TAG, you’re it.
What if controlling a robot didn’t just mean seeing, but actually feeling what it feels?
Most teleoperation today is vision-heavy and that is exactly why dexterous manipulation still breaks.
Teaching robots to perform dexterous manipulation tasks currently requires teleoperation, which limits demonstration quality, speed, and scalability. Instead, why not use human videos? The problem is that a human hand isn’t a robot hand, so data must be retargeted using simulation to resolve issues like collisions and interpenetration when controlling the hand.
In VideoManip, @chen_hongyi_ and co-authors built a system to solve this problem, taking in RGB videos of humans performing manipulation tasks and using them to create accurate simulations with which to learn robot policies.
Watch episode #73 of RoboPapers, hosted by @micoolcho and @chris_j_paxton, now to learn more!
Deja de decirle a Claude “haz esto”.
Deja de decirle a Claude “escribe código”.
Deja de decirle a Claude “corrige este error”.
En realidad estás tratando a una IA avanzada como a un becario junior.
Aquí tienes 8 prompts que puedes copiar y pegar directamente:
We are also releasing self-contained lecture notes that explain flow matching and diffusion models from scratch. This goes from "zero" to the state-of-the-art in modern Generative AI.
📖 Read the notes here: https://t.co/RULWDgn9pm
Joint work with @EErives40101.