PNP机器人按：Science Robotics发表了由谷歌 DeepMind Robotics 团队牵头，并通过与 Intrinsic 以及伦敦大学学院的多年合作，引入了一种专门的人工智能模型，旨在正面解决一项尚未解决的多机器人运动规划难题。

机器人操控一直是机器人技术领域的核心挑战。从工厂中的机械臂到家庭服务机器人，如何让机器人灵活、精细且智能地完成各种操作任务，是研究者们数十年来努力的方向。传统的操控方法往往需要工程师精心设计控制规则，或者让机器人反复观看人类演示进行模仿学习。但这些方 ...

几名孩子坐在教室里，面对一个白色的机器人，深吸一口气，开始朗读手中的故事书。他们的声音起初有些颤抖，但逐渐变得平稳、流畅。这并非某段短视频Vlog的拍摄现场，也不是什么AI教育广告的摆拍，而是一场严肃科学实验的真实记录。但朗读只是开始。接下来的几分钟 ...

But guide dogs have limitations. Although it may not be obvious to the casual dog lover, these animals can cause headaches ...

接下来，RoboBallet使用图神经网络（GNN）作为策略网络，通过权重共享来处理不断变化的图大小。其以观测图作为输入，并在每个时间步为所有机器人生成指令关节速度。这使得机械臂能够在只接收原始状态作为输入的情况下，进行关系和组合推理。

Developed by the Beijing Innovation Center of Humanoid Robotics, Tien Kung drew attention after claiming victory in the world ...

Automated ‘third hand’ for surgeons hailed as helping in routine tasks like retracting tissues, picking up gauze and clipping ...

Kumar says those types of scenarios partly inspired the idea of the triple backflip. Engineers can control each individual ...

Hundreds of humanoids from 16 countries stumbled over each other while competing in the World Humanoid Robot Games in Beijing ...

For many children, the transition from learning to read to reading to learn is a crucial and sometimes nervewracking ...

For one day only this September, the general public will have free admission to Science World as part of its Tech-Up ...

Social companion robots are no longer just science fiction. For example, after a children's reading robot became inactive, most households chose to keep it.