av自拍

Human hands are essential for sensing and interacting with the physical world, enabling us to manipulate objects with ease. Replicating this level of dexterity in robots remains a longstanding challenge, and a key milestone toward general-purpose robotics in unstructured environments. While modern AI has made remarkable advances in vision and language, robotic dexterity remains unsolved due to the complexity of high-dimensional control, limited real-world data, and the need for rich multisensory feedback. In this talk, I present the atomic skill approach to robotic dexterity - a framework that decomposes complex manipulation tasks into reusable, generalizable low-level skills. I will show how these atomic skills can be learned in simulation and composed through high-level policies to perform sophisticated behaviors, with examples including in-hand reorientation, thread fastening, and coordinated humanoid manipulation.