
Here’s a more personal breakdown of how we built Dyna-2.1 - the first Physical Agent to achieve 1-hour-long, dexterous whole-body autonomy. A lot of the system came down to a few fairly fundamental design choices.

Founding Researcher @DynaRobotics | ex Cruise& @Waymo | CoRL Best Paper

Here’s a more personal breakdown of how we built Dyna-2.1 - the first Physical Agent to achieve 1-hour-long, dexterous whole-body autonomy. A lot of the system came down to a few fairly fundamental design choices.

Managed to make it out of Austin after CoRL on my second attempt Saturday night! Lots of roboticists got stuck 😅 Silver lining is I got to hang out a bit more with one of my favorites @ChenTessler, who also got stuck Anyways, here is my ranking of the best demos I saw at the conference 🥇Taku from @DynaRobotics This was easily the conference favorite. It was such a clean demo, it just worked, and it worked so well it was easy to imagine it being deployed in the real world! No gimmicks, no tricks, they just let it run. Props to the team, they’re still killing it.

and the last time I attended (2022
1300+ CORL attendees rsvp'd for our happy hour.. the conference just 2 years ago was under 1100 attendees. Best time to build in robotics is today :)

u know it’s impressive when everyone is filming your bot
Long horizon mobile manipulation will always be the coolest thing you can do; probably the most impressive demo at CoRL


Heading to Austin for CORL! Come hang out at @DynaRobotics booth for some fun stuff ;) Please reach out if you want to chat about robots and potential opportunities! Also giving talks at the Self-Improving Robots and Efficient Foundation Model workshops! Hope to see you there!

I’m bringing Taku to @corl_conf to zero-shot some tasks. Come to Griffin Hall on the second floor of @JWMarriott to see Taku in person!

(I’m on them too

the future of robot learning might be dangerously dependent on the safety of a handful of flights from SFO to Austin today.

You know the most interesting conversations happen outside the conference walls. In Austin for CoRL? Join the Dyna crew and some of the brightest minds in robotics for an evening of food, drinks, and great conversations. Space is limited, so grab your spot! 🗓️ Wednesday, Nov 11 · 6–9 PM CST RSVP: luma.com/3du99deo

Spotted on the job by a hotel guest 👀 Our robots take towel duty seriously. If you spot them too, tag us! 📹: travelreligiously on Instagram instagram.com/p/DfMBo6yu-bV/

robotics needs its mac moment, then its iPhone moment, before we can talk about its GPT-3 moment.
10 Spicy Takes After Talking to 50 Friends at the Frontier of Robotics 🤖🔥 1/ Astra IS robotics' GPT-3 moment. Ironically, now that it's finally here, some in robotics seem reluctant to acknowledge it. Perhaps because it (sadly) didn't come from a robotics company? 2/ Robotics is becoming just another vertical for frontier labs. Not so different from coding in some respects. Why reinvent general intelligence for every industry? 3/ Robotics was too hard to underwrite until now. No convincing pretraining scaling law, no convergence on models, data, or hardware. No wonder some critics dismissed it as a fragmented industry playing an expensive "demo game". Astra may finally offer a credible path to scale. 4/ Robotics foundation-model startups have a case. But how strong is it? The argument: Astra handles System 2 (reasoning), while specialized models retain System 1 (skills) and System 0 (motor control). Fair. But isn't that already a narrower value proposition? And who says the boundary stops there? 5/ Follow the talent. Word is OpenAI reorganized its 30–40-person robotics team around the core Astra model. Hearing similar moves toward general models at @Tesla_Optimus. Org charts may tell us more than any demo. 6/ The robotics data gold rush is real. Million-hour procurement programs, some potentially reaching tens of millions of hours. Talk of budgets approaching $1B per frontier lab. 7/ Bullish on robotics hardware volumes. As intelligence becomes more accessible, the barriers to building useful robots could fall dramatically. The moat shifts toward reliability, dexterity, integration, and deployment. 8/ Robotics could fuel the next semiconductor and memory supercycle. A 100B-parameter model running on the edge requires ~50GB just for 4-bit weights. Now multiply that by millions of robots. Why do you think @JensenHuang is so obsessed with robotics? @elonmusk saw it coming: x.com/elonmusk/status/211477… 9/ Is self-driving immune to the general-model threat? After coding and robotics, why assume self-driving remains the exclusive domain of proprietary, vertical models? Robotaxi increasingly feels like a solved problem to me. But if and when frontier labs move into self-driving, we could see an Apple vs. Android dynamic. Think about the implications for $TSLA, Waymo, and other OEMs. 10/ The next bottleneck may not be intelligence. It's deployment. Models are improving faster than our ability to deploy robots in the messy real world. Integration, hardware variance, failure recovery, and economics remain brutally hard. The real moat may be turning intelligence into reliable, profitable physical work. -- I realize some of these takes may rub people the wrong way, especially those who have spent years doing the hard work of advancing robotics. That's not my intention. I'm sharing them to spark debate, not to declare winners and losers. Astra has only been out for a month or so, and it's far too early to draw definitive conclusions. More importantly, when the TAM is this enormous - potentially the largest in tech - there should be plenty of room for different approaches and many winners. ++ Full diligence report: robonomics.substack.com/p/ro…

A friend at Dyna once told me his career goal is to put 100 million robots into the world. I think that sums up why many of us are here: an ambitious vision, backed by a grounded understanding of what it takes to get there. Robotics is a complex systems problem. No matter how much you know, there's always another part of the stack you don't. What I love about Dyna is being surrounded by people who are masters of their own craft, and getting to learn from them every day. Building useful robots takes much more than a great model. It takes the full stack, and a team that knows how to bring it all together. If this sounds like the kind of challenge you'd love to work on, come join us!
Taku takes its name from Takumi, a master craftsman. Behind it is a team united by a love for what they do and a relentless pursuit of excellence. Meet the people and the craftsmanship behind robots built to last. Come build with us: dyna.co/careers

Taku takes its name from Takumi, a master craftsman. Behind it is a team united by a love for what they do and a relentless pursuit of excellence. Meet the people and the craftsmanship behind robots built to last. Come build with us: dyna.co/careers

Had a lot of fun briefly visiting @JasonMa2020 at @DynaRobotics on the way back to the airport. Super impressed and got to meet Taku (it works! Its real!)

the confidence & trust it takes to have these many people surrounding your robot
The first AI robot to ring the bell on Nasdaq