中的表现下降了 7.6 个百分点,而 Physical Intelligence 的 π0.5 下降了 24.7 个百分点。 > 在 RoboTwin 2.0 上,Verne 的测试显示,随机变化的杂物、光照和纹理使 V0.5 的成绩从 81.0% 降至 73.4%,而 Physical Intelligence 的 π0.5 从 70.7% 降至 46.0%。 > V0.5 基于 Wan2.2 视频生成器构建,通过超过 170 万次演示学习预测接下来的摄像头画面及产生这些画面的动作。 https://t.co/BaTwYMcNsj https://t.co/8WKzZHXJIw
Original

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

View this post on X ↗
Related contextVerne@VerneRobotics
Translation
隆重推出 V0.5:Verne 面向工业机器人的开放权重世界动作模型。 我们相信,推动机器人技术普及的起点,是让所有人都能使用前沿基础模型。 要让机器人进入每个行业,需要许多团队基于众多工作流程中共享的进展开展建设。 V0.5 是在 LIBERO 和 RoboTwin 2.0 基准测试中表现领先的美国制造开放权重模型。 我们希望你能加入我们,一起让 V0.5 投入实际应用。
Original

Introducing V0.5, Verne’s open-weight world action model for industrial robots. We believe democratizing robotics starts with making frontier foundation models open to everyone. Bringing robots to every industry will take many teams, building on shared progress across many workflows. V0.5 is the leading US-made open-weight model on LIBERO and RoboTwin 2.0 benchmarks. We hope you’ll join us in putting V0.5 to work.

View this post on X ↗

Source: Rohan Paul · x.com

Model
Found an error? Send a correction