Video action models are data efficient and allow robots to learn complex dexterous tasks. Learn more in our episode with @elvisnavah of @mimicrobotics ->
First look at our collaboration with @AudiOfficial on bringing AI-driven robotics into industrial production.
Our end-to-end pixel-to-action model, running on our bi-manual platform, is capable of performing a complex, dexterous and long-horizon insertion task.
Today, we’re excited to announce our $16M seed funding round, accelerating our mission to deploy frontier physical AI across industries.
Led by @Elaia_Partners alongside @speedinvest, with participation from Founderful, 1st Kind, 10x Founders, 2100 Ventures, Sequoia Scout Fund.
@GoogleDeepMind I wonder, as these models become smarter, that we'll see the user (ourselves) becoming an escalated bottleneck. We often need to able to interpret the reply to make use of it. E.g. the proof in the video has little value if no human can understand or validate it.
Introducing Streaming Diffusion Policy (SDP)!
SDP allows you to generate actions using a single denoising step, with no distillation!
SDP keeps an action buffer of partially denoised future actions, which is refined over time.
https://t.co/AsaBZJaSBS
Led by @sigmundhh
@julianibarz I think so, too! We explored this in our paper on TEDi Policy (https://t.co/5BFrpdbAz1) We implement this for a control policy and show that it increases the control frequency drastically while performing well