Physical Intelligence 发布 π0.7 机器人模型
π0.7 handles diverse prompts that don't just say what to do, but also how to do it, including rich language and multimodal information, such as visual subgoal i
AI 导读
Physical Intelligence 发布最新机器人模型 π0.7，可处理不仅说明做什么、还说明怎么做的多样提示词，包括丰富语言和视觉子目标图像等多模态信息，测试时这些图像可由轻量级世界模型生成。该模型展现出涌现的组合泛化能力，能把已学技能按提示词以新方式组合，例如学会用空气炸锅烤红薯；还能在没有该机器人洗衣折叠数据的情况下，控制新机器人 UR5e 折叠 T 恤。团队表示仍在探索 π0.7 的能力，更多细节见其博客、视频和完整研究论文。
正文
当前显示原文，中文全文译文尚未就绪。
π0.7 handles diverse prompts that don't just say what to do, but also how to do it, including rich language and multimodal information, such as visual subgoal images. At test time, these images can be produced by a lightweight world model. https://t.co/cbdovdVjBG