The Robot Report Podcast
00:55:17 · Scott Kuindersma, Eugene Demetri
And then you go all the way down to probably the bottom of the pyramids like YouTube. So it's like very unstructured video of people doing things and it's just a harder thing probably to leverage into real concrete improvements in robot behavior. But it'll probably be part of the story. So from our perspective, we're thinking about that whole set of things. And I think, you know, so is many other groups. And I think everyone's sort of taking different bets on the relative proportions that they're expecting to be part of the right answer, and they're investing resources in different parts of that pyramid. So you see people with like giant factories filled with teleoperators, and then some groups with like relatively modest tele operations, but a lot of investment around egocentric data collector simulation or things like this. [00:56:10] S3: And you mentioned before that obviously, Toyota Research Institute as a partner has been helping with that. Can you talk about that ongoing relationship for a moment? Isn't it something that you're expecting to continue?
00:56:10 · Eugene Demetri, Scott Kuindersma
[00:56:10] S3: And you mentioned before that obviously, Toyota Research Institute as a partner has been helping with that. Can you talk about that ongoing relationship for a moment? Isn't it something that you're expecting to continue? [00:56:21] S4: Yeah, for sure. Yeah, we're continuing to work together. I think us working with them has been just so much fun. They're an awesome team. I think we are very similar in terms of our outlook and what we think is important. The structure of how we've been working together is, we have a special space in our building that's kind of just like a research lab, and there's research scientists from TRI who are mixed in with our own research scientists in there, and they all kind of just work as one big team. We'll get some Atlas robots in there. So it's been really great, and I'm looking forward to continuing to work with [00:56:56] S3: And are you also working with the AI robotics institute as well?
00:56:56 · Eugene Demetri, Scott Kuindersma
[00:56:56] S3: And are you also working with the AI robotics institute as well? [00:57:00] S4: Yeah, for sure. So, yeah, that's kind of our sister organization, if you'd like to call it that. Yeah, so one of... There's many ways in which we work together. I think one of the most visible ones is our collaboration on reinforcement learning. So, that's another project that actually exists in the same physical space. So, we have people from the Robotics and AI Institute who are hanging out with us in the lab, and then we have a bunch of our own research scientists who are working with them. And so the results that we showed earlier in the year with the robot doing cartwheels and break dancing and things like that was actually a result from that collaboration. So the way I think about TRI collaboration is more focused on the LBM style manipulation research. And then the other project that we have that's a similar mechanically as that is the... With Ray is the reinforcement learning project. [00:57:54] S3: I may be able to answer this, but I know that Hyundai has been talking about testing Atlas as well. What's going on with that right now? [00:58:04] S4: Yeah. So that's something we're super excited about. Obviously, one of the big... You know, Hyundai is likely to be our our biggest, most important first customer as as they announced. And so we're really excited about Atlas doing work in their facilities. So we're planning on taking Atlas to some Hyundai facilities this year, and I'm sure we'll tell everyone about it when we're ready.
00:58:04 · Scott Kuindersma, Steve Crowe
[00:58:04] S4: Yeah. So that's something we're super excited about. Obviously, one of the big... You know, Hyundai is likely to be our our biggest, most important first customer as as they announced. And so we're really excited about Atlas doing work in their facilities. So we're planning on taking Atlas to some Hyundai facilities this year, and I'm sure we'll tell everyone about it when we're ready. [00:58:27] S0: That's awesome. Can't wait for that. They must be... I know they're... They just made a couple massive announcements about manufacturing back here in The States and how much robotics will be a part of that. They sound like a great partner. Just to wrap things up, I know you've obviously seen the evolution of Atlas in your time at Boston Dynamics. You've seen the evolution of these new training techniques. What's next for Atlas? What can we see besides the Hyundai trials? And how excited are all of you guys about where this is all headed? [00:58:56] S4: Yeah, I mean, we're very excited. I think you're gonna see more and more AI centric results from us. I think we're really committed to trying to break through the ceiling for humanoid manipulation. So I think you should look forward to more exciting things, both on the manipulation front as well as on the very on brand dynamic behavior front.
00:58:56 · Scott Kuindersma, Steve Crowe, Mike Oitzman
[00:58:56] S4: Yeah, I mean, we're very excited. I think you're gonna see more and more AI centric results from us. I think we're really committed to trying to break through the ceiling for humanoid manipulation. So I think you should look forward to more exciting things, both on the manipulation front as well as on the very on brand dynamic behavior front. [00:59:23] S0: Awesome. Well, we look forward to all of it and let us know anytime we can report on all this stuff as we love to see what's going on with Atlas. So Scott Kuindersma, VP of robotics research at Boston Dynamics. Thank you so much for being here, man. Thank you. Yeah. Just just fascinating stuff. I will say, I haven't received a call yet to to be the guy behind the camera, Mike, with the hockey stick that's messing with Atlas. Volunteered for that position because that just seems fun, you know, being able to... I wonder if they... And I should have asked this, like, they have parameters for that person? Like, here are things that you can do to mess with Atlas. Here are things that you can do to mess with Atlas because it's not able to recover uncertain things. I should have asked about that. And I also should have asked about... I don't if you remember at at the robotics summit earlier this year, we had former Boston Dynamics CTO, Aaron Saunders. He opened the show talking about Atlas and and all sorts of things that they're doing. But they talked about... And they showed some videos of people wearing those motion capture suits. Yep. [01:00:26] S1: Right.
01:00:26 · Steve Crowe
[01:00:26] S0: And how they can translate those behaviors and movements onto the Atlas humanoid without, a ton of tweaking that's needed at the end. And Scott talked a little bit about that for data collection, but I think there's so much more going on in that space that we should continue to unpack. I think it's just fascinating. Like Scott said, they're not 100% sure why large behaviour models work so well. It's sort of like that black box effect that is often talked about with artificial intelligence. But it's just amazing how, you know, there's a quote that Scott had and it's in the blog that Boston Dynamics posted about this, just about how much easier it's becoming to teach robots how to do things and how to manipulate objects. Like they're saying, you don't need PhD level education to do this stuff anymore. Yeah. Which is crazy. And they actually believe that. So if that is true and it continues to advance, you know, like we've always talked about, in order for robotics to scale, they need to be easier to build, easier to use, easier to train. And, you know, maybe this is the start of it. Obviously a long way to go, which they'll tell you right off the bat, but it's just very, very exciting times for humanoids, but really robot learning in general. I think, this is some cool stuff. And again, you know, I know we mentioned the Robotics Summit twenty twenty six. It's coming up, very far away, May twenty seventh and twenty eighth in Boston. This is our flagship show. But, Russ Tedrake of Toyota Research Institute, he's leading all the research that they're doing on Large Behavior Models. We've already confirmed him for a keynote at the Robotics Summit this spring. So he said that they'll have new results of what they're doing with Large Behavior Models and testing by then that they're going to be excited to share with the robotics world. So, I know Robo Business is still a month away and we're full steam ahead for that show, Mike, but we're already planning for the Robotics Summit twenty twenty six in Boston. And pretty thrilled to have Russ Tedrake of TRI as one of our keynote speakers. I think he joined us a couple years ago on an AI panel that you led. Right?