Tag
Neocambrian AI 推出 Mitts 触觉手套,可捕捉高精度触觉与动作数据,帮助机器人感知接触位置与压力,从而学习与物理世界交互。
The article discusses a method for building self-learning agents by combining agent traces with in-browser user activity, using the AG-UI protocol to capture and apply learnings, enabling products to improve through usage and create a business moat.
The author has built and extended a multimodal data capture rig for Physical AI training, featuring synchronized RGB, depth, 3D hand reconstruction, and tactile pressure data, and has deployed it globally.