{"id":624378,"date":"2019-11-27T03:15:07","date_gmt":"2019-11-27T11:15:07","guid":{"rendered":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/?p=624378"},"modified":"2022-11-07T11:39:00","modified_gmt":"2022-11-07T19:39:00","slug":"autonomous-systems-aerial-robotics-and-game-of-drones-with-gurdeep-pall-and-dr-ashish-kapoor","status":"publish","type":"post","link":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/podcast\/autonomous-systems-aerial-robotics-and-game-of-drones-with-gurdeep-pall-and-dr-ashish-kapoor\/","title":{"rendered":"Autonomous systems, aerial robotics and Game of Drones with Gurdeep Pall and Dr. Ashish Kapoor"},"content":{"rendered":"<p><a href=\"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788.png\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-large wp-image-624393\" src=\"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-1024x576.png\" alt=\"Gurdeep Pall and Ashish Kapoor on the Microsoft Research Podcast\" width=\"1024\" height=\"576\" srcset=\"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-1024x576.png 1024w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-300x169.png 300w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-768x432.png 768w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-1066x600.png 1066w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-655x368.png 655w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-343x193.png 343w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-640x360.png 640w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-960x540.png 960w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-1280x720.png 1280w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788.png 1400w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/a><\/p>\n<h3>Episode 100 | November 27, 2019<\/h3>\n<p>There\u2019s 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\u2019s why Gurdeep Pall, CVP of Business AI at Microsoft, and <a href=\"https:\/\/newed.any0.dpdns.org\/en-us\/research\/people\/akapoor\/\">Dr. Ashish Kapoor<\/a>, who leads research in <a href=\"https:\/\/newed.any0.dpdns.org\/en-us\/research\/group\/air\/\">Aerial Informatics and Robotics<\/a>, are using a simulated environment called <a href=\"https:\/\/newed.any0.dpdns.org\/en-us\/research\/project\/airsim-high-fidelity-visual-and-physical-simulation-for-autonomous-vehicles\/\">AirSim<\/a> to reduce the time, cost and risk of the testing necessary to get autonomous agents ready for the open world.<\/p>\n<p>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 <a href=\"https:\/\/newed.any0.dpdns.org\/en-us\/research\/academic-program\/game-of-drones-competition-at-neurips-2019\/\">Game of Drones<\/a>, an exciting new drone racing competition where the goal is to imbue flying robots with human-level perception and decision making skills\u2026 on the fly.<\/p>\n<h3>Related:<\/h3>\n<ul type=\"disc\">\n<li><a href=\"https:\/\/newed.any0.dpdns.org\/en-us\/research\/podcast\">Microsoft Research Podcast<\/a>: View more podcasts on Microsoft.com<\/li>\n<li><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" rel=\"noopener noreferrer\" target=\"_blank\" href=\"https:\/\/itunes.apple.com\/us\/podcast\/microsoft-research-a-podcast\/id1318021537?mt=2\">iTunes<span class=\"sr-only\"> (opens in new tab)<\/span><\/a>: Subscribe and listen to new podcasts each week on iTunes<\/li>\n<li><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" rel=\"noopener noreferrer\" target=\"_blank\" href=\"https:\/\/subscribebyemail.com\/www.blubrry.com\/feeds\/microsoftresearch.xml\">Email<span class=\"sr-only\"> (opens in new tab)<\/span><\/a>: Subscribe and listen by email<\/li>\n<li><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" rel=\"noopener noreferrer\" target=\"_blank\" href=\"https:\/\/subscribeonandroid.com\/www.blubrry.com\/feeds\/microsoftresearch.xml\">Android<span class=\"sr-only\"> (opens in new tab)<\/span><\/a>: Subscribe and listen on Android<\/li>\n<li><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" rel=\"noopener noreferrer\" target=\"_blank\" href=\"https:\/\/open.spotify.com\/show\/4ndjUXyL0hH1FXHgwIiTWU\">Spotify<span class=\"sr-only\"> (opens in new tab)<\/span><\/a>: Listen on Spotify<\/li>\n<li><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" rel=\"noopener noreferrer\" target=\"_blank\" href=\"https:\/\/www.blubrry.com\/feeds\/microsoftresearch.xml\">RSS feed<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/li>\n<li><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" rel=\"noopener noreferrer\" target=\"_blank\" href=\"https:\/\/note.microsoft.com\/ww-registration-microsoft-research-newsletter-s.html?wt.mc_id=S-webpage_podcast\">Microsoft Research Newsletter<span class=\"sr-only\"> (opens in new tab)<\/span><\/a>: Sign up to receive the latest news from Microsoft Research<\/li>\n<\/ul>\n<hr>\n<h3>Transcript<\/h3>\n<p><b><span data-contrast=\"auto\">Host:&nbsp;<\/span><\/b><b><span data-contrast=\"none\">Welcome to the 100<\/span><\/b><b><span data-contrast=\"none\">th<\/span><\/b><b><span data-contrast=\"none\">&nbsp;episode of the Microsoft Research Podcast! Join me in celebrating with two special guests, the head of Microsoft\u2019s 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.<\/span><\/b><span data-ccp-props=\"{}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host:&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">You\u2019re 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\u2019m your host, Gretchen Huizinga.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">There\u2019s a lot of excitement around self-driving cars, delivery drones, and other intelligent, autonomous systems<\/span><\/b><b><span data-contrast=\"auto\">.<\/span><\/b><b><span data-contrast=\"auto\">&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">B<\/span><\/b><b><span data-contrast=\"auto\">ut before they can be deployed at scale, they need to be both reliable and safe. That\u2019s 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&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">AirSim<\/span><\/b><b><span data-contrast=\"auto\">&nbsp;to reduce the time, cost and risk of the testing necessary to get autonomous agents ready for the open world.<\/span><\/b><span data-ccp-props=\"{}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"none\">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.&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">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\u2026 on the fly.<\/span><\/b><b><span data-contrast=\"auto\">&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">That and much more on this episode of the Microsoft Research Podcast.<\/span><\/b><span data-ccp-props=\"{}\">&nbsp;<\/span><\/p>\n<p><b><i><span data-contrast=\"auto\">(music plays)<\/span><\/i><\/b><span data-ccp-props=\"{}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: I want to welcome everyone to \u2013 are you ready? \u2013 the hundredth episode of the Microsoft Research Podcast! This is going to be a fun show because with me I have Gurdeep Pall, who is a Corporate Vice President at Microsoft and head of the Business AI division, and he leads the AI and Research Leadership Ream. And beside him is Dr. Ashish Kapoor, who\u2019s a podcast alum. My guest on Episode 22. Welcome back!<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: Yeah, thank you.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: And Ashish is the Senior Principle Research Manager for the Aerial Informatics and Robotics Group at Microsoft, aka AIR. I\u2019m glad to have you both here on this special episode. Welcome to the podcast group Gurdeep Pall and Ashish Kapoor!<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: Yeah, thank you very much. Very excited to be here.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: Yeah, likewise, really excited.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: So I\u2019ve just introduced you briefly but I\u2019d like each of you to give a little more detail on what you do for a living. Let\u2019s start with you, Gurdeep. You\u2019ve worn a lot of hats here at Microsoft and in other places as well. What\u2019s your focus now? What gets you up in the morning?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: Right now, I\u2019m focused on bringing emergent AI to interesting business problems. And I couldn\u2019t 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.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Is that your mandate, then, is to bring AI to the world at large?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: Yes, exactly. So with a slightly more focused way in a 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?<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Ashish, give us a \u201cdrone\u2019s eye view\u201d of your work and what you\u2019re doing. What gets you up in the morning?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: Yeah, work? Who works? We play! Yeah, so I would say I\u2019m 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\u2019s 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 try 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\u2019s when things get interesting. And that\u2019s what we do. That\u2019s what we start to think about: how we can bring these machine intelligence, machine learning 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.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Before we really get into it, I\u2019d like to establish for our listeners why the two of you are here together. Obviously, Gurdeep, you\u2019re the business side of AI and Ashish, you\u2019re the research side of AI. But describe your relationship in terms or how you know each other and how you work together.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: Great, I\u2019ll 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&nbsp;<\/span><span data-contrast=\"auto\">organizations, and I\u2019m basically looking at what area has come far enough along that this, potentially, can be channeled towards an existing business problem? You know, I\u2019ve known of Ashish for a long time. Eric Horvitz used to talk about him all the time on the phone 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.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Okay.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: 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, you know, 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.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Right.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: 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.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: You know, and I\u2019ll add to that, you know, Ashish is a researcher, but what I really think makes him almost like 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\u2019re, you know, very interested in from a research angle perspective, but he\u2019s very interested in how that can actually be\u2026<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Right.&nbsp;<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: \u2026commercialized or can have a bigger impact. So in that sense, it\u2019s really great to have him.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: Yeah, and likewise I would say, right, I mean, if you are building a business, instead of just thinking about monetary aspects, I mean, you know, we have the support where&nbsp;<\/span><span data-contrast=\"auto\">the research aspects are equally important. In fact, they are the center of it. So having that kind of balance is very important. So it\u2019s a great place to be.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Gurdeep, Microsoft is not the only company exploring autonomous systems. Talk about the broader ecosystem in this field and Microsoft\u2019s position within it, maybe starting with your perspective on Microsoft\u2019s evolving role in society and how the company\u2019s goals evolve with it?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: Yeah, these are great questions. So, you know, I think at the highest level, I think one way to think of what\u2019s happening around us is, you know, we are really at the onset really 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 childcare, you know, didn\u2019t 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 were built around these factories. That\u2019s the kind of far-reaching impact the first industrial revolution had. And then each one of them had a similar impact as well.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host:&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">Mmm<\/span><\/b><b><span data-contrast=\"auto\">-hmm.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: And I think this fourth industrial revolution is going to be just about as dramatic.&nbsp;<\/span><span data-contrast=\"auto\">Maybe more.<\/span><span data-contrast=\"auto\">&nbsp;And I think we just have to prepare for that. But coming down to, you know, specifically what we are focused on\u2026<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Yeah.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: \u2026today, we see a big shift from automation slowly towards autonomy.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host:&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">Mmm<\/span><\/b><b><span data-contrast=\"auto\">.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: Now, automation has basically enabled a level of productivity that you see today. But automation is very fragile, inflexible, expensive\u2026 it\u2019s very cumbersome. Once you set them up and when everything is working well, it\u2019s fantastic, and that is what we live with today.&nbsp;<\/span><span data-contrast=\"none\">You know, autonomous systems<\/span><span data-contrast=\"none\">,<\/span><span data-contrast=\"none\">&nbsp;we think<\/span><span data-contrast=\"none\">,<\/span><span data-contrast=\"none\">&nbsp;<\/span><span data-contrast=\"none\">can<\/span><span data-contrast=\"none\">&nbsp;actually make that a lot easie<\/span><span data-contrast=\"none\">r.&nbsp;<\/span><span data-contrast=\"auto\">Now the broad industry is really still oriented toward automation. So we have to bring that industry over slowly into this autonomous world. And what\u2019s interesting is, while these folks are experts in mechanical engineering and operations research and, you know, all those kind of important capabilities and logistics, they don\u2019t know AI very much.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: No.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: They don\u2019t know how to create horizontal tool chains which enable efficient development and operations of these type of systems. So that\u2019s the expertise we bring. I\u2019d add one more point to it, is that the places we are seeing autonomous systems being built, like&nbsp;<\/span><span data-contrast=\"auto\">autonomous driving, they\u2019re actually building it in a very, very vertical way. And, in some ways, that\u2019s a bit of a legacy of how robotics systems have been built in the past. And we don\u2019t think that\u2019s a scalable way, because there\u2019s going to be literally thousands and thousands and thousands of different kinds of autonomous systems, so you need these horizontal<\/span><span data-contrast=\"none\">&nbsp;<\/span><span data-contrast=\"auto\">building blocks, and that\u2019s what we\u2019re focused on.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: 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\u2019s hype and what\u2019s hope and what\u2019s real?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: Yeah, 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 verticals, like self-driving. 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!<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: If you\u2019ve got it<\/span><\/b><b><span data-contrast=\"auto\">,<\/span><\/b><b><span data-contrast=\"auto\">&nbsp;though\u2026<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: Yeah!, So\u2026 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 a bigger and bigger part in autonomy and robotics.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host:&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">Mmm<\/span><\/b><b><span data-contrast=\"auto\">-h<\/span><\/b><b><span data-contrast=\"auto\">m<\/span><\/b><b><span data-contrast=\"auto\">m.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: 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\u2019re stuck for 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 are 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\u2019t have to spend billions of dollars trying to create your ecosystems and everything.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Right.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: It\u2019s a tool chain. 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?<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host:&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">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\u2019s the fine differentiation there?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: The main differentiation is that, let\u2019s say you\u2019re a&nbsp;<\/span><span data-contrast=\"none\">BMW&nbsp;<\/span><span data-contrast=\"auto\">car assembly line. And today, most car assembly is done by robots. Now, let\u2019s 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,&nbsp;<\/span><span data-contrast=\"none\">that&nbsp;<\/span><span data-contrast=\"auto\">they need to stop the arm and then they need to basically have certain torque set\u2026 That\u2019s all it does. Then it moves out of the way, new car comes in, they go exactly to the point and they turn it and it goes on, right?<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Got it.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: So now, if the car happened to stop half an inch before, it\u2019s going to come to that same point, and then it\u2019s going to have a big problem. That is automation for you. When everything is working exactly correctly it is like fast chu, chu, chu, chu\u2026<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Really good.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: 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, and it will find it and just align itself correctly and then go for it.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Okay.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: That is autonomous.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Okay.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: Where it has a certain level of planning capability and then control capability to deal with unforeseen situations.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: So the autonomous setup is upstream of the automated because it\u2019s still going to be running the same kind of thing, but you\u2019re giving it a brain.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: Exactly.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><i><span data-contrast=\"auto\">(music plays)<\/span><\/i><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Let\u2019s get technical. You\u2019ve just alluded to machine learning and some various flavors therein, and then I really want to talk about reinforcement learning now, especially&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">because it seems to be the brains behind the autonomous systems we\u2019re talking about. So, Gurdeep, would you start by talking about the machine learning landscape and the various methodologies that are involved?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: 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\u2019t have much labels and the algorithm has to make sense of it. And then you have semi-supervised, which somewhat sits in the middle where you may have some data, something the machine figures out. And you know, those methods have worked very well for certain kind of problems, right? Like for example, let\u2019s say language. If you want to train our speech stack to basically pick up a new language and train for it, it\u2019s pretty easy. You get a thousand hours of labeled data and, you know, these algorithms are very sophisticated they can go pretty much, learn up to a certain level of performance. What happens for problems that exist in the real world is that, either it\u2019s 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.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Right.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: So reinforcement learning is another approach to AI, which basically says that I\u2019m going to learn by actually taking action in the real world and every time I take action get smarter. And in some ways, you know, this model is how humans learn as well. So, at a high level, that\u2019s 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\u2019re acting against, the algorithm will take an action, and the state changes, and you get a reward back whether you\u2019re getting closer or farther from your objective. And then at that point you take the next action. You get a reward back. And you stay in this loop\u2026 eventually you figure it out.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Okay.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: So that\u2019s reinforcement learning for you.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: So, Ashish, when we talked, we\u2019ve 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\u2019s a whole different ball of wax. You gave us an overview, a little over a year ago, on&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">AirSim<\/span><\/b><b><span data-contrast=\"auto\">&nbsp;and why simulation is important in this particular milieu.&nbsp;<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: Yeah, yeah.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Review for us, for those of our listeners who have not heard that podcast, tell us what&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">AirSim<\/span><\/b><b><span data-contrast=\"auto\">&nbsp;is and why the \u201csim\u201d part is so important when we talk about these kinds of systems.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: So&nbsp;<\/span><span data-contrast=\"auto\">AirSim<\/span><span data-contrast=\"auto\">&nbsp;aspires to be a near realistic simulation for AI and robotics systems. So, in a nutshell it\u2019s a video game on steroids that&nbsp;<\/span><span data-contrast=\"auto\">softwares<\/span><span data-contrast=\"auto\">&nbsp;are playing. And the game comprises of a robotic agent that\u2019s operating in an environment which is akin to reality. So Gurdeep just mentioned about technology 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\u2019s what makes them hard. So, for instance, when you\u2019re 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 times. So for instance, you know, Atari games. You know, we\u2019ve 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&nbsp;<\/span><span data-contrast=\"auto\">PacMan<\/span><span data-contrast=\"auto\">. 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 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, you know, 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, it gathers these experiences. And we can do that very quickly. We don\u2019t have to wait days and days, and we don\u2019t have to ruin hundreds of millions of robots. You can do everything in simulation, get this data, and given that&nbsp;<\/span><span data-contrast=\"auto\">AirSim<\/span><span data-contrast=\"auto\">&nbsp;is trying to be near realistic, the data that you gathered is fairly close to reality. So, you can hope that the policies and the machine learning intelligence that you\u2019re generating will transfer to real world as well.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Okay. So when we talked more than a year ago, this was sort of kind of news, right?&nbsp;<\/span><\/b><b><span data-contrast=\"none\">I would like to know&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">where it is now? I mean what has happened in this last year? Has it found traction?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor:&nbsp;<\/span><span data-contrast=\"auto\">AirSim<\/span><span data-contrast=\"auto\">&nbsp;was released as an open source project two and a half years ago and since then we\u2019ve 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&nbsp;<\/span><span data-contrast=\"auto\">AirSim<\/span><span data-contrast=\"auto\">&nbsp;to solve very difficult problems. For instance, collaborators at USC, they have been using&nbsp;<\/span><span data-contrast=\"auto\">AirSim<\/span><span data-contrast=\"auto\">&nbsp;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 a few pixels big. Again, where do you get real world data for that?<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: No.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: So consequently,&nbsp;<\/span><span data-contrast=\"auto\">AirSim<\/span><span data-contrast=\"auto\">&nbsp;to the rescue, where we instantiate the entire savannah in simulation and start collecting data at scale. So that\u2019s one example. And similarly, I mean, folks have trained racing cars. So for instance, our collaborators in&nbsp;<\/span><span data-contrast=\"auto\">Technion<\/span><span data-contrast=\"auto\">, they have built an SAE racing car \u2013 so SAE is Society of Automobile Engineers \u2013 and they have a competition on F1 racing cars, but autonomous. And so they train their perception models in&nbsp;<\/span><span data-contrast=\"auto\">AirSim<\/span><span data-contrast=\"auto\">&nbsp;to do the controls. So people are solving very hard challenges in autonomy using this technology.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: And very different ones. I mean, from poachers to F1 racing cars. My mouth is open right now. It\u2019s like, mind-boggling. And interesting.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: I would add to that. I mean it\u2019s\u2026 got\u2026 now at 9,000 stars on GitHub?<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: Yes, yes. Yeah, yeah.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: \u2026so it\u2019s at 9,000 stars\u2026&nbsp;<\/span><span data-contrast=\"auto\">AirSim<\/span><span data-contrast=\"auto\">.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Mouth is still open\u2026 Well, I want to talk about Game of Drones. And this is a competition that\u2019s coming up for&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">NeurIPS<\/span><\/b><b><span data-contrast=\"auto\">&nbsp;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\u2019s amazing. And we talked about simulated drone racing. They actually have live drone racing\u2026<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: Live drone racing, yeah\u2026!<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: \u2026in empty arenas. These guys are in cages and then the drones going like Harry Potter in Quidditch, kind of thing. I was blown away. So, talk about what you\u2019re 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.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: So Game of Drones is a competition that is being held at&nbsp;<\/span><span data-contrast=\"auto\">NeurIPS<\/span><span data-contrast=\"auto\">&nbsp;2019, and this was jointly proposed by Microsoft, Stanford University and University of Zurich. So, yeah, you know, this is in collaboration with academia and it\u2019s 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. Like, you know, we talk about all these superhuman feats that AI algorithms can achieve, but they come no way close in solving this. So what\u2019s 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\u2019s wearing goggles. And through these goggles, he can see a video stream through a camera mounted on a drone that\u2019s flying at an incredible fast rate.&nbsp;<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Yeah.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: 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 to four numbers, and you can go to YouTube and see all those videos, what fantastic things they can do\u2026<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: I did!<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: They can do flips. They can do quick turns. I mean, it\u2019s amazing, 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\u2019s make it even more challenging. It\u2019s not just about you going through that course. What if you\u2019re also participating against another drone? So now you start thinking about strategies as well. So it\u2019s not just about obstacle avoidance, it\u2019s also about how can I beat my opponent? So it\u2019s bringing in all of these difficult problems which lie at the intersection of perception, controls and planning. And the hope is that, by fielding such a competition, we would start to understand in what would it take to build technologies that can solve this hard problem. Now mind you, trying to do this in the real world is extremely hard because, as I said, our algorithms are nowhere near in solving even 1% of this challenge.&nbsp;<\/span><span data-contrast=\"auto\">So consequently, we field this in simulation.<\/span><span data-contrast=\"auto\">&nbsp;So there are courses that are built in&nbsp;<\/span><span data-contrast=\"auto\">AirSim<\/span><span data-contrast=\"auto\">&nbsp;where competitors can try their algorithms and see how well they fare. There is an ongoing leader board where, you know, you can track your progress against your opponents and then there are prizes as well.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Gurdeep, what do you say about this thing?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: You know, what is amazing to me is how relevant this is in the world. I mean, you don\u2019t even have to roll out like hundreds of years. You can see how relevant this is going to be in the next ten years. Today, people are making tall claims about autonomous driving and oh, it\u2019s going to be this year, it\u2019s going to be next year, somebody says fifty years, so there\u2019s 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 these 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.&nbsp;<\/span><span data-contrast=\"auto\">And this Game of Drones goes to the heart of that.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: 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&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">l<\/span><\/b><b><span data-contrast=\"auto\">egal issues, business issues, regulatory issues. So even as Ashish\u2019s team over here is setting up Game of Drones and doing their own research, what\u2019s going on in this other lane?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: You\u2019re absolutely right. You know, this is sort of a brave new world with a whole bunch of new things that you open up. If you\u2019re, let\u2019s say, the city of Bellevue, right? And you know, here you were, just about the time you figure out how to get traffic right and coordinating the lights changing, and you\u2019re driving 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 just start thinking about that problem.&nbsp;<\/span><span data-contrast=\"none\">And so&nbsp;<\/span><span data-contrast=\"none\">how are they<\/span><span data-contrast=\"none\">&nbsp;<\/span><span data-contrast=\"none\">going to<\/span><span data-contrast=\"none\">&nbsp;deal with this really complex world?&nbsp;<\/span><span data-contrast=\"auto\">So, I think, you know, this is an area, some of the areas, that we are starting to look at is, what kind of solutions will they need in a world like this.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Is there, from the business perspective\u2026 because I would assume the researchers are just working on the technology\u2026<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: No\u2026 I think it\u2019s 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.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Okay.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: And just to give you a nugget, in our research group, the perspective that we have is that if their 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 our system&nbsp;<\/span><span data-contrast=\"none\">fails&nbsp;<\/span><span data-contrast=\"auto\">because there was something outside of those specifications, it\u2019s a human\u2019s fault, because as a designer, he didn\u2019t 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 when we say that every mistake needs to be traced to a responsible human who can then take corrective action on it.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: I want to talk a little bit more, Ashish, about something you mentioned on airborne collision avoidances systems and the whole concept of air traffic controls, if we\u2019re talking about flying robots. Even now, that particular job is really high stress and very rule-based for humans, but you\u2019ve painted a picture where we\u2019re going to have hundreds of autonomous vehicles. How do you even begin?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: So, I mean, you\u2019re absolutely right. The job of ATC is one of the most difficult ones, and it\u2019s considered 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\u2019m, again, not using the phrase autonomous, but more about automated decision-making, because\u2026<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Interesting.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: \u2026because, 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.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Okay.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: So that\u2019s where airborne collision avoidance systems comes into effect. If you have these vehicles which are broadcasting their state \u2013&nbsp; so not just flying vehicles, it can be cars as well, it can be forklifts, it can be delivery robots \u2013 but they are broadcasting their state and their intent on what they want to do\u2026<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Okay.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: \u2026then 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\u2019ve been to Japan, you have this intersection Shibuya where the red lights happen across, and I think it\u2019s five or seven different intersections merge together, and you have three hundred, four hundred people crossing at once. And within, you know, 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.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Everything you come up with brings up new things is like, this is research forever, right? Momma needs a new pair of shoes!<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: Totally.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Well, there\u2019s another competition that I\u2019d like to talk about. Ashish, you and a team of collaborators just employed your&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">AirSim<\/span><\/b><b><span data-contrast=\"auto\">&nbsp;technology to win a pretty amazing competition called the DARPA&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">SubT<\/span><\/b><b><span data-contrast=\"auto\">&nbsp;Challenge,&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">SubT<\/span><\/b><b><span data-contrast=\"auto\">&nbsp;standing for subterranean. And you won it rather decisively. So tell us about this challenge and why it was an important proving ground for&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">AirSim<\/span><\/b><b><span data-contrast=\"auto\">.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: 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&nbsp;<\/span><span data-contrast=\"auto\">AirSim<\/span><span data-contrast=\"auto\">&nbsp;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 manmade 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\u2019s very useful if you can have robots that can navigate, that can map, that can go over obstacles and find things. So&nbsp;<\/span><span data-contrast=\"auto\">SubT<\/span><span data-contrast=\"auto\">&nbsp;Challenge is centered around that. And our collaborators at CMU and OSU, they have a pretty amazing robotics system that\u2019s 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&nbsp;<\/span><span data-contrast=\"auto\">environment that\u2019s 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, right?<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Hmm.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: So the simulation environment helps them by validating their methodologies, as well as collecting training data for their perception models. So the competition&nbsp;<\/span><span data-contrast=\"none\">itsel<\/span><span data-contrast=\"none\">f<\/span><span data-contrast=\"none\">&nbsp;<\/span><span data-contrast=\"auto\">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,&nbsp;<\/span><span data-contrast=\"none\">were a survivor<\/span><span data-contrast=\"none\">,<\/span><span data-contrast=\"none\">&nbsp;<\/span><span data-contrast=\"none\">a&nbsp;<\/span><span data-contrast=\"auto\">backpack, a cell phone, a drill and, I believe, a flashlight.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: So this was a real cave?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: This was a real cave.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: And real robots?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: And real robots and there were all these objects. And the team, whoever could go and detect maximum number of these objects, won.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: And so the simulation prior to, gave you an advantage for executing it in real life?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: Yeah. And all the algorithms that were there, whether it be, you know, finding it and planning and all that, would be tested in this simulation environment.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Right.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: And to me, I mean, the biggest thing about this, other than achievement of, you know, winning the DARPA Challenge is always a\u2026<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Cool thing.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: \u2026you know, it\u2019s a pretty&nbsp;<\/span><span data-contrast=\"auto\">swaggy<\/span><span data-contrast=\"auto\">&nbsp;thing. But, to me, what is really interesting about it is 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 this as a tipping point in moving from some of the old ways of doing things towards kind of what we are pushing.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><i><span data-contrast=\"auto\">(music plays)<\/span><\/i><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Well, it\u2019s time for \u201cwhat could possibly go wrong?\u201d on the Microsoft Research podcast, and, when we\u2019re talking about flying robots, the answer is, a lot! So the general&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">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\u2019re addressing those so that I don\u2019t lose sleep at night. Gurdeep?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: Great. Let me first frame it in the context of this industry and Microsoft and what we\u2019ve learned. You know, the good thing is that there\u2019s just a brief history of computing. You know, you don\u2019t have to go back to, you know, 10,000 years. I\u2019ve worked on Windows NT and, you know, we thought we were being very careful about making sure the code can\u2019t be hacked and this and that. We had no idea.&nbsp;<\/span><span data-contrast=\"none\">The&nbsp;<\/span><span data-contrast=\"auto\">moment the internet got connected and these machines got 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\u2019t afford to see that happen in the autonomous systems space.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host:&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">M<\/span><\/b><b><span data-contrast=\"auto\">mm<\/span><\/b><b><span data-contrast=\"auto\">.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: 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 AETHER, I\u2019m a huge fan of that because I think, as a company, we\u2019ve said we\u2019re going to proactively look at AI all up and, you know, identify some of these things. And I think, in our case in particular, we\u2019re 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 \u201ctrustworthy autonomy.\u201d And we 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.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Ashish, what would you add?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: Yeah, so\u2026<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: What keeps you up at night?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: I mean all those things that Gurdeep mentioned, but I\u2019ll mentioned one specific thing, which keeps me up at night because something that, you know, as a researcher or a technologist, it\u2019s hard for me to influence. We are making progress. We are thinking about it. And the 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.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host:&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">M<\/span><\/b><b><span data-contrast=\"auto\">mm<\/span><\/b><b><span data-contrast=\"auto\">.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: And I\u2019m 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\u2019ll play by regulation, right? However, many of those bad actors will not. So I think that\u2019s a tension that I don\u2019t know how to resolve.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: So as you two have identified some things that I think nobody would argue, these are the highest level \u201cwhat keeps me up at nights\u201d on the planet\u2026 Aside from thinking about it, are there things that you\u2019re kind of building or baking into your research and your execution that would say, hey, we\u2019ve got this?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: Absolutely. In fact, I think Ashish should talk about some of the research work that he\u2019s been doing and we are actively looking to see how we can productize that\u2026<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Okay.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: \u2026as part of our trustworthy autonomy pillar and feature set. So, yes, we are actively looking at that.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: You want to talk about that\u2026&nbsp;<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: Yeah, yeah.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: So safety is very important. Not from the point of view of, you know, a hacker attacking a system, our cyber-security flaws and things like those, but also from the fundamental technology point-of-view.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Hmm.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: So for instance, your robots, or your autonomous systems, they will have sensors and they will 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\u2019s a big question that we are trying to answer. And the way we are thinking about this is now building policies that are optimal in the worst case.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host:&nbsp;<\/span><\/b><b><span data-contrast=\"auto\">M<\/span><\/b><b><span data-contrast=\"auto\">mm<\/span><\/b><b><span data-contrast=\"auto\">.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: So, we need to look down to history and things about how airplanes and spaceships were designed. You know, they solved a very 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&nbsp;<\/span><span data-contrast=\"auto\">need to learn from those fields and we need to look at the technologies they employed. So that\u2019s, you know, in a nutshell, that\u2019s what we\u2019re looking into.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: At the end of every podcast I give my guests the opportunity to say anything they want to our listeners. So Gurdeep and Ashish, do you have any parting advice, warning, wisdom or predictions? What challenges lie ahead for autonomous systems in your minds?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: 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\u2019s quite hard to get started on it, but I\u2019m 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\u2019re 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.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Hmm. Gurdeep? Last words?<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: You know, humans overestimate what can happen in three years and underestimate what happens in ten years. And we are embarking on another one of those moments where I think ten years from now, the world is going to be very, very, very different. And it\u2019s inevitable. So it\u2019s not like you know, let\u2019s 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.&nbsp;<\/span><span data-contrast=\"none\">Y<\/span><span data-contrast=\"none\">ou know,&nbsp;<\/span><span data-contrast=\"auto\">I have to remind people that it\u2019s only a couple years ago, the iPhone was ten years old. And when the iPhone came out, nobody could have predicted how it changed lives. And I think you could say that with the internet, you can say that with the 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.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Host: Gurdeep Pall, Ashish Kapoor, thank you for making Episode 100&nbsp;<\/span><\/b><b><i><span data-contrast=\"auto\">this<\/span><\/i><\/b><b><span data-contrast=\"auto\">&nbsp;fantastic.<\/span><\/b><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Gurdeep Pall: Thanks for having us.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><span data-contrast=\"auto\">Ashish Kapoor: Thank you very much.<\/span><span data-ccp-props=\"{\"201341983\":0,\"335559685\":720,\"335559740\":240,\"335559991\":720,\"469777462\":[1620],\"469777927\":[0],\"469777928\":[1]}\">&nbsp;<\/span><\/p>\n<p><b><i><span data-contrast=\"auto\">To learn more about how Microsoft is working to bring emergent AI into real world applications, visit Microsoft.com\/research<\/span><\/i><\/b><\/p>\n","protected":false},"excerpt":{"rendered":"<p>There\u2019s 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\u2019s 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. On the podcast, 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\u2026 on the fly.<\/p>\n","protected":false},"author":39507,"featured_media":624393,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"msr-url-field":"https:\/\/player.blubrry.com\/id\/52267015\/","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":[],"msr_hide_image_in_river":0,"footnotes":""},"categories":[240054],"tags":[243900,243906,243912,243918,243915,186418,243909,243903,215279],"research-area":[13556],"msr-region":[],"msr-event-type":[],"msr-locale":[268875],"msr-post-option":[],"msr-impact-theme":[],"msr-promo-type":[],"msr-podcast-series":[],"class_list":["post-624378","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-msr-podcast","tag-airsim","tag-autonomous-agents","tag-autonomous-systems","tag-drone-racing-competition","tag-game-of-drones","tag-machine-learning","tag-open-world","tag-simulated-environment","tag-simulation","msr-research-area-artificial-intelligence","msr-locale-en_us"],"msr_event_details":{"start":"","end":"","location":""},"podcast_url":"https:\/\/player.blubrry.com\/id\/52267015\/","podcast_episode":"","msr_research_lab":[],"msr_impact_theme":[],"related-publications":[],"related-downloads":[],"related-videos":[],"related-academic-programs":[593767],"related-groups":[237595],"related-projects":[669597,607743,359810],"related-events":[609480],"related-researchers":[],"msr_type":"Post","featured_image_thumbnail":"<img width=\"960\" height=\"540\" src=\"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-960x540.png\" class=\"img-object-cover\" alt=\"Gurdeep Pall and Ashish Kapoor on the Microsoft Research Podcast\" decoding=\"async\" loading=\"lazy\" srcset=\"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-960x540.png 960w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-300x169.png 300w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-1024x576.png 1024w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-768x432.png 768w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-1066x600.png 1066w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-655x368.png 655w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-343x193.png 343w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-640x360.png 640w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788-1280x720.png 1280w, https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-content\/uploads\/2019\/11\/Research_Podcast_Ashish-and-Gurdeep_Site_10_2019_1400x788.png 1400w\" sizes=\"auto, (max-width: 960px) 100vw, 960px\" \/>","byline":"","formattedDate":"November 27, 2019","formattedExcerpt":"There\u2019s 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\u2019s why Gurdeep Pall, CVP of Business AI at Microsoft, and Dr. Ashish Kapoor,&hellip;","locale":{"slug":"en_us","name":"English","native":"","english":"English"},"_links":{"self":[{"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/posts\/624378","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/users\/39507"}],"replies":[{"embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/comments?post=624378"}],"version-history":[{"count":4,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/posts\/624378\/revisions"}],"predecessor-version":[{"id":896304,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/posts\/624378\/revisions\/896304"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/media\/624393"}],"wp:attachment":[{"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/media?parent=624378"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/categories?post=624378"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/tags?post=624378"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=624378"},{"taxonomy":"msr-region","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-region?post=624378"},{"taxonomy":"msr-event-type","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-event-type?post=624378"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=624378"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=624378"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=624378"},{"taxonomy":"msr-promo-type","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-promo-type?post=624378"},{"taxonomy":"msr-podcast-series","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-podcast-series?post=624378"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}