Physical Intelligence 发布机器人模型 π0.7，展现组合泛化能力
Our newest model, π0.7, has some interesting emergent capabilities: it can control a new robot to fold shirts for which we had no shirt folding data, figure out
AI 导读
Physical Intelligence 发布最新机器人模型 π0.7，展现出多项涌现能力：能控制新机器人 UR5e 折叠 T 恤，尽管此前没有该机器人的衣物折叠数据；还能通过语言指导学会使用家电，并在单一模型中完成多种灵巧任务。该模型具备组合泛化能力，可根据提示词以新方式组合已学技能，例如用空气炸锅烤红薯。π0.7 可处理包含丰富语言和多模态信息（如视觉子目标图像）的提示，这些图像在测试时可由轻量级世界模型生成。
正文
当前显示原文，中文全文译文尚未就绪。
Our newest model, π0.7, has some interesting emergent capabilities: it can control a new robot to fold shirts for which we had no shirt folding data, figure out how to use an appliance with language-based coaching, and perform a wide range of dexterous tasks all in one model! https://t.co/s9NxKfb7pe