More than a year ago, we released DYNA1, “the first robot foundation model built for round-the-clock, high-throughput dexterous autonomy.” Looking back at the DYNA1 videos now, it’s funny how we thought of it as “high-throughput dexterous” back then. With DYNA1, we showed for the first time that a robot foundation model could be robust enough for true 24/7 automation. But it still wasn’t enough to fully meet customer needs — customers care about throughput, and they care about quality of outcome too (they even want us to remove napkins with stains on them...) It’s hard, and some people may see napkin folding as a “small” use case. But we thought it was important to go through the full deployment cycle to figure out what the real research problems in robotics are. Through the DTF deployment, we explored large-scale pretraining, RL, data-collection hardware, and a lot more. So here it is: a real “round-the-clock, high-throughput dexterous autonomy” system that creates value for customers. If you care about solving the real problems in robotics, join us!

to me, showing scaling laws in robot performance with human-hand data is one of the most important problems to solve in robotics. beyond the common narrative that human-hand data is the most abundant data source compared with teleop and umi-style data, there are two more reasons people often miss: - human-hand data is one of the few types of data that is forward-compatible. the promise of little to no data-to-deployment gap with teleop and umi will disappear once your end effectors change. - human-hand data collection is also the least intrusive way to gather physical data without hurting labor productivity. adding any device to human hands will only slow down dexterity and reduce precision. this cannot be emphasized enough if the goal is to reach human-level performance. DYNA2 takes a stab at this challenging but rewarding problem. huge props to Dyna team for pulling this off! if you look closely, you will also find previews of other exciting work happening at Dyna!