Emerson S
@Em_Nomadic
Physical AI & Robotics◽️Growth & GTM Engineer @tnkrdotai ◽️Head of GTM @DiracRobotics ◽️GTM @Hyphenbox
7.5K Following 5.3K Followers
The amount of egocentric data being collected is exploding. Making all of that footage actually useful for robot learning is where things get really interesting.
Really interesting approach from Asimov. Instead of asking the policy to compensate for hardware inconsistencies, they focused on making the hardware itself more deterministic and predictable.
Feels like an underrated part of closing the Sim2Real gap.
Show more
The more robot data we collect, the more important it becomes to know what is actually inside it.
Which action happened at which time? Where did the robot fail? What happened immediately before the failure? Did it recover? When did the task move into another stage?
Raw video contains all of this information, but structured annotations are what make it easier to actually work with.
Show more
The robotics companies that win won’t just have the best demos. They’ll have the strongest deployment loop.
Skild AI: first commercial deployment → 60+ paying customers → $100M ARR in 10 months.
Every deployment creates new problems to solve and new knowledge to feed back into the system.
Show more
This feels like a genuine GPT-3 moment for robotics.
S1 can observe one video of a human completing a task it has never seen before, then carry out that long-horizon workflow without task-specific fine-tuning or post-training.
Moving from “collect data, train, and deploy” toward “show the robot once and let it act” would fundamentally change how quickly robots can adapt to new work.
Incredible progress from the @SkildAI team.
Show more
