Physical Intelligence 提出 MEM 多尺度具身记忆系统
With MEM, our model can carry out real, multi-stage tasks in the real world, like cleaning up an entire kitchen or setting up the ingredients for a recipe. The
AI 导读
Physical Intelligence 开发了 Multi-Scale Embodied Memory（MEM）记忆系统，为模型同时提供短期视觉记忆和长期语义记忆。短期记忆用高效视频编码器记住近期交互的细节，长期记忆则让模型用文本总结事件，最长可记住 15 分钟的内容。该记忆系统让机器人能完成清理整个厨房、按食谱备料等多阶段真实任务，并展现出从过去错误中即时调整行为的上下文适应迹象。
正文
当前显示原文，中文全文译文尚未就绪。
With MEM, our model can carry out real, multi-stage tasks in the real world, like cleaning up an entire kitchen or setting up the ingredients for a recipe. The videos show how the robot keeps track of long-horizon memory in text. https://t.co/ihCbtDUst5