Colin Angle on Why Home Robots Failed Before and Why AI Changes Everything

Transcript

[00:00:00] Colin Angle: In the land of robotics, what AI has done is allowed us to do things that we could only dream of. Now we're in a world where those things we could only imagine 10 years ago suddenly aren't just possible -- they're practical. What a cool moment in time to be a roboticist. Necessity is the mother of invention, and we hooked onto the AI bus at the right time, and the AI bus has only accelerated, not slowed down.

Building robots is really hard, so we have to be more than just a watch-me toy. What we're announcing is our first step in delivering a different kind of robot. This is the greatest application of robots that in my entire career I could imagine. I just couldn't build it until, honestly, six months ago.

[00:00:49] Brian Heater: The generations of attempts at home robots and home pets didn't last. And people do have expectations about what robots can and can't do in the home. So how are you really going to express to people that this is something different?

[00:01:05] Colin Angle: Well, I think that...

[00:01:18] Brian Heater: Hello and welcome to another episode of Automated. My name is Brian Heater. I am the managing editor at the Association for Advancing Automation. I am here to bring you our first ever returning guest. As a matter of fact, it's only been, I think, a month or two since the last time we had Colin Angle on the show.

Although this time we are chatting about happier circumstances than recent iRobot news. Colin is back in the CEO role at a brand new company, Familiar Machines & Magic. He walks us through the decision to get back in the saddle and explains why this shot at home robotics is different than all of the others that came before it.

We also dig into the early days of iRobot and entertain my obsession with the company's My Real Baby doll. If you're enjoying the show, don't forget to like and subscribe, and please check out the newsletter over at Automated.fm. And with all of that, please enjoy this conversation with Colin Angle.

[00:02:16] Brian Heater: We talk a lot about what's coming up next in automation on the show, but if you really wanna see the future in motion, you've got to be there in person.

Automate 2026 is where the world's leading innovators, builders, and dreamers come together to show you what's possible. Robots, AI, machine vision, motion control -- you name it. All automation under one roof. And as part of Automate this year, the Humanoid Robot Forum brings together leaders, engineers, and researchers for a two-day deep dive into the real-world development, deployment, and commercialization of humanoid robotics.

Register for free at automateshow.com to join us in Chicago, June 22nd through the 25th. We will see you there.

Was retirement ever an option?

[00:03:03] Colin Angle: How could you retire when the tools to create the coolest robots that we have ever seen were suddenly available? I guess I thought about it, but then rejected it swiftly.

[00:03:20] Brian Heater: So let's break that down a bit. When you say suddenly available, I assume to a certain extent you're probably talking about LLMs, these sort of breakthroughs that we've been seeing in AI, some of the hardware breakthroughs.

[00:03:37] Colin Angle: Well, for a long time the challenge of building a robot was situational awareness. For a long time there's been speech recognition that could understand what you said, but robots had a really hard time understanding enough context to translate an understanding of "go to the kitchen and get me a beer" into going to your kitchen, opening your refrigerator, and actually bringing you back a beer, or whatever it was.

And so the power of what AI has brought to the robot industry actually is more profound in many ways than what it's done to the chat world. Because we can understand our environment, we can control higher-degree-of-freedom systems in a dynamic and graceful way. We can then take all that and start overlaying personality to what we're doing.

It's like, it's not that we used to be able to do spreadsheets -- it just took forever and you had to be really good at math, and then suddenly spreadsheets made it fast and accessible. In the land of robotics, what AI has done is allowed us to do things that we could only dream of. There was no solution that was clunky but serviceable.

Now we're in a world where those things we could only imagine 10 years ago suddenly aren't just possible -- they're practical to do. So what a cool moment in time to be a roboticist.

[00:05:28] Brian Heater: If I'm reading between the lines here, it sounds like you're talking a bit about the difference between hard-coding a robot and using machine learning. Is that fair?

[00:05:37] Colin Angle: Yeah, but at different levels. Sort of at the lowest level: making a walking robot walk used to be incredibly hard. Now that's table stakes. And the question is how much dexterity and how much speed can you get out of those legs? How much expressiveness? But what about facial expression?

What about manipulation? What about full-body animation? Things that, as you add more and more degrees of freedom to your robot, get dramatically harder and harder using traditional techniques. But reinforcement learning suddenly allows you to train motion policies that are stylish and dynamic and amazing -- and that's just the low-level stuff.

Then you add to that this idea that I can take audio and video streams coming in and translate them into a rich understanding of the environment that I'm operating in. Well, we couldn't do that particularly well two years ago, we couldn't a year and a half ago. And that's all changing really quickly.

And then the ability to reason on that context -- and not just reason on it from an intellectual perspective, but add an emotional perspective about what we're seeing. It is cool. It's a new toolkit of awesomeness that is unlocking the potential of -- you know, even the word "robot" doesn't make sense anymore, because at least in my mind, robot is associated with dull, dirty, dangerous tasks.

And what we're really opening up is something much broader than what traditionally robots were thought to be able to do. So using this new term, physical AI, is something that I think is a great term because it's more expansive in scope.

[00:07:45] Brian Heater: Obviously you and I have talked many, many times over the years, and we talked a lot during your time at iRobot. Towards the end, it strikes me that you were laying the foundation, or at least attempting to lay the foundation for this. So much of the work that you were doing in your last several years came down to mapping the home. I know that you had those sort of early partnerships with Amazon and Alexa, so it was voice, it was smart home.

It seemed to me that you were sort of pulling together potentially the pieces, or maybe the infrastructure. But now you're describing these breakthroughs that have happened in the last two years. I'm wondering how much of it you would've had to have just sort of scrapped and started from scratch anyway.

[00:08:38] Colin Angle: I mean, the ideas translate over. This idea, when you're creating a robot that is designed to live in a home -- the iRobot journey brought with it just an appreciation of how important the relationship between the Roomba and the Roomba's owner was in actually having a positive experience.

How do you keep Roomba out of the closet? What does it take for people, four years later, to be using the Roomba multiple times a week as opposed to once a week, then once every other week, and then it's, "oh yeah, I've got one of those." The trajectory of engagement was some of the really interesting work we did towards the later years of iRobot.

We had limited tools, but it came down to finding a way for the Roomba to be part of the family's routine. By far the largest failure mode of Roomba to clean your home was user-cancel: someone turning it off because it tried to vacuum the living room while someone was watching television.

So they just reached down and unthinkingly turned it off because it was annoying, and it never got turned on again.

[00:10:06] Brian Heater: See, I thought you were gonna say poop.

[00:10:08] Colin Angle: Well, that --

[00:10:09] Brian Heater: That's number two.

[00:10:11] Colin Angle: So to speak. Poop was actually much more solvable than getting into your routine. I mean, that was a big, big deal, because it didn't happen very often, but when it happened, boy, that was bad. Computer vision actually worked really well in solving that problem. But understanding a home environment -- well, that's a less easily tractable challenge.

[00:10:39] Brian Heater: So as you mentioned before we got on, I dug up a very old screenshot of you, and it was from a very old video of you. It's interesting to me, in light of the conversation that we are currently having and in light of the news that you're just about to announce -- by far and away, the most interesting thing about the early days of iRobot is this kind of bifurcation in the projects that the team was doing.

So much of the funding was coming from DARPA, so there were a lot of these sort of military-based robots, search-and-rescue, things like that. And then at the same time, you were going after the home. Obviously Roomba is the big one that everybody knows. And then the other one that makes an appearance in here, that I think is maybe in a sense a precursor, is My Real Baby.

[00:11:34] Colin Angle: My Real Baby was actually the culmination of a lot of work we did on "can a robot effectively emote." Back then -- and the body of evidence has only grown -- showing that many interactions on the screen are less impactful than a similar interaction where instead of it being a screen, it's an embodied physical thing. The really cool research into brain MRI scanning -- you look at someone doing a chatbot and their brain activates a teeny tiny bit. Whereas if they're having the same interaction with a physical thing, the brain is lighting up, oxytocin is being emitted, and the impact is greater.

Even in early iRobot days, we were thinking, if you build a robot, it's hard. I mean, building robots is really hard, so we have to be more than just a watch-me toy. We have to be more than something that -- heck, I could put a plate of glass between me and the robot and the interaction wouldn't change. If that's what you're doing, well, just make it a computer program that runs on a screen.

But if there's actually an opportunity to do something physical -- whether that is something as mundane as Roomba and vacuuming the floor, or something that is more physically interactive, where you're actually holding something like My Real Baby and rocking it -- you're going to have a much more powerful experience.

We were trying to figure out how to really create significant value with physical interaction in the early days. But the technology just wasn't there. It was too hard to understand what was going on. We had a few interesting successes, but none of it really scaled.

[00:13:57] Brian Heater: The reason why I stumbled on that video specifically is because on the about page of your new company, you have a small bio and it mentions Genghis. Genghis was a very, very early project that you were doing, and I'd love it if you could really kind of walk me through this connection, because it says that there's a connection there, or that it was maybe an early precursor to Aibo, to Sony's robot dog. What is the link there?

[00:14:29] Colin Angle: Genghis was actually my undergraduate thesis at MIT, and we were thinking about what our robots are good for. At the time, we had conversations around -- I think NASA had talked about its Mars rover program, and at the time the plan was to send something about the size of a Humvee to Mars or the moon, as the next generation of rovers. It needed to be that big because in order to roll over a half-meter boulder, you needed a one-meter tire. And so that set the whole logic behind the scale.

And yet insects are really good at climbing over things that are much bigger than they are. So this idea of walking robots is a really interesting place. At the time -- this is 1989 -- walking robots were research topics that had multimillion-dollar hardware budgets and so forth. And Rodney Brooks, my professor, and I said, let's build a bug. Genghis was a six-legged walking robot using hobby servos to control the legs, and a very simple set of behaviors -- at least computationally simple -- that interacted with one another to allow Genghis to walk over very rough terrain.

Genghis indirectly led to the Micro Rover program at NASA, and led to the Sojourner Rover being added to the Mars Pathfinder mission. So it had a really interesting trajectory in space exploration. But we had this group from Sony come in, look at it, and say, "wait, you can do that? Oh, that's interesting." And that led directly to the Sony Aibo dog being created.

That's fascinating and is relevant because when we founded iRobot, the actual first name of iRobot was Artificial Creatures Inc. This idea that we could use the AI that we were creating, way back 35 years ago, to try to build the robots we were promised -- and these were actually sentient creatures that lived alongside us and had interesting reasons to exist and purpose. We did work on facial expression. We did work on My Real Baby to try to figure out how do you make a baby that actually understands how it's being played with.

Ultimately that got put down, and then started to be picked up late in the game as we realized we needed to move from building robot vacuums that sort of operated independent of people, and move toward building robot vacuums that really worked with you in close partnership to understand what you wanted it to do, and knew itself whether it was doing a good job or not.

It was sort of a journey of focus on human connection toward simpler solutions that require less human connection -- you know, turn it on by pushing the button. And then in later years: if this thing is going to take its next step forward, we gotta bring the human connection back into the equation.

[00:18:20] Brian Heater: One of the things you mentioned in that video with regards to My Real Baby is there's a ball inside the robot, which seems to essentially function like a gyroscope. As far as the baby knows that it's being moved, it reacts to that. And obviously these are hardcoded reactions we're talking about -- there are like a set number of reactions that this baby has based on certain ways that you interact with them.

Now, as we're talking about this next step and these things that AI can do, what does it mean for a more complex, more sophisticated robot to actually learn from human behavior?

[00:19:07] Colin Angle: If you're trying to build a machine that is designed for human connection, then somehow you need to teach that machine social norms -- or at least some level of social norms -- so that it knows when it behaves in a certain way that you're going to interpret that behavior in a certain way. And when you do certain things, it should be able to get a sense of what's going on, because it should react in those in an appropriate fashion.

If you try to sort of break the robot AI revolution into three parts: one part is the motion part, which we've talked about already. One part is the perception part -- this idea of taking audio and video streaming information and turning that into, your, someone named John that you live with just came in the door and he looks upset and the room is messy, and there's the following things going on -- and that this tableau of information is then sent to a reasoning model.

The reasoning model has a job of taking that tableau of information coming to it and deciding what to tell the body of the machine -- what should it do? And it's not hard-coded anymore, it's trained. In fact, there are ways of training models now where the way we do it at my new company is we write stories.

We write stories about how we want our familiar -- this is my name for an emotionally sophisticated, emotionally intelligent robot machine that's focused on human connection. So my familiar has a personality that is built from a few dozen stories about how it should react and behave. And then those stories are taken by AI and turned into thousands of stories. And those thousands of stories are used to train models that connect information about what's going on in the world to actual familiar behavior.

[00:21:58] Brian Heater: I bring this up every so often when we're talking in this space. Years ago, I was interviewing the founders of Anki, and remember at the time that they raised a lot of money, and one of the things that they did with that funding was go and hire a bunch of animators from Dreamworks and Pixar.

Looking through some of the staff with Familiar Machines & Magic, there are some Imagineers on there, there are some Disney folks on there. What does it mean to pull people in to do storytelling, and what are those sorts of lessons that you can learn from, like, animation, for example?

[00:22:44] Colin Angle: It might be helpful to take a step back and sort of talk about the company's mission, and then we can get into the tactics. Because the company is this really exciting blend of advances that iRobot made -- and just blowing out of the water the price-performance expectations of what a robot could be. We couple that with a strong dose of Boston Dynamics, which taught us that machines don't have to move like machines, or at least don't have to move like traditional concepts of machines. And then you add a third dimension of Hollywood, and you get a very interesting set of capabilities.

And my stepping back is, why are you doing this? It gets at the fact that this new toolkit that we've talked about is revolutionizing what machines can do. So there's this new name, physical AI, that represents an opportunity for machines to enter our world and create tremendous value -- and expectations of the value that physical AI can bring to the world: $5 trillion over the next 20, 30 years.

Typically the thought process is, okay, we're really talking about humanoids and factories, right? And the answer is, well, yes, but only about half of that $5 trillion represents manufacturing and inspection and warehouse automation types of uses. The other half has to do with machines that interact with people, that are doing things like elder care, that are doing things like providing emotional support, or helping parents get through the day, or providing entertainment, or office security, or finally making the smart home work -- things where these robots are not operating in a lights-out factory on the other side. They're actually creating very useful work in our homes, and we need to figure out how to interact with them.

So, okay, that's a really hard, really interesting problem. And depending on which YouTube videos or X videos you are -- what your favorite channel is -- there's a lot of energy out there sort of showing us humanoids in the home, which certainly could happen eventually. But that's not how it's gonna start. This idea that you're gonna have a humanoid robot in your home pushing an upright vacuum cleaner -- come on, guys. We solved this one already. We don't need a $20,000 humanoid robot pushing an upright vacuum cleaner.

What we do need is maybe a little bit of help in the home to reinforce a healthy routine. It's not so much robot pets, but maybe it's in the same genre of creatures, as opposed to humanoids, that we want to physically interact with -- but that have a little bit more purpose and reliability beyond staying fed and getting the right amount of sleep. Something that could help us get some more exercise. Something that could help reduce isolation by saying, "how about we go for a walk?" Or, "this doom-scrolling thing you've been doing for the last hour and 10 minutes isn't really probably how you want to be spending your time. Why don't you go to bed, and tomorrow make a different decision?"

There's a very interesting entry point, as long as we can solve some important challenges. Does this new familiar look like something that I want with me when I take a walk? Can I trust it? Obviously there's lots of stories in the media about AIs that are overstepping -- plush toys with an AI chip giving dating advice and things like that. And how do I make sure that this isn't something that ends up in a closet, like so many robots, after their initial minutes of glorious "wow, look how cool this thing is"?

At Familiar Machines & Magic, we really tried to take on these challenges head-on and create something that could -- one of my go-tos is, I gotta build a robot that delivers more value than it costs to create.

[00:28:21] Colin Angle: I need to make it delight. I need it to be trustworthy. I need it to deliver long-term engagement. What we're announcing is our first step in delivering a different kind of robot, which we think meets these criteria.

So it is more pet-like in appearance. It's not a dog, it's not a cat -- it's a furry quadruped. Because we want you to pet it. People spend on average an hour and a quarter a day petting their pet. If you could do something like that with a familiar -- oh my God.

You need to trust it. So let's not stream any video or audio to the cloud. Let's do it all on the edge. Let's sort of use Roomba rules: if you wanna connect it to the cloud, you can -- it'll make its memories a little bit better, and it will evolve over time if you do, but you don't have to. And if you do, we'll be very transparent as to what information is being shared.

Let's make it not talk. It'll make sounds, it'll make pet-like noises, so you'll know if it's happy or sad or excited and so forth. But we just take off the table any idea of this thing giving you advice. Because, you think about it, your pet can communicate really, really well, and it doesn't talk.

[00:29:56] Brian Heater: This is that ChatGPT problem that you're getting at before -- people using it as a therapist.

[00:30:01] Colin Angle: Use of human language is not necessary for a wide variety of home applications. And then let's do this all at a similar price point to pet ownership. And suddenly this thing that we're talking about, this familiar, feels kind of cool. Why wouldn't you want this?

[00:30:34] Brian Heater: I wanted to walk through some lessons learned through your time at iRobot, and how that informed this company and the kind of portfolio that you're working on. The first and most obvious one: we've been having this conversation for 20 years of, what's after the robot vacuum, right? By and large for iRobot, the question was, okay, what's the next value prop that we can have? What's the next thing in the home that we can do? Cleaning pools, cleaning gutters, mowing the lawn, for example.

This is a different approach, right? I mean, you're talking about a different -- at least to start with -- a different theory of what constitutes value.

[00:31:31] Colin Angle: Not really. Meaning that, when you go and you look at a product for the home, you're competing for wallet share, right? A family has only so much money it's willing to spend, and it chooses very deliberately how it spends money.

How much do you spend on your cable bill? How much do you spend on your large-screen TV? How much do you spend on vacuuming and mopping? The challenge that iRobot was -- our logical expansions went from vacuuming to mopping, to air purification, to pool cleaning. There were adjacencies, but each of those adjacencies were cast against, what does the average household spend on these different things?

So a robot vacuum is a problem that people do frequently, they dislike doing it, and they spend a lot of money on it. Boom, boom, boom -- you got three wins. Mopping: yeah, people hate doing it so much, they actually don't do it very often, which works against you. And they do it with a mop that they're used to spending $8 on. So buying a robot vacuum -- it's almost price parity versus a really nice regular vacuum. A robot mop versus a manual mop has a huge price discrepancy between those two things, and that's why ultimately an independent Scooba robot failed. But it was a nice add-on to your vacuum.

Now, people spend a lot on pets. There is an epidemic-level crisis on isolation, feelings of isolation and loneliness among adults in the United States, and it's even more severe outside of the United States. In some regions the pet industry is taking off, or growing very rapidly. So there is both need and significant spend around trying to solve challenges of isolation and loneliness, and looking at wellness, and looking at parents saying, "for the love of God, I feel so guilty giving my child an iPad to watch all afternoon long, but I don't have another choice."

There are these very concrete needs that a technology that can now potentially exist -- if it's well executed, if it's appropriately priced, and if it's amazing -- could actually be even more attractive than Roomba, because of the acuteness of the need that many households face.

So this isn't, "gee, Colin, you used to be very pragmatic and now you're doing this weird, soft stuff." This is the greatest application of robots that in my entire career I could imagine. I just couldn't build it until, honestly, six months ago. In fact, the company was started when the technology didn't yet exist to do what we're doing now. But it felt like maybe it did, or maybe it would soon, and we're actually every day growing into a world where building familiars is possible.

[00:35:46] Brian Heater: What does it mean, in those early days, for the company to exist prior to the technology that's really going to unlock it? Obviously it has to sort of exist in a different form than it is right now, where it is product-focused.

[00:36:02] Colin Angle: Well, you have the idea. And, you know, coming out of iRobot, I realized that I shouldn't be afraid of having a lot of degrees of freedom.

[00:36:16] Brian Heater: It's a very roboticist thing of you, Colin.

[00:36:18] Colin Angle: Yeah, yeah, yeah. I mean, that's a totally geeky and nerdy thing to say. But if every motor you add to your robot costs you $2,500 (if you want it to be dynamically controlled), you're going to build a robot with four motors. It's just not going to be very complicated.

But when you start saying, well, maybe it's a couple tens of dollars, suddenly it's like, well, to build a quadruped you need 12 motors -- three for each leg, if you don't want to cheat. And we don't want to cheat. Okay, that's not so bad. We can do that.

And so the company started getting off the ground with this idea of what we wanted to build. And then starting to do the math: could we build this thing that isn't fake -- it's not an illusion, it's real, it is dynamically controlled, it could move in a graceful, lifelike fashion, it could carry enough compute on board to actually run AI models, and have enough budget for stereo sensing and array microphones? You say, wait, that could actually work.

We had confidence -- because my team included some folks who helped set up the logistics and operations that iRobot benefited from -- we started off with a really amazing reality around target for hardware costs that we convinced ourselves was achievable.

And then where I say, gee, it wasn't actually possible until six months ago: what I'm really talking about is, can we put a full-stack AI system, including reinforcement learning, including a behavior engine, including a reasoning engine, including a perceptual engine, and a memory system, on the edge with an embedded solution? The answer was, well, maybe we can on day one of the company, and now we're sitting around having working prototypes of it functioning on the edge. That wasn't actually possible when we started, but is possible today, and will continue to improve as the weeks pass. Meaning the world is changing that rapidly.

[00:39:03] Brian Heater: But there was a sense that, okay, we can't really do this until this thing is unlocked, and you had to anticipate that those things were coming in a certain timeline.

[00:39:13] Colin Angle: Well, we kind of did the official entrepreneur thing, where we benefited from a little bit of wishful thinking. Necessity is the mother of invention, and we sort of hooked onto the AI bus at the right time. The AI bus has only accelerated, not slowed down. So it wasn't that we knew it didn't exist -- we knew that it might exist, and then benefited from progress.

[00:39:49] Brian Heater: So the other iRobot learning that I wanted to talk about -- and I think you were kind of in a roundabout way getting at it -- is the privacy question. Because that is effectively why it's really important to run this thing on edge. That was something that I suspect you kind of had to learn a few times over the years with iRobot, as the sensors were becoming more and more sophisticated on the systems.

[00:40:15] Colin Angle: Right. And you know, the cloud was always promised to be infinite free compute, and yet compute in the cloud is neither free nor infinite. So if you are doing humanoids for industrial settings, the cloud is a great resource. But if you are in the home, just having a solid wifi connection is the exception, not the rule.

So latency is gonna be a problem if you're trying to run a real-time system over the cloud. It's completely unaffordable from the perspective of a consumer, so cost is a problem. And then streaming video and audio up to the cloud is a privacy non-starter -- people don't want that either. So latency, privacy, cost issues all drive you to having to have an edge solution.

[00:41:17] Brian Heater: This is something that I've never asked you, and it's just occurring to me now as we're talking. Throughout your very long time working at iRobot and working on the Roomba, was there ever a conversation, or was it ever pitched to you, to actually give Roomba a voice?

[00:41:39] Colin Angle: Very controversial. We gave it its beeps and boops back at the beginning because there weren't any good affordable speech chips. So making it more R2-D2 was sort of the only option given the tools that we had.

We ultimately gave it a utility voice, to give error messages, so that your Roomba will say, "wifi not connected," or, "please check your rollers, they're clogged." Because doing that by beeping just was a miserable consumer experience. But we kept the use of that voice to be used in a way that it was clear it wasn't Roomba talking to you -- it was something, a maintenance system or something. That made it easier, because people did personify Roomba, but every Roomba owner sort of has a different mental image as to what their Roomba is, and giving it a voice would probably work very rapidly against us. Because you'd start assuming that if you talk to Roomba, well, it'll understand.

And even today, natural conversations that are meant to be coherent and consistent over long periods of time are extraordinarily difficult to do. Even just two, three years ago, it wasn't even close. So it wasn't considered, and I don't think the benefits, even today with today's technology, makes sense for Roomba to have a real personality.

[00:43:43] Brian Heater: One of the sort of big selling points with the familiar is this idea of it adapting over time, adapting to your schedules and your wants and needs. I'm wondering if part of that is the ability to have each one of these develop, in a certain sense, their own individual personality, from one familiar to another.

[00:44:14] Colin Angle: Absolutely. There will be no two familiars that are the same. These are learning and adapting machines, both from working to make sure that everyone looks a little different, to different personalities, to different learnings.

Every familiar has some unique connection between the familiar's owner -- which we call the owner the guardian -- and the familiar itself. So you see the robot in the first seconds, you're like, oh my God, that's the coolest thing I've ever seen. And then within a minute you see that it is behaving in a way that is purposeful, that is illustrative of a behavior. And then our mission: once we get home, what is our role? Where can we help out? Are we greeting you when you come home? Are we watching television with you after dinner? Are we hanging out with you while you make breakfast?

The establishment of routine is a critical part of the familiar's learning. The analogy to Roomba was: if you scheduled your Roomba, you were super happy, and you had years of engagement. If you didn't schedule your Roomba, after a few months your utilization went way, way, way down, and maybe you were in a closet.

So this idea of -- within the first few days, do you have a place? And then long-term, what does the familiar do for you, and what do you do for it? This idea of bidirectional caring, that evolves -- and you will be able to teach your familiar new tricks, you will be able to learn new things from your familiar, and that relationship will grow and become deeper over time.

By getting each of these four time periods right, we believe we can create a little bit of happiness in people's lives, that gives them some helpful nudges to reinforce a positive routine, be this hyper-loyal presence in your world, with an affordable cost of ownership.

The other wonderful lesson that we took away from iRobot is, how do we test all these hypotheses? And how were we able to bring some of the thought leaders around consumer testing to make sure that these philosophies that we have talked about are actually real, such that this next robot is never described as soft in its benefit, but instead, this is a bit of joy that I care for and is one of my favorite purchases.

[00:47:31] Brian Heater: We're just about out of time, so we can close on this. But I'm wondering if, to a certain extent, you feel like there's gonna be a bit of an uphill battle because of all of the generations of attempts at home robots and home pets. They're these beloved -- we mentioned Aibo, there's Lovot, and Jibo. These are robots that people loved, but for whatever reasons, didn't last. And people do have expectations about what robots can and can't do in the home. So how are you really going to express to people that this is something different?

[00:48:10] Colin Angle: Well, I think that ultimately people will try and realize that it's different. I mean, this is not a watch-me toy. This is something that, if you're not motivated to touch and pet it, then boy, we did something wrong. This is something that doesn't live in a four-by-four box in front of you. This is something that can take you for a walk outside.

There's never been a consumer robot that was able to do that. This actually lives in your space. You get up and you go to the kitchen -- it can follow you and hang out with you. No robot has ever been able to do that before, right? So what we're doing is so miles beyond what has gone before.

I appreciate, and I think it's unavoidable, for people to initially think, gee, why is this not like that? But the reality of what we have created is so different that it's not even a useful comparison. And just like Roomba -- no one believed Roomba was gonna work, and until people tried Roomba... I think that this is going to be a new product that word of mouth -- reviewers bring home and their voice is the voice that matters. And we're very confident, just in the experience that we're creating.

[00:50:03] Brian Heater: Well, we are out of time. Colin, always a pleasure. Thank you so much.

[00:50:08] Colin Angle: My pleasure.

[00:50:10] Brian Heater: Thanks to Colin, thanks to Dan for setting up the conversation. I will be bothering you very soon to test-drive one of those new robots. Thanks as always for tuning in. Please like and subscribe and rate the show. Tell some friends -- conveniently forget to mention it to your enemies. Check out the Automated newsletter that hits inboxes on Thursday and LinkedIn on Friday. And with that, we will see you next week with another episode of Automated.