Robots as professional Chefs - Nikhil Abraham, CloudChef
Channel: aiDotEngineer
Published at: 2025-07-20
YouTube video id: MBWGiWJDlSo
Source: https://www.youtube.com/watch?v=MBWGiWJDlSo
[Music] Hey everyone, I'm Nikil. I'm the co-founder CEO of Cloud Chef. Today I'm going to tell you guys how we took a general purpose robot that was not meant for cooking. It was just a robot with two hands. how we trained it or put it through culinary school and it's now a professional chef that's working in various different kitchens doing actual real work like a chef. So before we get into that a quick thing about cloud chef our mission basically is to make highquality nutritious food affordable to everyone and the only way we know how to do it at this point is by automating all commercial labor or all commercial kitchen labor with what we call culinary intelligent robots. So, robots that can act, sense, and reason and behave in the real world like a chef. So, you guys probably all have seen the Tesla Optimus dancing, and like I've seen it, too. And the immediate question that comes to mind is maybe this is how a robot chef will be where, you know, it's it's it's in the kitchen, it's beating down equipment, whatnot, right? But turns out that those guys are a little too expensive. They're not really there yet. There are lots of problems with humanoids. But on the other hand, if you look at form factors like these, they're also general purpose. They're basically just two hands in a mobile base that can move around and actually do all the work that a regular chef would be able to do. And as compared to humanoids, these are now way cheaper than human labor. Like humanoids, if you plot them on this curve, you'll probably not even see them at this point because of like how unreliable they are, how much maintenance it requires. But these wheeled robots with two hands, no problem. Way cheaper than a human uh way cheaper than any human uh chef. But what's missing is actually, you know, software. And what we did was we took that, we took this robot, like I said, we put it through culinary school and now we have chef-like robot labor. So you uh commercial facilities can hire this robot, pay it hourly wages like $12 an hour. It'll always show up. No overtime, no turnover, no uh calling in sick and just or even better than a human, it plugs in place into any arbitrary novel kitchen. So it learns new recipes from one expert demonstration and it is robust to ingredient variation, appliance variation, and can cook on arbitrary portion sizes. This is actually a task that's actually harder for humans to do too. Like when I say we put these robots through culinary school, what we actually do is like what is culinary school for a robot? It needs to learn all the motion primitives that come with human beings. So how do you pick something? How do you stir a pot? And to do that we have these robot foundation models that we fine-tune. We have teley operation to fall back for all these edge cases. But that's not enough. Like you still need the robot to understand food. Like are the onions brown enough? Are are the onions brown enough? If you're cooking steak, is it like shrinking well enough? If you're cooking shrimp, uh do you can you sense when the shrimp is done? And these are like ingredients that vary seasonally, daily, like onions today might require 7 minutes to saute. It'll require like 9 minutes to saute tomorrow. And we basically uh have thermal and visual embeddings that are specific to cooking that help us reason through these like unseen environments. And we've basically modeled recipes as state machines based on these embedding models at the core. And now even if even after you have this, the next thing that you need is it needs to adapt to any new kitchen that it has never seen before. So it needs to be able to see a recipe once, understand what to do and interact with real humans in a workflow and actually do work. So we put our culinary understanding to the test and we at this point do better than even expert chefs in their cuisine of training. And like if you take so basically we evalu across a mix of cuisines. We got uh given the task was given live cooking data, an expert demonstration and a text recipe, can you estimate where in the cooking process you are? Can you track progress uh like a human being? We put it through this expert human chefs who get paid more than $150,000 a year still perform worse than our tiny model that's doing perception in this case. And in fact, when we put like state-of-the-art models like Gemini 2.5 or 03, they actually perform way worse than our own models and that's partly because they don't have any thermal modality. And the thing is thermal modality does not have internet scale data. So what we did is we went and installed sensors in active commercial kitchens, collected hundreds of thousands of uh collected data worth hundreds of thousands of live cooked meals in various kitchen environments across various different recipes, cuisines and seasons. So we collected this private data, we trained a model, we scraped a bunch of public data like uh trained some self-supervised models on that and a combination of this is basically what our culinary system uh banks on. And it is what I like I said is now way better than human chefs at just decision-m during cooking. But motor skills on the other hand, it's not as good as a human, but it is getting there. So we again put it through all these different evals. was sautéing, it's almost as fast as the human cook, picking and pouring, slightly less fast, grilling, stirring. So, it's all a bunch of evals that we did on top of motor skills. And this is how in fact our system is right now about 95% autonomous, 5% teleyoperated. And it's way faster and way more reliable than just teleyop or just foundation models. And basically the robot comes into a kitchen like I said looks at a recipe once from a chef and it's just able to do it. So for example here it's cooking a recipe from a two Michelin star chef who's based out of San Francisco and basically while it's cooking it's looking at how the onions are browning. It's comparing it to how brown the onions were getting when the chef was cooking it. Takes it to the right amount of brownness. It knows exactly what to do for the next recipe where the ingredients are kept. It's not pre-programmed to know where the ingredients are, what kind of uh what kind of variation you'll find. It is doing all that reasoning within the system itself. So yeah, so if we go further and there's a recipe, we'll see how uh it's cooking this chicken. It's basically getting clean readings every single uh every few minutes. And at the end of it, I will basically show you what happens. And yeah, at the end of it, you have actual. So these are actually recipes that go into the the stomachs of actual real customers. So the robots cooking at various different facilities at this point. It's sorry, it's deployed in the real world and yeah, so it's deploy it's deployed in the real world. It's being used in all all these sorts of kitchens. On the right, you can see it cook recipes in our in-house kitchen. On the left, it's also like CCTV footage of the robot doing some operation. Uh I'm I'm not even sure. I just pulled it off of our of the CCTV before getting on stage and just pulled it up here. And this is video from a couple of months ago where the robot's doing uh regular cooking like a human being. And outside of uh our own facilities, this is how for example the robots working at one of our customers facilities doing chicken wings. It's basically fetching the chicken wings from some place uh kept to the side, waits for the uh cook to be done. Uh now it'll basically collect the cooked chicken, put put it inside a bowl and goes ahead, sauces it and mixes it like a human being. And while doing this the robot has a robot is practically a weighing scale itself. So it knows exactly what amount of ingredients it has put in. It knows how much it has stirred and yeah so basically we are cloud chef like I said. Uh at this point we're hiring uh we are a very small team. We are growing super fast and we're looking for people in software, ML and robotics. If you know anyone please uh reach out to me. My email address is nicilcloudshef.co. And yeah thank you. If any of you have any questions, I'm happy to take it. Thank you. So for us, success means two things. One is how good is the robot at understanding what's happening in the cooking process. So uh very simple intuition for that is okay if you give the entire cooking feed to a human being and if you give the entire cooking like video video and uh infrared feed to our system which estimates state better because once you have a cooked recipe you can use that as label data to understand okay if uh the system predicts that this is 40% done was it actually 40% done or was it actually 50% done that's actually a supervised learning signal that we can get after We uh uh uh have data from like recreations like any food recreation from any chef with thermal and uh RGB footage. We're able to do that. The other part is like motions like how fast is the robot able to do physical motions as compared to a human being which I said we're not as good as human beings yet. It's it's basically a data problem. The more data we get, the better we the better and faster we get at doing any individual uh task inside. Does that answer your question? Yes. For the end taste. So the thing that we realized is as a professional like no professional chef is cooking to chemical cons like to consistency that's that can be measured in any chemical way. So our competition is not getting chemical level consistency every single time. It's about it's about getting consistency to a degree that is better than a chef can do a second time. So a common benchmark that we do is we get a chef to cook a recipe once and then we get our system when I we get our robot recreate that recipe a couple of times and then we do blind taste tests and so those are more unscalable emails that we do inhouse which act as a higher signal to okay actually the end product that we get is better than what uh chefs are able to do. No, it's basically just hand uh two hands on a mobile base uh with some cameras and stuff on it. It shows up at the kitchen. You basically interact with it like a human being and that's the form factor there. There's no uh additional screens etc. Those are just for video sake. Uh it depends. Uh ideally humans don't need to but today in some deployments humans do end up doing it but our idea is that because the robot h we because we have joint torque data from like all the different motors from the robot the robot itself is a weighing scale. So when it picks up something it already knows how heavy it is. So that is one thing that we've worked a lot worked on a lot where we are able to work on arbitrary unseen appliances because our sensing stack is so good and uh the other thing is almost all appliances inside kitchens are controlled using knobs. So the motion primitive that the robot needs is to know how to turn a knob and then uh our control systems take care from there. Yeah. Sure. Does this have where it can move automatically? Yes. Yeah. mostly because you guys can go right now. So, uh, right now for most motions, we are anywhere between like 80 to 95% the speed of a human being. And ideally, there's nothing stopping robots from being even faster than human beings. It's mostly just a data problem. Right now the reason why it's not as fast as human beings is because the data that we collect on these robots are done by human beings who telly operate the robot and because human beings telly operating the robot are not as intuitive at telly operating the robot as their own bodies they're not as fast as so the data is kind of slow and then over time we expect with RL and stuff it'll be faster to this yeah So uh there's nothing stopping a robot from doing that either. It's just we don't have like we haven't gone out collected data for those tasks yet. So it's just something on our road map. We are very much blind to that. Where can we eat this? Oh, you can eat this in Palo Alto. So if you're in San Francisco, if you order from Wingstar, that's a customer of ours who uses it. So you'll get it from there. If you're in Palo Alto, you can order from India's top 20 and it'll you can eat from there as well. Or if you're in Menlo Park, you can go to this uh high-end Indian restaurant called Alan and you some of the food there is also cooked by it. We've uh we've asked questions around like chopping and food preparation and whatnot and like a speed of the robot but in terms of uh throughput in the actual process uh how much of that even matters like uh you know how much of the energy already goes in you know throughout the day into prep versus the like uh 90 you know percent or 80% like does that matter this is not a manufacturing facility. uh when it comes to servicing like how much of the economic value is already taken care of because you have the telly operator in the back to make sure things are insured have you guys found that meaningful or is that not a big deal at all and not a like is that trivial essentially at this point great question so basically what uh the quick answer to that is about 50% of the labor cost inside any kitchen is line cooking labor and that's where we are going at first and the advantage there I mean uh speed does play a factor But there's another uh variable that we have in our control which is we are able to speed up recipes uh more than any human being is able to do because we know exactly like we've had several instances where we've recorded like we've observed a chef in motion and realized that oh this process that takes them 20 minutes to do can actually be done in 14 minutes. So if the robot is even like 10% slower it doesn't really matter. That's how it works. Then a tiny follow up to that is like I guess it works more than 40 hours a week. Does this like process? Yeah. Unlike a human being who uh after working 40 hours a week uh goes into overtime territory, robot can work for like 168 hours. Like there's nothing stopping a robot from working for 24/7. The practical constraint is most facilities don't operate 24 hours. So the robot will operate as long as the facility is operating and then there are some tasks that you can do overnight. So once we get into cutting, chopping etc. The robot will just be doing that overnight before the actual stuff comes in. Sorry, mine was kind of related to before. So did this did you find new bottlenecks and things like dishwashing, crosscontamination, stuff that you maybe weren't expecting to deal with this process? So dishwashing etc. Not that much. And even for things like crosscontamination, we just put small gloves on the robot and then like our customers switch that out every day. They were these are washable small silicone pads. I can pull up the video on that. But basically that's how we take care of it. And then uh for things like dishwashing, those are not tasks that we are envisioning doing in the short term. we want to do more of the tasks that actually add to the quality of the food that's being uh put out. So that's why we are mostly focused on line cooking for now. Maybe sometime later like prepping, chopping, etc. Last question. Oh yeah. Uh sorry. Um so there was uh it learns from chefs, right? The recipes from chefs. Is it able to modify steps of a recipe to cook things faster? So that is still an experimental phase. There are cuisines in which we are able to do this really well but we aren't yet able to do this across all cuisines. So for cuisines where the thermodynamic dynamics modeling of uh what's happening in the process is straightforward it is much more easier to uh basically like uh fasten like speed recipes up uh do minor variations etc. And there are some cases where it's not that easy. It's a it it is still like experimental territory. We're still working on that. Yeah. Last question. Uh in the current version, it alerts somebody in the facility that the robot needs ingredients to work and then they they take care of it. Hopefully once there are enough robots in the facility, they'll just talk to each other. And uh thank you so much [Music]