WEBVTT - Technically Speaking (An Intel Podcast): A Safer World With AI Digital Twins 0:00:04.480 --> 0:00:12.280 Welcome to tech Stuff, a production from iHeartRadio. Hey they're 0:00:12.360 --> 0:00:16.000 tech Stuff fans. This is Jonathan Strickland speaking. I've got 0:00:16.000 --> 0:00:19.920 something special for y'all today. What follows is an episode 0:00:20.000 --> 0:00:24.720 from season two of our podcast technically Speaking. This particular 0:00:24.800 --> 0:00:28.880 episode is about digital twins, which I thought was a 0:00:28.920 --> 0:00:32.280 really fascinating topic. It was one that I wasn't actually 0:00:32.320 --> 0:00:36.000 really familiar with, and I learned a lot and I 0:00:36.000 --> 0:00:39.520 hope you will too. So check this out, and if 0:00:39.560 --> 0:00:42.599 you enjoy it, make sure you go and subscribe to 0:00:42.800 --> 0:00:48.040 technically Speaking. You've got two seasons of really cool material 0:00:48.360 --> 0:00:51.560 in those episodes, so check that out. And I hope 0:00:51.560 --> 0:00:53.120 you enjoy this episode. 0:00:55.040 --> 0:00:58.320 Where do world changing ideas get This start at Intel. 0:00:58.400 --> 0:01:01.440 It starts with real solutions, and real solutions start with 0:01:01.560 --> 0:01:06.560 exceptional engineering, the quantum computing revolution, the next generation of 0:01:06.600 --> 0:01:10.640 AI experts, the renewable energy grid, liquid cooling, data centers, 0:01:10.720 --> 0:01:14.800 early diagnosis for cancer, water restoration, and even farmland protection. 0:01:15.160 --> 0:01:18.440 The examples are countless, the impacts are endless, but the 0:01:18.520 --> 0:01:22.200 foundation is always the same. It starts with Intel. Join 0:01:22.319 --> 0:01:25.120 us in redefining what's achievable through the power of AI. 0:01:25.680 --> 0:01:34.160 Learn more at Intel Dot com slash stories. Workplaces like 0:01:34.240 --> 0:01:37.920 factories or fulfillment centers are filled with many moving parts 0:01:38.120 --> 0:01:43.480 and require constant supervision and alertness to ensure worker safety. 0:01:44.920 --> 0:01:48.440 But what happens when errors or accidents happen unexpectedly On 0:01:48.520 --> 0:01:51.840 the simplest level, it creates chaos and can impact productivity. 0:01:52.240 --> 0:01:55.520 On a larger scale, can create a dangerous environment for employees. 0:01:56.240 --> 0:01:59.480 How can technology like AI and the creation of a 0:01:59.520 --> 0:02:03.800 digital twe in help quickly correct errors and prevent accidents 0:02:04.080 --> 0:02:07.640 before they occur? And could these virtual replications of a 0:02:07.640 --> 0:02:11.400 physical space ensure workers go home to their families safe 0:02:11.400 --> 0:02:14.680 and sound. Join us as we learn more about the 0:02:14.720 --> 0:02:17.840 world of digital twins and the many ways they can 0:02:17.880 --> 0:02:25.240 not only improve workplace safety, but also public safety. Welcome 0:02:25.280 --> 0:02:28.960 to Technically Speaking, an Intel podcast, the show that brings 0:02:29.000 --> 0:02:32.720 you the stories and insights of AI, presented by iHeartMedia's 0:02:32.840 --> 0:02:38.239 Ruby Studio and Intel. Hey then, I'm gram class. Today, 0:02:38.360 --> 0:02:42.160 we're exploring the spaces and places replicated by digital twins. 0:02:42.800 --> 0:02:46.400 For starters, what is a digital twin? We're going to 0:02:46.440 --> 0:02:50.040 be examining digital spaces that represent an actual physical space 0:02:50.200 --> 0:02:53.520 in our world. To discuss the topic further, We're joined 0:02:53.560 --> 0:02:59.360 by Tony Franklin. Tony Franklin is the general manager of 0:02:59.400 --> 0:03:03.800 the Federal and Aerospace Markets, which includes military, aerospace, and 0:03:03.840 --> 0:03:06.480 government within the Network and Edge Group. He has more 0:03:06.520 --> 0:03:10.960 than twenty years of corporate entrepreneurial, business development and management experience, 0:03:11.560 --> 0:03:15.120 focusing on starting and growing multiple businesses that apply to 0:03:15.320 --> 0:03:21.000 the Internet of Things, intelligence systems, and communications technologies. Intel's 0:03:21.000 --> 0:03:23.960 Network and Edge Group provide solutions that lead the industry 0:03:23.960 --> 0:03:27.120 and transforming businesses and the way we live. Are making 0:03:27.160 --> 0:03:30.080 it simple to create exciting new diet solutions. 0:03:30.800 --> 0:03:35.040 Welcome to the show, Tony, Thank you, thank you, glad 0:03:35.040 --> 0:03:35.560 to be here. 0:03:35.840 --> 0:03:39.040 We've seen a lot of science fiction depictions of digital 0:03:39.040 --> 0:03:41.760 twins over the years and movies and films. The one 0:03:41.760 --> 0:03:44.400 that comes to mind is the Matrix, where the entire 0:03:44.440 --> 0:03:48.200 world is the digital twin. Although it's a useful sinister motives, 0:03:48.960 --> 0:03:51.040 I'd like to get your definition of what a digital 0:03:51.040 --> 0:03:51.480 twin is. 0:03:52.080 --> 0:03:54.040 Yeah. Sure, it's interesting you said the matrix. 0:03:54.080 --> 0:03:56.200 I had to laugh because of all the examples we've 0:03:56.280 --> 0:03:58.680 joked about, that's one that hasn't come up, and it's 0:03:58.760 --> 0:04:01.360 so obvious when you said, I'll start to use that 0:04:02.280 --> 0:04:04.600 in its simplest form for me, a digital twin is 0:04:04.760 --> 0:04:07.240 the digital replica of the real world. 0:04:07.920 --> 0:04:11.360 And in terms of the technologies that are out there 0:04:11.920 --> 0:04:16.000 needed for digital twining, maybe you could describe a little 0:04:16.000 --> 0:04:20.160 bit of how those sorts of systems are put together 0:04:20.279 --> 0:04:24.160 and what are some of the technology that Intel has 0:04:24.279 --> 0:04:25.200 that can help that. 0:04:25.920 --> 0:04:26.200 Yeah. 0:04:26.240 --> 0:04:30.400 Sure, it's really been an evolution of technologies that some 0:04:30.480 --> 0:04:32.679 of them were all used to using, and some of them, 0:04:32.800 --> 0:04:34.279 you know, if you're not in the field, maybe not 0:04:34.360 --> 0:04:37.800 so much. And so Gartner, one of the well known analysts, 0:04:37.839 --> 0:04:42.239 has this Emerging Technologies trending chart they do every year, 0:04:42.800 --> 0:04:46.360 and they talk about edge AI, so artificial intelligence at 0:04:46.400 --> 0:04:49.080 the edge, you know, the place where data is actually 0:04:49.120 --> 0:04:51.320 being generated more so than in say the cloud or 0:04:51.400 --> 0:04:55.400 data centers. That's happening, It continues to evolve, it's growing 0:04:55.440 --> 0:04:57.760 more and more. We're pushing more and more intelligence to 0:04:57.880 --> 0:04:59.520 the edge. And by the edge, it could be everything 0:04:59.520 --> 0:05:01.479 from a self phone or refrigerator or a car. 0:05:01.640 --> 0:05:04.000 Again, where is the data actually being generated? 0:05:04.760 --> 0:05:07.640 And then they talk about digital twins being sort of 0:05:07.680 --> 0:05:10.240 the now to three years. I think one of their 0:05:10.400 --> 0:05:14.400 data points was something like forty percent of businesses large 0:05:14.400 --> 0:05:17.120 businesses in particular plan to use digital twins over the 0:05:17.160 --> 0:05:19.600 next two to three years to actually generate revenue, So 0:05:19.640 --> 0:05:22.479 that's happening now, and then lastly over the next maybe 0:05:22.560 --> 0:05:25.000 six plus years, they talk about the metaverse. Now, while 0:05:25.000 --> 0:05:27.680 we don't generally talk about the metaverse as much, the 0:05:27.800 --> 0:05:30.000 name means different things to different people, but it's the 0:05:30.040 --> 0:05:33.720 full extent of how it was. Commerce and any other 0:05:33.800 --> 0:05:38.520 business really leverage a fully digital space that has interaction 0:05:38.800 --> 0:05:42.040 with the real world. So there's this spectrum that has 0:05:42.080 --> 0:05:45.800 been happening between sensors, with cameras being the most obvious 0:05:46.000 --> 0:05:49.560 because we're all using cameras today. Our phones have so 0:05:49.600 --> 0:05:52.640 many censers we take them for granted, but all the sensors. 0:05:52.640 --> 0:05:56.039 One of the key technologies that are needed an ability 0:05:56.080 --> 0:06:00.280 to replicate if you're doing visual digital twins, so an 0:06:00.320 --> 0:06:03.520 ability to replicate the real world, and of course physics 0:06:03.520 --> 0:06:05.960 modeling if you're really doing analysis and you need to 0:06:06.000 --> 0:06:10.600 replicate the physical asset in a digital world, So computing 0:06:10.760 --> 0:06:15.560 capability to be able to replicate the behavior of the object, 0:06:16.120 --> 0:06:19.040 with AI being a critical component to now actually apply 0:06:19.360 --> 0:06:23.240 intelligence and analysis to the twin. So when you think 0:06:23.240 --> 0:06:25.880 about those different areas well. Intel, we don't make sensors. 0:06:26.000 --> 0:06:28.839 Everything else along the way is where we tend to 0:06:28.839 --> 0:06:32.800 play clearly, computing technology, the ability to apply AI, so 0:06:33.080 --> 0:06:36.880 both from the software side and the various different computing 0:06:36.960 --> 0:06:42.400 technologies that enable AI, whether it's processors or GPUs, are 0:06:42.880 --> 0:06:46.080 AI accelerators, et cetera. And then of course we have 0:06:46.160 --> 0:06:50.880 a very broad, really world class partnership and ecosystem that 0:06:50.960 --> 0:06:53.240 we work with to enable the different industries. 0:06:54.000 --> 0:06:56.240 Okay, and in terms of trying to get like a 0:06:56.320 --> 0:07:00.640 visual kind of representation of what this would clients say, say, 0:07:00.680 --> 0:07:03.960 if you're walking in a warehouse, for example, and you're 0:07:03.960 --> 0:07:05.880 looking at the shelves around you, you might see some 0:07:05.920 --> 0:07:10.200 conveyor belts. How would it actually look in a digital twin. 0:07:10.960 --> 0:07:15.280 It depends on the use case. The simplest version i'd 0:07:15.360 --> 0:07:17.920 use that many people should be able to relate to Obviously, 0:07:17.920 --> 0:07:21.040 many people can relate to matrix. But from an application standpoint, 0:07:21.560 --> 0:07:25.640 I would say think about Google Earth or Google Maps. 0:07:25.720 --> 0:07:30.120 Even that is a type of model right. Another example 0:07:30.200 --> 0:07:35.000 is many of the retail applications allow you to basically 0:07:35.400 --> 0:07:40.400 embed their items that are for sale into the digital 0:07:40.440 --> 0:07:44.600 replication of your particular space. So it's a real world 0:07:45.000 --> 0:07:47.440 and digital combination. That's always the key. 0:07:47.720 --> 0:07:51.080 So those are very basic, simple applications that people use 0:07:51.280 --> 0:07:53.160 and don't even realize. They don't think about them as 0:07:53.160 --> 0:07:56.440 digital twins, but they're already getting used to this relationship 0:07:56.480 --> 0:07:59.120 between the real world and the digital world. 0:07:59.640 --> 0:08:00.320 Yes, I saw. 0:08:00.360 --> 0:08:03.480 Intel has a software platform called Scenescape that can transform 0:08:03.560 --> 0:08:06.240 data from this world of senses to create a real 0:08:06.280 --> 0:08:09.160 time digital twin of your physical space. Can you tell 0:08:09.200 --> 0:08:11.320 me a little bit more of how that works? So 0:08:11.320 --> 0:08:14.560 there's really three basic steps. One is mapping your space. 0:08:15.080 --> 0:08:18.520 The key though in the type of real time digital 0:08:18.560 --> 0:08:23.720 twinning that we pursue is it is a coordinate, accurate space, 0:08:23.920 --> 0:08:26.280 so it's not just taking a random space. We know 0:08:26.400 --> 0:08:28.520 that that room is twenty feet by twenty five feet, 0:08:28.520 --> 0:08:31.960 and we also know that the cameras are six feet 0:08:32.040 --> 0:08:35.840 up on the wall. We know the actual XYZ of 0:08:35.880 --> 0:08:38.640 the space, So that's the first step. Second step is 0:08:39.120 --> 0:08:42.360 calibrate the space. So calibrate meaning I have the space, 0:08:42.800 --> 0:08:45.560 where are my sensors? So my sensor is ten feet up, 0:08:45.600 --> 0:08:48.440 four feet over in that corner, et cetera. Now you 0:08:48.520 --> 0:08:52.000 turn on your sensors and you ingest that into scenescape. 0:08:52.200 --> 0:08:56.280 Notice I haven't actually visualized necessarily anything. So the key 0:08:56.400 --> 0:08:59.400 for people to realize in real time digital twinning. There 0:08:59.400 --> 0:09:01.800 are some applications where someone's not actually going to be 0:09:01.800 --> 0:09:05.440 sitting there watching the digital twin of the store. They 0:09:05.440 --> 0:09:09.280 don't need to do that real time. The AI and 0:09:09.600 --> 0:09:13.520 computing obviously, the AI tools and the actual AI models, 0:09:13.920 --> 0:09:18.719 the inferencing capability of scenescape is doing the work. You 0:09:18.760 --> 0:09:22.320 are configuring it so you could add things like heat 0:09:22.400 --> 0:09:25.880 maps or trip wise so that you can actually have 0:09:26.200 --> 0:09:30.640 events based on whatever policy you want to implement, so 0:09:30.760 --> 0:09:33.760 that you don't have to actually monitor. So I'll know 0:09:33.880 --> 0:09:37.319 that over in this area of the meat department, if 0:09:37.320 --> 0:09:40.320 there's more than twenty people for twenty seconds, there's something 0:09:40.320 --> 0:09:43.160 that happens. I don't even have to watch anything for that. 0:09:43.480 --> 0:09:47.480 The intelligence is making it happen now. If what I 0:09:47.520 --> 0:09:51.320 want to do later is now hit the rewind button. 0:09:51.480 --> 0:09:54.200 The founder and creator for this particular product, he has 0:09:54.200 --> 0:09:57.120 a phrase I'd love to use. It's called the DVR 0:09:57.240 --> 0:10:00.840 for the real world. AI is happening real time, but 0:10:00.920 --> 0:10:04.520 if you want additional analysis afterwards, you have that capability. 0:10:05.120 --> 0:10:07.679 I can imagine there's a lot of challenges trying to 0:10:07.920 --> 0:10:10.760 come up with these digital twins. What are some of 0:10:10.840 --> 0:10:14.839 the top challenges or issues that people who are looking 0:10:14.880 --> 0:10:17.760 to try and deploy these sorts of systems would have 0:10:17.840 --> 0:10:18.400 to consider. 0:10:19.160 --> 0:10:23.440 The most prominent one, to be honest with you, is 0:10:23.600 --> 0:10:27.920 the mindset more than anything technical. You think about some 0:10:28.040 --> 0:10:31.559 of the technology that's growing in our own home, siy 0:10:31.880 --> 0:10:36.880 alexa are cars. There's so much technology, and most people 0:10:36.920 --> 0:10:40.920 really don't understand you're already using AI. In many cases, 0:10:40.920 --> 0:10:44.000 you're already using some sort of digital twin technology. There 0:10:44.040 --> 0:10:46.520 was one demo we had for Scenescape and the executive 0:10:46.600 --> 0:10:48.640 loved it. It's like, this is amazing. I can do 0:10:48.720 --> 0:10:51.280 motion tracking. I see where people are. I can have 0:10:51.400 --> 0:10:55.800 multiple cameras monitoring the same asset, our person or object, 0:10:55.800 --> 0:10:58.559 but I only see one, so it deduplicates the person. 0:10:59.160 --> 0:11:01.800 I can track with somebody's been in a space. Maybe 0:11:01.800 --> 0:11:04.600 I have a radiation sensor and I can actually track 0:11:04.679 --> 0:11:06.720 how long that person has been in the space, and 0:11:06.760 --> 0:11:09.520 I can set triggers. There's so much he saw that 0:11:09.559 --> 0:11:12.800 can be done, and he was so excited and he said, 0:11:12.800 --> 0:11:15.680 where's the AI, right, Well, it's the AI that's doing 0:11:15.720 --> 0:11:19.440 everything you just described. That's right, you just and it 0:11:19.520 --> 0:11:21.920 actually set us back for a second. We're like, well, clearly, 0:11:22.520 --> 0:11:24.600 we need to make sure we understand where people are 0:11:24.679 --> 0:11:28.040 starting from. We can't assume they already know there's a 0:11:28.120 --> 0:11:31.959 level of technology and integration of their technology. 0:11:33.440 --> 0:11:35.400 And that's one of the biggest challenges when it comes 0:11:35.440 --> 0:11:39.559 to understanding digital twin technology. It's the messaging some of 0:11:39.600 --> 0:11:42.360 the very tools that you're accustomed to right now, like 0:11:42.520 --> 0:11:44.719 the cell phone or the smart speaker that you are 0:11:44.800 --> 0:11:48.320 listening to this podcast with essential when we consider the 0:11:48.320 --> 0:11:50.800 future of digital twining. So when it comes to a 0:11:50.840 --> 0:11:54.800 future that incorporates AI into our daily lives, we've actually 0:11:54.920 --> 0:12:00.199 already taken the first steps down that path. One of 0:12:00.240 --> 0:12:03.720 the things I like to examine is the way that 0:12:04.200 --> 0:12:08.319 technology actually helps democratize. And maybe you have some sense 0:12:08.360 --> 0:12:12.400 of the type of customers. Are they sort of large enterprises, 0:12:12.440 --> 0:12:15.160 because I'm really keen to see this sort of technology 0:12:15.240 --> 0:12:18.840 really get pushed down to the smaller businesses, you know, 0:12:19.000 --> 0:12:21.400 and make it affordable for them to adopt and use. 0:12:21.840 --> 0:12:24.120 Do you have any thoughts about that particular trend. 0:12:24.440 --> 0:12:29.760 Yeah, absolutely, I'd say they're all generally larger enterprises, but 0:12:29.840 --> 0:12:33.200 they may be larger enterprises with smaller facilities, so they 0:12:33.240 --> 0:12:36.120 have to think about the implementation at the store level, 0:12:36.480 --> 0:12:38.400 and then they can step back and look at it 0:12:38.440 --> 0:12:41.480 at an operational level for the entire business that they're 0:12:41.480 --> 0:12:44.960 trying to run. When you think about physical security, well, 0:12:45.000 --> 0:12:47.560 physical security can happen on a construction site, it can 0:12:47.640 --> 0:12:50.440 happen in an office space, it can happen anywhere. But 0:12:50.520 --> 0:12:53.400 the companies we're dealing with are generally the companies that 0:12:53.920 --> 0:12:56.520 one have the actual technology, so they may be the 0:12:56.520 --> 0:12:59.920 camera vendors, et cetera. But whereas actually being implemented the 0:13:00.200 --> 0:13:04.160 targeting a broad range in particular segments like I mentioned, 0:13:04.559 --> 0:13:07.199 but the actual implementation may happen at a different level. 0:13:07.320 --> 0:13:11.560 So it's the companies that apply technology across specific segments 0:13:11.880 --> 0:13:15.520 and then they actually tear those down. Cities can be 0:13:15.640 --> 0:13:18.840 large or they can be smaller, but you're implementing generally 0:13:19.160 --> 0:13:22.760 starting at an intersection level, so that could be maybe 0:13:22.840 --> 0:13:26.880 four cameras max. But now I've got a thousand intersections, 0:13:27.320 --> 0:13:30.120 so it grows in scales, and what we're seeing back 0:13:30.120 --> 0:13:32.600 to that early adopter, we see the big picture. 0:13:32.679 --> 0:13:33.120 Let's start with. 0:13:33.160 --> 0:13:36.960 Three intersections, and let's see and understand where technology can 0:13:37.000 --> 0:13:39.480 be applied there. Because one of the ways I like 0:13:39.520 --> 0:13:43.120 to explain to people, you need to understand the environment 0:13:43.200 --> 0:13:45.640 the scene. That's what it's called scenes. Gape the scene, 0:13:46.200 --> 0:13:48.960 the area, your environment better. That's one way to think 0:13:49.000 --> 0:13:50.800 about digital twin being able to enable that. 0:13:54.120 --> 0:13:58.720 Coming out next on Technically Speaking and Intel podcast, I. 0:13:58.640 --> 0:14:01.040 Am the ultimate digital twin that I watch. I don't 0:14:01.040 --> 0:14:03.840 care about an avatar that's fun and fancy. I was 0:14:03.840 --> 0:14:05.920 something that helps improuse my quality of light. 0:14:07.240 --> 0:14:09.320 We'll be right back after a brief message from our 0:14:09.360 --> 0:14:21.560 partners at Intel. Where do world changing ideas get their start? 0:14:22.280 --> 0:14:25.840 At Intel? It starts with real solutions, and real solutions 0:14:25.840 --> 0:14:30.080 start with exceptional engineering. Empowering those with disabilities starts with 0:14:30.160 --> 0:14:34.280 assistive AI, and stopping crop loss from infestation starts with 0:14:34.360 --> 0:14:38.760 thermal imaging and open technology, while artificial intelligence that predicts 0:14:38.760 --> 0:14:43.040 depression starts with educational programs like Intel's AI for Youth. 0:14:43.840 --> 0:14:48.680 And that's just the start the quantum computing revolution. The 0:14:48.720 --> 0:14:54.080 next generation of AI experts the renewable energy grid, liquid cooling, 0:14:54.160 --> 0:14:59.800 data centers, radiation exposure prevention in space, water restoration, and 0:15:00.000 --> 0:15:04.880 early cancer detection. The examples are countless, the impacts are endless, 0:15:05.400 --> 0:15:09.520 but the foundation is always the same. It starts with Intel. 0:15:10.720 --> 0:15:20.240 Learn more at Intel dot com, Forward Slash Stories. Welcome 0:15:20.280 --> 0:15:23.600 back to Technically Speaking, an Intel podcast. I'm here now 0:15:23.680 --> 0:15:29.360 with Intel's own Tony Franklin. Do you have any other 0:15:29.400 --> 0:15:34.120 examples of benefits that your customers have seen, whether it 0:15:34.120 --> 0:15:36.960 be productivity, increase, revenue, better, safety. 0:15:37.640 --> 0:15:40.080 Yeah, I'll go on reverse since you said safety last, 0:15:40.080 --> 0:15:43.640 because that's one that is so common yep to people. 0:15:43.680 --> 0:15:45.960 In fact, I think it was the university in Texas 0:15:46.760 --> 0:15:50.200 that has doing some pilots with the cities and with 0:15:50.360 --> 0:15:54.000 smart vehicles. And it's a device called a roadside unit. Again, 0:15:54.000 --> 0:15:55.800 most people don't even realize that you pull up to 0:15:55.800 --> 0:15:59.160 an intersection, there's normally a smaller box on the side. 0:15:59.320 --> 0:16:02.920 You already have the box that controls the lights, etc. Well, 0:16:02.960 --> 0:16:04.960 I want to do more so you can make that 0:16:05.080 --> 0:16:07.960 unit more intelligent. You can actually allow that roadside unit 0:16:08.040 --> 0:16:10.920 to communicate with cars. As cars become more intelligent, they 0:16:10.920 --> 0:16:13.720 have five G, they have wireless communications. So they implemented 0:16:13.760 --> 0:16:16.760 a pilot where there was a particular intersection, so as 0:16:16.760 --> 0:16:19.960 the car pulls up. Imagine an alley off to the left, 0:16:20.280 --> 0:16:23.800 so the car can't see down the alley clearly, but 0:16:23.840 --> 0:16:26.000 there's a pole on the right that has a camera. 0:16:26.120 --> 0:16:28.280 The camera can see the car coming. The camera can 0:16:28.320 --> 0:16:30.840 see down the alley. The camera has a roadside unit 0:16:31.080 --> 0:16:35.360 with intel processing equipment. It's running scene skate again. They 0:16:35.360 --> 0:16:40.080 don't even need to visualize this. The camera sees someone 0:16:40.160 --> 0:16:43.720 walking down the alley, the car is coming forward. It 0:16:43.720 --> 0:16:46.200 can communicate to the car because even the cars with 0:16:46.240 --> 0:16:48.920 the cameras can't see around corners, so the camera can 0:16:48.960 --> 0:16:52.080 communicate there is somebody walking. You need to slow down. 0:16:52.520 --> 0:16:55.360 Knowing the speed of the car is great acceleration, we 0:16:55.440 --> 0:16:58.040 understand that, but knowing where that car is at the 0:16:58.040 --> 0:16:59.920 speed of a car coming down the highway is one thing. 0:17:00.120 --> 0:17:02.200 The speed of a car coming down that street where 0:17:02.200 --> 0:17:05.440 there's an alley is a totally different scenario. I need 0:17:05.480 --> 0:17:07.800 to know the location of that car relative to the 0:17:07.840 --> 0:17:11.040 camera and relative to the person around the corner, both 0:17:11.080 --> 0:17:13.680 coming at the same time. So three D is also 0:17:13.720 --> 0:17:16.680 a key aspect and value of digital twin That translates 0:17:16.960 --> 0:17:19.480 to end benefit like you're talking about. So that's safety 0:17:19.560 --> 0:17:22.720 right there, and that safety translates to insurance as an example. 0:17:23.240 --> 0:17:28.720 Yeah, just fitting off that safety theme. Can technologies like 0:17:28.800 --> 0:17:34.120 scenescape and having those sort of cameras help with worker safety, 0:17:34.160 --> 0:17:39.040 say in a factory or warehouse, where they can detect 0:17:39.200 --> 0:17:41.960 or even predict, you know, if something's going to go 0:17:42.040 --> 0:17:45.760 wrong and actually warn a worker that something's going to happen. 0:17:46.280 --> 0:17:47.080 Yeah. Absolutely. 0:17:47.200 --> 0:17:50.639 Robot interaction is a common one also, so think about 0:17:50.840 --> 0:17:54.720 robots with cameras and the cameras and sensors that are 0:17:54.760 --> 0:17:58.320 around Mobile World Congress is going on right now, and 0:17:58.400 --> 0:18:00.520 I think it was last year. We did a escape 0:18:00.520 --> 0:18:03.080 demo there and it was purely an industrial We had 0:18:03.119 --> 0:18:06.720 the robotic arms that were moving and they were building something. 0:18:07.119 --> 0:18:09.080 And then you have a sensor doesn't even need to 0:18:09.080 --> 0:18:11.640 be a camera that has a digital n scen escape 0:18:11.640 --> 0:18:14.880 the trip wire, so we know if somebody crosses this point, 0:18:15.440 --> 0:18:17.400 then it's a trip wire. So that was the actual demo. 0:18:17.720 --> 0:18:19.600 So there was a safety zone and then there was 0:18:19.680 --> 0:18:22.160 crossing the safety zone. So if you enter the safety zone, 0:18:22.200 --> 0:18:23.560 there could be a warning light to go off. You 0:18:23.560 --> 0:18:25.800 don't have to stop anything, but I know someone's in 0:18:25.840 --> 0:18:27.840 the safety zone, I know how long they've been in 0:18:27.880 --> 0:18:30.520 the safety zone and if they cross past that, then 0:18:30.560 --> 0:18:32.960 I know I can start to shut down automatically equipment 0:18:33.160 --> 0:18:36.479 if that's the policy that that particular site chooses to use. 0:18:36.480 --> 0:18:39.800 So I think can execute another one in a more 0:18:40.000 --> 0:18:44.960 constrained environment warehouse that we've seen is where there's actually 0:18:45.359 --> 0:18:50.119 a controlled space, so radiation. Actually, the earlier example I 0:18:50.160 --> 0:18:52.959 talked about is a real example where there's an area 0:18:53.040 --> 0:18:55.960 that it needs to be climate controlled and it literally 0:18:56.000 --> 0:18:58.640 has radiations. So they have a radiation sensor both inside 0:18:58.640 --> 0:19:01.200 outside and commodity or do you have the equipment on 0:19:01.720 --> 0:19:04.760 how long has a person been in this particular space, 0:19:05.119 --> 0:19:07.520 and I could set timers and triggers so I know 0:19:07.600 --> 0:19:09.600 that they can only be in for so long, and 0:19:09.640 --> 0:19:12.760 I can also track that. So that's real time action 0:19:12.880 --> 0:19:15.480 and control, and I can also use that for later 0:19:15.600 --> 0:19:18.480 analysis and prediction. Maybe I need to change the configuration 0:19:18.520 --> 0:19:20.360 of the room, maybe I need to put more signs up, 0:19:20.640 --> 0:19:23.479 But you can have real time action and decisions and 0:19:23.600 --> 0:19:25.040 also post analysis. 0:19:25.640 --> 0:19:28.879 Yeah, what you said there about the simulation is quite 0:19:29.080 --> 0:19:32.119 interesting because you know, as you're talking else, you know 0:19:32.359 --> 0:19:35.320 it came back to the gaming side of things, playing 0:19:35.359 --> 0:19:39.240 SimCity or roller coaster tycoon being able to sort of 0:19:39.280 --> 0:19:41.720 simulate you know, if I put this thing here, is 0:19:41.760 --> 0:19:42.560 it going to be dangerous? 0:19:42.600 --> 0:19:45.000 If I put that over there? Does that help the workers? 0:19:45.040 --> 0:19:46.320 Does it help with productivity? 0:19:46.840 --> 0:19:50.760 Maybe talk a little bit of some examples of using 0:19:50.800 --> 0:19:54.440 real world data to kind of do what if analysis 0:19:54.520 --> 0:19:59.760 of various scenarios that management and workers together can can 0:19:59.760 --> 0:20:02.840 see mille and potentially improve the workplace. 0:20:03.720 --> 0:20:06.280 So let's take something like a gaming site, I mean 0:20:06.320 --> 0:20:11.400 like a football or soccer So clearly those are massive 0:20:11.480 --> 0:20:14.440 events with a lot of people, a lot of insurances, 0:20:14.520 --> 0:20:19.200 there's safety concerns, there's access to medical professionals that need 0:20:19.240 --> 0:20:22.680 to get in and out. So can I take existing 0:20:22.920 --> 0:20:27.159 data that has already been captured using existing cameras and 0:20:27.200 --> 0:20:29.680 I can actually run simulations on that. I could also 0:20:30.400 --> 0:20:32.280 ideally what I want and I need it. If I'm 0:20:32.280 --> 0:20:33.960 going to do a digital twin, I need some sort 0:20:34.000 --> 0:20:37.040 of digital twin of the environment. The level of depth 0:20:37.119 --> 0:20:39.280 is just depending upon the level of analysis that you 0:20:39.320 --> 0:20:42.320 want to conduct. Now, what I need is what's the 0:20:42.440 --> 0:20:44.760 data that I've been able to collect, because most of 0:20:44.800 --> 0:20:46.840 these places they're already going to have some data, even 0:20:46.880 --> 0:20:49.360 if it's just camera feed data. I could take that 0:20:49.760 --> 0:20:52.600 and actually start to run models on Okay, where are 0:20:52.600 --> 0:20:56.399 people congregating? I can actually post camera feed and apply 0:20:56.600 --> 0:20:59.680 inference data to that, so I can use the AI 0:20:59.760 --> 0:21:03.000 to it. Andy, well, that's a person, and that's an animal. 0:21:03.119 --> 0:21:05.160 That's a car over there, And now I can start 0:21:05.200 --> 0:21:07.760 to look at Okay, how often are they in these spaces? 0:21:07.800 --> 0:21:10.520 Where am I getting congregation? Where am I getting long 0:21:10.640 --> 0:21:14.360 killing live? So I can do analysis all on existing data. 0:21:14.680 --> 0:21:17.480 Now I can start to reconfigure whatever actions need to 0:21:17.480 --> 0:21:20.720 be taken, so all of that can happen before I've 0:21:20.720 --> 0:21:22.159 shown up physically at the space. 0:21:24.240 --> 0:21:28.280 Just think about all the personal identifiable information involved in 0:21:28.320 --> 0:21:30.600 some of the tasks we're talking about today. Well, the 0:21:30.640 --> 0:21:32.920 sheer amount of streaming data coming in from a host 0:21:32.920 --> 0:21:36.480 of senses required to implement digital twining, keeping that data 0:21:36.520 --> 0:21:41.080 secure is paramount to the future of this industry. I 0:21:41.240 --> 0:21:44.080 like to get your thoughts around the whole privacy side 0:21:44.119 --> 0:21:46.159 of things, and you know what can be done to 0:21:46.280 --> 0:21:49.639 make sure that as individuals we don't feel like where 0:21:50.240 --> 0:21:51.680 our privacy is getting invaded. 0:21:52.320 --> 0:21:54.040 That's a very good topic and we thought about that 0:21:54.240 --> 0:21:57.760 from the beginning. So one of the ways that we've 0:21:57.760 --> 0:22:00.760 defined scenescaper is we primarily work on meta data, and 0:22:00.800 --> 0:22:03.600 what metadata simply means is, for instance, we don't do 0:22:03.600 --> 0:22:06.359 any facial recognition. I need to know that that's a 0:22:06.359 --> 0:22:07.959 person or I need to know In fact, we had 0:22:07.960 --> 0:22:10.680 an actual scenario where a customer had a particular area 0:22:11.040 --> 0:22:13.240 and they knew people were around, but at night there 0:22:13.240 --> 0:22:14.959 were objects and they didn't know what it was. They 0:22:14.960 --> 0:22:17.480 were animals, and the model hadn't been trained for animals. 0:22:17.560 --> 0:22:19.879 So the model can say, hey, there's something there. I 0:22:19.920 --> 0:22:23.159 can't say that it's a deer versus or whatever, but 0:22:23.320 --> 0:22:28.320 it's not a human, you know. And so think about 0:22:28.359 --> 0:22:30.240 the simplicity of that. Now, I don't have to transmit 0:22:30.920 --> 0:22:35.800 every movement, every aspect. I'm only transmitting what's critical to 0:22:35.920 --> 0:22:38.919 make the decisions that are needed real time and for 0:22:38.960 --> 0:22:39.920 post analysis. 0:22:40.359 --> 0:22:44.159 We talked a little bit about fulfillment centers and warehouses. 0:22:44.960 --> 0:22:48.880 I like everyone else's ecomma sites like Amazon Prime. I'm 0:22:48.920 --> 0:22:51.439 just wondering if you could maybe paint a picture of 0:22:51.560 --> 0:22:54.000