Microsoft Research Podcast - 100 - Autonomous systems, aerial robotics and Game of Drones with Gurdeep Pall and Dr. Ashish Kapoor

Episode Date: November 27, 2019

There’s a lot of excitement around self-driving cars, delivery drones, and other intelligent, autonomous systems, but before they can be deployed at scale, they need to be both reliable and safe. That’s why Gurdeep Pall, CVP of Business AI at Microsoft, and Dr. Ashish Kapoor, who leads research in Aerial Informatics and Robotics, are using a simulated environment called AirSim to reduce the time, cost and risk of the testing necessary to get autonomous agents ready for the open world. Today, Gurdeep and Ashish discuss life at the intersection of machine learning, simulation and autonomous systems, and talk about the challenges we face as we transition from a world of automation to a world of autonomy. They also tell us about Game of Drones, an exciting new drone racing competition where the goal is to imbue flying robots with human-level perception and decision making skills… on the fly. https://www.microsoft.com/research  

Welcome to the 100th episode of the Microsoft Research Podcast. Join me in celebrating with two special guests, the head of Microsoft's Business AI Division, and the lead researcher for Aerial Informatics and Robotics, as we explore how the power of simulation is paving the way for robust autonomous systems in real-world situations. You're listening to the Microsoft Research Podcast, a show that brings you closer to the cutting edge

of technology research and the scientists behind it. I'm your host, Gretchen Huizenga. There's a lot of excitement around self-driving cars, delivery drones, and other intelligent autonomous systems. But before they can be deployed at scale, they need to be both reliable and safe. That's why Gurdip Paul, CVP of Business AI at Microsoft, and Dr. Ashish Kapoor, who leads research in aerial informatics and robotics, are using a simulated environment called AirSim to reduce the time,

cost and risk of the testing necessary to get autonomous agents ready for the open world. Today, Gurdip and Ashish discuss life at the intersection of machine learning, simulation and autonomous systems, and talk about the challenges we face as we transition from a world of automation to a world of autonomy. They also tell us about Game of Drones, an exciting new drone racing competition where the goal is to imbue flying robots with human-level perception and decision-making skills on the fly. That and much more on this episode of the Microsoft Research Podcast. I want to welcome everyone to Are You Ready?, the 100th episode of the Microsoft Research Podcast.

This is going to be a fun show because with me I have Gurdip Paul, who is a Corporate vice president at Microsoft and head of the business AI division, and he leads the AI and research leadership team. And beside him is Dr. Ashish Kapoor, who's a podcast alum, my guest on episode 22. Welcome back. Yeah, thank you. And Ashish is the senior principal research Manager for the Aerial Informatics and Robotics Group at Microsoft, a.k.a. AIR. I'm glad to have you both here on this special episode. Welcome to the podcast, Gurdip, Paul, and Ashish Kapoor.

Yeah, thank you very much. Very excited to be here. Yeah, likewise. Really excited. So I've just introduced you briefly, but I'd like each of you to give a little more detail on what you do for a living. Let's start with you, Gurdip. You've worn a lot of hats here at Microsoft and in other places as well. What's your focus now? What gets you up in the morning? Right now, I'm focused on bringing emergent AI to interesting business problems. And I couldn't imagine at this point in my career

working on something more exciting because the way we think of it, AI is the fourth industrial revolution. So to the extent that we can bring AI into all these different domains around us is one of the most exciting opportunities I think ever and certainly for my career. Is that your mandate then is to bring AI to the world at large? Yes, exactly. So with a slightly more focused way in the sense that, you know, AI, of course, can be applied to many things. And Microsoft has lots of products and you can infuse AI into those products. My focus is how do you create new businesses with emergent AI? Ashish, give us a drone's eye view of your work and what you're doing. What gets you up in the morning?

Yeah, work? Who works? We play. Yeah, so I would say I'm very blessed to work in an organization where we have the opportunity to pursue some of the ambitions. Specifically what I do at Microsoft is lead a research group that's working at the intersection of autonomous systems, machine learning, and simulation. So specifically what we are interested in is building these intelligent agents. And when you think about intelligence, machine learning and artificial intelligence have a big role to play in that.

And so what we're trying to do is take a look at some of the, I would say, techniques on the edge, innovate in those techniques, and then try to solve these hard problems in autonomy. People have been doing machine learning for several decades now, but most of the machine learning right now stops at making predictions. But when you start building systems that act upon those things, that's when things get interesting. And that's what we do.

That's what we start to think about, how we can bring these machine intelligence and machining techniques and apply to systems which act upon it. And autonomous systems are a great example that need to act upon this kind of inferences that machine learning folks have been doing for years. is why the two of you are here together. Obviously, Gurdeep, you're the business side of AI, and Ashish, you're the research side of AI. But describe your relationship in terms of how you know each other and how you work together. Great. I'll start. So, you know, as part of my charter to look at emergent AI and see if new businesses can be created with it, the MO that I have is actually very simple. I just spend a lot of time talking to MSR folks, you know, Eric, Peter, and folks

inside their organizations. And I'm basically looking at what area has come far enough along that this potentially can be channeled towards an existing business problem. You know, I've known of Ashish for a long time. Eric Horvitz used to talk about him all the time even before to me. And then, you know, I got to understand the work that he was doing. So as we were thinking about this sort of overarching autonomous system thing, it was very natural for me to work closely with Ashish. And then eventually, as is pretty common with the areas that we have in

business AI, Ashish moved into my team because typically we have research, engineering, and business folks all together working closely on one particular mission. So Ashish is heading up the research side of that. Okay. So we were part of core Microsoft research, and it was apparent that the impact of some of the work that was happening in our group went beyond just the research impact. It had the potential to empower a lot of machine learning developers and researchers who might want to foray into robotics, for instance. While in research, we have expertise in catering to research crowd. So specifically writing papers and talking about academia. In fact, we had a lot of folks from academia looking into it. And slowly it trickled into other parts of engineering as well. And it made sense for us to start thinking something

bigger than academia, something bigger than research. And the technology is mature enough, but it needs guidance and I would say experience of folks who can build businesses around it. So consequently, I am a research team embedded in the larger organization where we continue to innovate and work on technology while keeping an eye on how it can empower and be useful to other folks. And, you know, I'll add to that, you know, Ashish is a researcher, but what I really think makes him almost like a perfect for the business AI organization is because he really wants to bring that research into real world solutions. And I think that desire is very important because a lot of times, you know, researchers prefer to continue pursuing what they're, you know, very interested in from a research angle perspective. But he's very interested in how that can actually be commercialized or can have a bigger impact. So in that sense, it's really great to have him. Yeah.

And likewise, I would say, right, I mean, if you're building a business, instead of just thinking about the monetary aspects, I mean, you know, we have the support where the research aspects are equally important. In fact, they are at the center of it. So having that kind of balance is very important. So it's a great place to be. Pradeep, Microsoft is not the only company exploring autonomous systems. Talk about the broader ecosystem in this field and Microsoft's position within it.

Maybe starting with your perspective on Microsoft's evolving role in society and how the company's goals evolve with it? These are great questions. So, you know, I think at the highest level, I think one way to think of what's happening around us is, you know, we are really at the onset of the fourth industrial revolution. If you look at what happened with the first industrial revolution, with the steam engine and the factories that got created with it, I mean, it changed societies. This whole notion of child care, you know, didn't exist before the first industrial revolution. And the reason it came up is because people for the first time left their larger families and moved into these towns which are

built around these factories. That's the kind of far-reaching impact the first industrial revolution had. And then each one of them had a similar impact as well. And I think this fourth industrial revolution is going to be just about as dramatic, maybe more. And I think we just have to prepare for that. But coming down to, you know, specifically what we are focused on. Today, we see a big shift from automation slowly towards autonomy. Now, automation has basically enabled the level of productivity that you see today. But automation is very fragile, inflexible, expensive. It's very cumbersome.

Once you set them up and when everything is working well, it's fantastic. And that is what we live with today. You know, autonomous systems, we think, can actually make that a lot easier. Now, the broad industry is really still oriented towards automation. So we have to bring that industry over slowly into this autonomous world. And what's interesting is while these folks are experts in mechanical engineering and operations research, and all those kind of important capabilities and logistics, they don't know AI very much. They don't know how to create horizontal tool chains which enable efficient development and operations of these type of systems.

So that's the expertise we bring. Add that one more point to it, is that the places we are seeing autonomous systems being built, like autonomous driving, they're actually building it in a very, very vertical way. And in some ways, that's a bit of a legacy of how robotic systems have been built in the past. And we don't think that's a scalable way

because there's going to be literally thousands and thousands and thousands of different kinds of autonomous systems. So you need these horizontal building blocks. And that's what we're focused on. Ashish, I want you to answer the same question, but perhaps from a research perspective and where you see Microsoft Research

and Microsoft in general as a player in this space, what's hype and what's hope and what's real? Yeah, definitely. So, you know, automation is where everyone has been focusing on. And autonomy promises to make these things simpler because now your automation is more robust. It has the ability to decide when things are not correct and correct them if needed. And of course, folks have been going after certain vertical like self-driving and they are spending billions of dollars. What if I want to have a different kind of robot that has similar kind of capability? Do I go and spend a few billion dollars again to do that? Probably not. If you got it though. Yeah. So also on the other hand, from the research

perspective, we are increasingly seeing the impact of machine learning technologies on robotics. So, you know, technologies such as reinforcement learning, imitation learning, and now, you know, also unsupervised or self-supervised learning are playing bigger and bigger part in autonomy and robotics. My background is in machine learning. And the way I went into robotics was, you know, there was a vertical that I really cared about, but it was extremely difficult to get into robotics. You not only need to worry about hardware, you also have to worry about orchestration of things, you know, having several people making sure things are safe. If your robot does something stupid, it breaks down, and then you're stuck for a few days. So consequently, a lot of our work in the group have focused on removing some of these obstacles.

If you are a machine learning researcher, developer, if you're a programmer, and if you want to build a robot, what can we bring to you? So that the process for automating and making something autonomous is much simpler. So that you don't have to spend billions of dollars trying to create your ecosystems and everything. It's a tool change. There are modular parts. There are things like simulations. There are things like deep learning methodologies. There are algorithms that you can mix and match almost like Legos. And can we enable that? My brain is going in a thousand directions now because of you two. Thank you very much.

I want to put a little finer point on the difference between automated and autonomous. They both share the same root word. What's the fine differentiation there? The main differentiation is that, let's say you're a BMW car assembly line. And today, most car assembly is done by robots. Now, let's say BMW is launching a new car line. They now need to basically configure that entire assembly line with each station to perform different tasks. Today, the way this line is assembled is that these robots, they know that exactly at this point in the XYZ space that they need to stop the arm.

And then they need to basically have certain torque set. That's all it does. That moves out of the way. New car comes in. They go exactly to that point and they turn it and it goes off. Got it. So now if the car happened to stop half an inch before, it's going to come to that same point and then it's going to have a big problem. That is automation for you.

When everything is working exactly correctly, it is like fast. Really good. Exactly. In an autonomous world, the arm has to find this particular place. And now this thing seeks and finds the right place, even if it is, you know, five inches this way on top, and it'll find it and it'll just align itself correctly and then go for it. That is autonomous, where it has certain level of planning capability and then control capability to deal with unforeseen situations. So the autonomous setup is upstream of the

automated because it's still going to be running the same kind of thing, but you're giving it a brain. Exactly. Let's get technical. You've just alluded to machine learning and some various flavors therein. And I really want to talk about reinforcement learning now, especially because it seems to be the brains behind the autonomous systems we're talking about. So, Gurdip, would you start by talking about the machine learning landscape and the various methodologies that are involved? Sure. When we talk about AI today, probably the most prevalent methodology is something called supervised learning. And supervised learning, the way those algorithms work is that you have a lot of data and you have labels for the data, which basically tell the algorithm how it should adjust its weights.

Then you have unsupervised learning, which is on the other extreme, where you get lots and lots of data, but you really don't have much labels, and the algorithm has to make sense of it. And then you have semi-supervised, where someone sits in the middle, where you may have some data, some of the machine figures out. And, you know, those methods have worked very well for certain kind of problems, right? Like, for example, let's say language. If you want to train our speech stack to basically pick up a new language and train for it, it's pretty easy. You get 1,000 hours of label data, and, you know, these algorithms are very sophisticated. They can go pretty much, you know, learn up to a certain level of performance. What happens for problems that exist in the real world is that either it's very difficult to capture the data or it is nearly impossible to capture all the data that you would ever need to operate inside that.

So reinforcement learning is another approach to AI, which basically says that I'm going to learn by actually taking action in the real world. And every time I take action, I get smarter. And in some ways, you know, this model is how humans learn as well. So at a high level, that's what reinforcement learning is. And the way it is actually implemented practically is that, you know, you have the state, which is the state that you're acting against. The algorithm will take an action and the state changes and you get a reward back, whether you're getting closer or farther from your objective. And then that point you take the next action, you get a reward back and you stay in this loop.

Eventually you figure it out. So that's reinforcement learning for you. So, Ashish, when we talked, we've talked many times, you were mentioning how reinforcement learning has been really successful in game scenarios. And when we get into the open world, it's a whole different ball of wax. You gave us an overview a little over a year ago on AirSim and why simulation is important in this particular milieu. Yeah. Review for us. For those of our listeners who have not heard that podcast, tell us what AirSim is and why the sim part is so important when we talk about these kinds of systems.

So AirSim aspires to be a near-realistic simulation for AI and robotic systems. So in a nutshell, it's a video game on steroids that softwares are playing. And the game comprises of a robotic agent that's operating in an environment which is akin to reality. So Gurdeep just mentioned about technologies such as reinforcement learning and imitation learning, which are trying to solve this decision-making problem. So as an autonomous agent, you need to make decisions. And decisions are not just about now, but it also needs to factor into account the future consequences as well. And that's what makes them hard. So for instance, when you're playing games, so things like Go or Atari games or Pac-Man or any

other video game, right? As a gamer, you have a sense of what your actions right now have a consequence in future. And in order to bake that effect into your machine learning, you need to play millions and millions of time. So, for instance, you know, Atari games, you know, we've been hearing about how machine learning can solve some of these video games at superhuman level, almost getting perfect score. For instance, some of the recent work at Microsoft Research in Montreal talks about Pac-Man. But one thing you need to realize is that you are trying to play these games several hundred millions of times before something reasonable starts to appear as a policy.

We do not have such luxury in the real world. I cannot have a robot bonk into things a million times before I start to learn something new. So consequently, simulation. And more importantly, these simulations with cloud compute specifically, like you can have millions of instances on Azure where these robotic systems, which at the back end have a deep neural network or some kind of machine learning agent guiding them, gathers these experiences. And we can do that very quickly. We don't have to wait days and days,

and we don't have to ruin hundreds of millions of robots. You can do everything in simulation, get this data, and given that AirSIM is trying to be near realistic, the data that you gather is fairly close to reality. So you can hope that the policies and the machine learning intelligence that you are generating will transfer to real world as well. Okay, so when we talked more than a year ago, this was sort of kind of news, right? I would like to know where it is now. I mean, what has happened in this last year? Has it found traction?

AirSim was released as an open source project two and a half years ago. And since then, we've seen increased usage. There are several hundred folks using it for sure. And then there are some very close academic collaborators that have used technologies based on AirSim to solve very difficult problems. For instance, collaborators at USC, they have been using AirSim to train computer vision models to recognize poachers from drones that are flying over Savannah. So, you know, you can imagine how difficult that problem is that you have some drone flying at night over Savannah and your goal is to detect all of these warm bodies, be it animals or poachers, and which

are few pixel big. Again, where do you get real world data for that? So consequently, it adds into the risk, you have to instantiate the entire savannah and simulation and start collecting data at scale. So that's one example. And similarly, I mean, folks have trained racing cars. So for instance, our collaborators in Technion, they have built an SAE racing car. So, SAE is Society of Automotive Engineers, and they have a competition on F1 racing cars, but autonomous. And so, they train their perception models in RSM to do the controls.

So, people are solving very hard challenges in autonomy using this technology. And very different ones. I mean, from poachers to F1 racing cars. My mouth is open right now. It's like mind-boggling and interesting. I mean, from poachers to F1 racing cars, my mouth is open right now. It's like mind-boggling and interesting. I would add to that. I mean, it's now got 9,000 stars on GitHub. So it's at 9,000 stars. Mouth is still open. Well, I want to talk about Game of Drones. And this is a competition that's coming up for NeurIPS 2019. Ashish,

before I talked to you this week, I was actually unaware that drone racing was a thing, let alone a hugely popular thing. And then I went down the YouTube rabbit hole and saw what it was. And it's amazing. And we talked about simulated drone racing. They actually have live drone racing in empty arenas. These guys are in cages and then the drones are going like Harry Potter Quidditch kind of thing. I was blown away. So talk about what you're doing in this arena, no pun intended, of drone racing and how Game of Drones is playing into that and what you hope to accomplish from like a research and science perspective on it. So Game of Drones is a competition that is being held at NeurIPS 2019. This was jointly proposed by Microsoft, Stanford University, and University of Zurich. So this is in collaboration with academia, and it's trying to solve, I would say, one of the hardest problems in autonomy. I would even say that this is one of the goals to aspire for, ultimately.

We talk about all these superhuman feats that AI algorithms can achieve, but they come nowhere close in solving this. So what's really happening in a drone race in real world when people are playing with it is that a person is sitting on a chair and he's wearing goggles. And through these goggles, he can see a video stream through a camera mounted on a drone that's flying at an incredible fast rate. And by looking at that video feed, a human brain is able to essentially send four numbers. You know, those are the control commands, which is the thrust, yaw, roll, and pitch, right? The whole image gets translated into four numbers.

And you can go to YouTube and see all those videos. What fantastic things they can do. They can do flips. They can do quick turns. I mean, it's amazing, like the power of human brain. So the big question is, can you actually have this thing driven by a software? So all your software is seeing is that camera feed. And can you translate all that information into useful control signals? And more importantly, let's make it even more

challenging. It's not just about you going through that course. What if you are also participating against another drone? So now you start thinking about strategies as well. So it's not just about obstacle avoidance. It's also about how can I beat my opponent? So it's bringing in all of these difficult problems, which lie at the intersection of perception, controls, and planning. And the hope is that by feeling such a competition, we would start to understand

and what would it take to build technologies that can solve this hard problem. Now, mind you, trying to do this in real world is extremely hard because, as I said, our algorithms are nowhere near in solving even 1% of this challenge. So consequently, we feel this in simulation. So there are courses that are built in AirSim

where competitors can try their algorithms and see how well they fare. There is an ongoing leaderboard where you can track your progress against your opponents, and then there are prizes as well. Gurdeep, what do you say about this thing? What is amazing to me is how relevant this is in the world. I mean, you don't even have to roll out like hundreds of years. You can see how relevant this is going to be. I mean, you don't even have to roll out like hundreds of years. You can see how relevant this is going to be in the next 10 years. Today, people are making tall claims about autonomous driving.

And, oh, it's going to be this year. It's going to be next year. Somebody says 50 years. So there's all this going on. And actually, what is underlying all that is that there is this missing piece that nobody has cracked. The missing piece is that most of the autonomous driving systems are actually built with old school robotics. And the problem with old school robotics

is that it is not sufficient to solve these complex problems. And that is the missing piece. And this game of drones goes to the heart of that. Gurdeep, I want you to go on a little bit there. There are some other big issues on the horizon related to exactly what you were just talking about. When autonomous systems head to real world applications and they involve upstream work with like legal issues, business issues, regulatory issues. So even as Ashish's team over here is setting up Game of Thrones and doing their own research, what's going on in this other lane?

You're absolutely right. You know, this is sort of a brave new world with a whole bunch of new things which open up. If you're, let's say, city of Bellevue, right? And, you know, here you were you just about the time you figured out how to get traffic right and coordinating the lights changing when you're driving on a on a main arterial you know now suddenly you have delivery robots you have drones you have self-driving trucks you have cars you have all these things going around and now you

know things are messed up all over again you You just start thinking about that problem. And so how are they going to deal with this really complex world? So I think, you know, this is an area, some of the areas that we're starting to look at is what kind of solutions they will need in a world like this. Is there, from the business perspective, because I would assume the researchers are just working on the technology. I think it's important to actually, from a research point of view, take a stand on this. So, you know, we think deeply about this in research as well. And just to give you a nugget, in our research group, the perspective that we have is that if there is a system failure happens, you should be able to find someone, some human, who is responsible for it. So for instance, if there is an autonomous

system that you have designed, a human tells the system, these are the safety specifications. I always want you to be in these things. So if a system fails because there was something outside of those specifications, it's a human's fault because as a designer, he didn't think about that. So there is a philosophy even in research that we need to adhere to. In our case, we take this thing very seriously, where we say that every mistake needs to be traced to a responsible human who can then take corrective action on it. I want to talk a little bit more, Ashish,

about something you mentioned on airborne collision avoidance systems and the whole concept of air traffic controls. If we're talking about flying robots, even now that particular job is really high stress and very rule-based for humans. But you've painted a picture where we're going to have hundreds of autonomous vehicles. How do you even begin? So, I mean, you're absolutely right. The job of ATC is one of the most difficult ones. And it's considered the most stressful job in the world because so much is at stake. And these guys do an amazing job trying to keep us safe while the demand on the system is increasing.

And as you can imagine, as you see more and more drones and flying taxis, this system would not scale. So we will have to start thinking about automated decision-making. So I'm again, not using the phrase autonomous, but more about automated decision-making because, you know, there should be some human accountability, as I said, but a lot of tasks should be automated and almost on the verge of autonomous systems. So that's where airborne collision avoidance systems comes into effect. If you have these vehicles which are broadcasting their state, so not just flying vehicles, it can be cars as well, it can be forklifts,

it can be delivery robots, but they are broadcasting their state and their intent on what they want to do. Then can you come up with decision-making modules that operate on each robot so that they can take care of themselves? An example that I really like to show is if you've been to Japan, you have this intersection, Shibuya, where the red lights happen across. And I think five or seven different intersections merge together. And you have 300, 400 people crossing at once. And within three minutes, everyone has crossed.

There are no collisions. What would it take us to build something like that? But again, this is right at the intersection of machine learning, autonomy, robotics. Everything you come up with brings up new things. It's like, this is research forever, right? Mama needs a new pair of shoes. Well, there's another competition that I'd like to talk about. Ashish, you and a team of

collaborators just employed your AirSim technology to win a pretty amazing competition called the DARPA Sub-T Challenge, Sub-T standing for subterranean. And you won it rather decisively. So tell us about this challenge and why it was an important proving ground for AirSim. Yeah. So Team Explorer, which was spearheaded by Carnegie Mellon University and Oregon State University. So they are our close collaborators. And they had been using AirSim for many other research projects. And when they decided to participate in the DARPA Subterranean Challenge, we had conversations on how simulation could help them achieve the mission. So just a quick introduction on what DARPA Subterranean Challenge is. Terrains under the ground, be it

man-made caves, mines, natural caves, tunnels, etc., are very difficult to navigate and can be very dangerous. So think about search and rescue operations. Instead of sending humans, it's very useful if you can have robots that can navigate, that can map, that can go over obstacles and find things. So Sub-T Challenge is centered around that. And our collaborators at CMU and OSU, they have a pretty amazing robotic system that's designed to address those challenges. However, how do they test these systems? How do they get training data so that these systems can

learn to see objects in these worlds? So consequently, we created a simulation environment that several miles long set of caves with different kinds of effects such as fog and wetness and different objects hidden at different places so that they can go and test their algorithms and systems before our team explorer needs to solve these in real world. So the simulation environment helps them by validating their methodologies as well as collecting training data for their perception models. So the competition itself was to identify several of these objects

that were lying in a real cave. And you had to send your robots and you had to identify. So the objects, for instance, were a survivor, a backpack, a cell phone, a drill, and I believe a flashlight. So this was a real cave. This was a real cave. And real robots. And real robots.

And there were all these objects. The team, whoever could go and detect maximum number of these objects, won. And so the simulation prior to gave you an advantage for executing it in real life. Yeah. And all the algorithms that were there, whether it be, you know, finding it and planning and all that, would be tested in the simulation environment. Right. be tested in this simulation environment. And to me, I mean, the biggest thing about this, other than achievement of winning the DARPA challenge is always a pretty swaggy thing. But to me, what is really interesting about it, this thesis that we have, that you can

create these brains in a simulation environment and you can perform much, much better than anything else in the real world. I mean, this got completely established. In fact, you know, I hope that the industry sees us as a tipping point in moving from some of the old ways of doing things towards kind of what we are pushing. Well, it's time for what could possibly go wrong on the Microsoft Research Podcast. And when we're talking about flying robots, the answer's a lot. So the general risks are pretty obvious, but I know each of you have thought through some specific challenges that keep you up at night. Talk in turn about issues of safety and trustworthiness of autonomous systems and how you're addressing those so that I don't lose sleep at night. Gurdeep?

Great. Let me first frame it in the context of this industry and Microsoft and what we've learned. You know, the good thing is that there's just a brief history of computing. You know, you don't have to go back to, you know, 10,000 years. I've worked on Windows NT. And, you know, we thought we were being very careful about making sure the code can't be hacked and this and that. We had no idea. The moment the internet got connected and these machines were on the internet, you basically could be attacked from anywhere. And there were such strong incentives for people, for bad actors to really do their best work. We can't afford to see that happen in the autonomous system space. We have to proactively get in and say, we need to

solve these problems before these systems are unleashed in the real world. Because the consequence of things failing in the real world is very, very high. I mean, this is where it gets completely real. So that is the broader context, I would say. And by the way, I should plug in. I mean, I think the work that Eric is driving with Ether, I'm a huge fan of that because I think as a company, we've said we're going to proactively look at AI all up and identify some of these things. And I think in our case in particular, we are looking at even from a product perspective or the

tool chain that we are building in my team, how this is one of the differentiated pillars. We call it trustworthy autonomy. And we've made it one of the differentiated pillars. We call it trustworthy autonomy. And we've made it one of the three pillars so that over time we get more and more sophisticated and whoever is using our tool chain to create autonomous systems can actually benefit from all that. Ashish, what would you add? Yeah, so... What keeps you up at night? Yeah, I mean, all those things that Gurv mentioned, but I'll mention one specific thing, which keeps me up at night because something that, you know, as a researcher or a technologist, it's hard for me to influence.

We are making progress. We are thinking about it. And community at large is getting aware of those things. So there are at least some progress. But here is the deal. I think the pace at which the technology is evolving is very rapid. And I'm afraid that, you know, the regulation might not be evolving that quickly. But the reality is the following. Right now, if you want to build an autonomous system, there are plans out there on the web.

Anyone who has some kind of an engineering expertise can just go ahead and build it very rapidly, right? And of course, you know, a lot of good actors who are trying to make things better in autonomous systems, they'll play by regulation, right? However, many of those bad actors will not. So I think that's a tension that I don't know how to resolve. So as you two have identified some things that I think nobody would argue, these are the highest level, what keeps me up at night on the planet. Aside from thinking about it, are there things that you're kind of building or baking into your research and your execution that would say, hey, we got this? Absolutely. In fact, I think Ashish should talk about some of the research work that he's been doing. And we are actively looking to see how we can productize that as part of our trustworthy

autonomy pillar and feature set. So, yes, we are actively looking at that. Do you want to talk about that? Yeah, definitely. So safety is very important, not from the point of view of, you know, a hacker attacking your system or cybersecurity flaws and things like those, but also from the fundamental technology point of view. So, for instance, your robots or your autonomous systems, they will have sensors and they'll see the world through very likely a machine learning system. And we know machine learning systems have problems like bias is one, you know, they make mistakes.

And when we know that these systems have problems how do you then assure safety so that's a big question that we are trying to answer and the way we are thinking about is is now building policies that are optimal in the worst case so we need to look down to history and things about how airplanes and spaceships were designed you know they solved a fairly difficult problem, and now we can hop onto an airplane without worrying about our safety. What would it take us to do that? And we need to learn from those fields,

and we need to look at the technologies they employed. So that's, you know, in a nutshell, that's what we're looking into. At the end of every podcast, I give my guests the opportunity to say anything they want to our listeners. So, Gurdip and Ashish, do you have any parting advice, warning, wisdom, or predictions? What challenges lie ahead for autonomous systems in your minds? If you are an aspiring roboticist, this is the time to come out. The reason being that, you know, the technology is there.

There are a lot of people excited about it. And definitely the tool chains are becoming much easier. I have my son who wants to do robotics. And it's quite hard to get started on it. But I'm hoping, you know, by the time he goes to middle school, he should be able to build these autonomous systems. And he could imagine and he could build these things very easily. So, you know, if you're excited about robotics and machine learning, I think there are stuff out there. And I would encourage everyone to come out and, you know, play and

contribute. Gurdeep, last words. You know, humans overestimate what can happen in three years and underestimate what happens in 10 years. And we are embarking on another one of those moments where I think 10 years from now, the world is going to be very, very, very different. And it's inevitable. So it's not like, let's slow down or whatever. I think we just have to lean in and go really fast and pre-think some of these things so that as the world really adopts these things, it is done in a way that we can all survive it. You know, I remind people that it's only a couple of years ago, the iPhone was 10 years old. And when the iPhone came out, nobody could have predicted

how it changed lives. And I think you can say that with the internet, you can say that with personal computer and so many things. I think this is one of those moments. So we have to get into it, both getting ahead of it, leveraging it, you know, getting our kids to be trained in these things. And I think we just have to get in as a society. Gurdeep Pal, Ashish Kapoor, thank you for making episode 100 this fantastic. Thanks for having us. Thank you very much.