WEBVTT - A Safer World With AI Digital Twins 0:00:03.480 --> 0:00:07.440 Workplaces like factories or fulfillment centers are filled with many 0:00:07.480 --> 0:00:11.319 moving parts and require constant supervision and alertness to ensure 0:00:11.400 --> 0:00:17.120 worker safety. But what happens when errors or accidents happen 0:00:17.239 --> 0:00:21.079 unexpectedly On the simplest level, it creates chaos and can 0:00:21.120 --> 0:00:24.520 impact productivity. On a larger scale, can create a dangerous 0:00:24.600 --> 0:00:29.200 environment for employees. How can technology like AI and the 0:00:29.240 --> 0:00:32.879 creation of a digital twin help quickly correct errors and 0:00:33.000 --> 0:00:37.760 prevent accidents before they occur? And could these virtual replications 0:00:37.760 --> 0:00:40.639 of a physical space ensure workers go home to their 0:00:40.640 --> 0:00:44.599 families safe and sound. Join us as we learn more 0:00:44.600 --> 0:00:47.680 about the world of digital twins and the many ways 0:00:47.800 --> 0:00:53.920 they can not only improve workplace safety, but also public safety. 0:00:55.160 --> 0:00:58.960 Welcome to Technically Speaking, an Intel podcast, the show that 0:00:58.960 --> 0:01:02.160 brings you the stories and insights of AI, presented by 0:01:02.200 --> 0:01:08.560 iHeartMedia's Ruby Studio and Intel. Hey there, I'm gram class. Today, 0:01:08.640 --> 0:01:12.480 we're exploring the spaces and places replicated by digital twins 0:01:13.080 --> 0:01:16.720 for starters, what is a digital twin? We're going to 0:01:16.760 --> 0:01:20.319 be examining digital spaces that represent an actual physical space 0:01:20.520 --> 0:01:23.839 in our world. To discuss the topic further, We're joined 0:01:23.840 --> 0:01:29.640 by Tony Franklin. Tony Franklin is the general manager of 0:01:29.680 --> 0:01:34.080 the Federal and Aerospace Markets, which includes military, aerospace, and 0:01:34.120 --> 0:01:36.760 Government within the Network and Edge Group. He has more 0:01:36.800 --> 0:01:41.240 than twenty years of corporate entrepreneurial, business development and management experience, 0:01:41.840 --> 0:01:45.399 focusing on starting and growing multiple businesses that apply to 0:01:45.600 --> 0:01:51.280 the Internet of Things, intelligence systems, and communications technologies. Intel's 0:01:51.280 --> 0:01:54.200 Network and Edge Group provide solutions that lead the industry 0:01:54.240 --> 0:01:57.400 and transforming businesses and the way we live are making 0:01:57.440 --> 0:02:02.040 it simple to create exciting new buyetis Welcome to the show. 0:02:01.840 --> 0:02:05.840 Tony, Thank you, Thank you, glad to be here. 0:02:06.120 --> 0:02:09.320 We've seen a lot of science fiction depictions of digital 0:02:09.320 --> 0:02:12.040 twins over the years and movies and films. The one 0:02:12.080 --> 0:02:14.679 that comes to mind is the matrix. But the entire 0:02:14.720 --> 0:02:18.520 world is a digital twin. Although it's a useful sinister motives. 0:02:19.240 --> 0:02:21.320 I'd like to get your definition of what a digital 0:02:21.360 --> 0:02:21.760 twin is. 0:02:22.360 --> 0:02:24.360 Yeah. Sure, it's interesting you said the matrix. 0:02:24.360 --> 0:02:26.519 I had to laugh because of all the examples we've 0:02:26.600 --> 0:02:28.960 joked about, that's one that hasn't come up, and it's 0:02:29.040 --> 0:02:31.480 so obvious when you said it. I'll start to use 0:02:31.560 --> 0:02:34.720 that in its simplest form from me a digital twin 0:02:34.840 --> 0:02:37.520 is the digital replica of the real world. 0:02:38.200 --> 0:02:41.680 And in terms of the technologies that are out there 0:02:42.200 --> 0:02:46.280 needed for digital twining, maybe you could describe a little 0:02:46.280 --> 0:02:50.480 bit of how those sorts of systems are put together 0:02:50.560 --> 0:02:54.440 and what are some of the technology that Intel has 0:02:54.560 --> 0:02:55.520 that can help that. 0:02:56.200 --> 0:02:56.480 Yeah. 0:02:56.520 --> 0:03:00.720 Sure, it's really been an evolution of technologies that some 0:03:00.800 --> 0:03:02.920 of them were all used to using, and some of them, 0:03:03.080 --> 0:03:04.560 you know, if you're not in the field, maybe not 0:03:04.639 --> 0:03:08.079 so much. And so Gartner, one of the well known analysts, 0:03:08.120 --> 0:03:12.520 has this Emerging Technologies trending chart they do every year, 0:03:13.080 --> 0:03:16.600 and they talk about edge AI, so artificial intelligence at 0:03:16.680 --> 0:03:19.400 the edge, you know, the place where data is actually 0:03:19.400 --> 0:03:21.600 being generated more so than in say the cloud or 0:03:21.680 --> 0:03:25.720 data centers. That's happening, It continues to evolve, it's growing 0:03:25.760 --> 0:03:28.040 more and more. We're pushing more and more intelligence to 0:03:28.200 --> 0:03:29.840 the edge. And by the edge, it could be everything 0:03:29.880 --> 0:03:32.160 from a cell phone or refrigerator or a car. Again, 0:03:32.200 --> 0:03:35.680 where is the data actually being generated. And then they 0:03:35.720 --> 0:03:38.840 talk about digital twins being sort of the now to 0:03:39.000 --> 0:03:41.400 three years. I think one of their data points was 0:03:41.400 --> 0:03:45.680 something like forty percent of businesses, large businesses in particular 0:03:45.840 --> 0:03:47.920 plan to use digital twins over the next two to 0:03:47.960 --> 0:03:50.680 three years to actually generate revenue. So that's happening now, 0:03:51.120 --> 0:03:53.720 and then lastly over the next maybe six plus years, 0:03:53.720 --> 0:03:55.960 they talk about the metaverse. Now, while we don't generally 0:03:55.960 --> 0:03:58.880 talk about the metaverse as much, the name means different 0:03:58.920 --> 0:04:01.240 things to different people, but it's the full extent of 0:04:01.560 --> 0:04:05.280 how it does. Commerce and any other business really leverage 0:04:05.280 --> 0:04:10.680 a fully digital space that has interaction with the real world. 0:04:10.800 --> 0:04:14.080 So there's this spectrum that has been happening between sensors, 0:04:14.360 --> 0:04:17.400 with cameras being the most obvious because we're all using 0:04:17.960 --> 0:04:20.800 cameras today. Our phones have so many sensors, we take 0:04:20.839 --> 0:04:23.200 them for granted. But all the sensors, one of the 0:04:23.240 --> 0:04:27.840 key technologies that are needed an ability to replicate if 0:04:27.920 --> 0:04:32.120 you're doing visual digital twins, so an ability to replicate 0:04:32.200 --> 0:04:34.600 the real world, and of course physics modeling if you're 0:04:34.640 --> 0:04:37.680 really doing analysis and you need to replicate the physical 0:04:37.760 --> 0:04:41.960 asset in a digital world, So computing capability to be 0:04:42.000 --> 0:04:46.919 able to replicate the behavior of the object, with AI 0:04:47.000 --> 0:04:50.479 being a critical component to now actually apply intelligence and 0:04:50.560 --> 0:04:53.920 analysis to the twin. So when you think about those 0:04:53.920 --> 0:04:56.880 different areas well, intel, we don't make sensors. Everything else 0:04:56.920 --> 0:04:59.800 along the way is where we tend to play clearly 0:05:00.040 --> 0:05:03.800 muting technology the ability to apply AI, so both from 0:05:03.800 --> 0:05:08.160 the software side and the various different computing technologies that 0:05:08.400 --> 0:05:14.440 enable AI, whether it's processors or GPUs, are AI accelerators, 0:05:14.560 --> 0:05:17.440 et cetera. And then of course we have a very broad, 0:05:17.920 --> 0:05:21.840 really world class partnership and ecosystem that we work with 0:05:21.920 --> 0:05:23.560 to enable the different industries. 0:05:24.279 --> 0:05:26.520 Okay, and in terms of trying to get like a 0:05:26.600 --> 0:05:30.520 visual kind of representation of what this would look like. 0:05:30.600 --> 0:05:33.720 So say if you're walking in a warehouse, for example, 0:05:33.960 --> 0:05:35.840 and you're looking at the shelves around you, you might 0:05:35.880 --> 0:05:39.599 see some conveyor belts. How would it actually look in 0:05:39.640 --> 0:05:43.520 a digital twin? It depends on the use case. The 0:05:44.000 --> 0:05:47.360 simplest version i'd use that many people should be able 0:05:47.400 --> 0:05:49.560 to relate to. Obviously many people can relate to matrix. 0:05:49.600 --> 0:05:53.120 But from an application standpoint, I would say think about 0:05:53.360 --> 0:05:58.279 Google Earth or Google Maps. Even that is a type 0:05:58.320 --> 0:06:01.560 of model right. Another example is many of the retail 0:06:01.600 --> 0:06:08.080 applications allow you to basically embed their items that are 0:06:08.080 --> 0:06:13.440 for sale into the digital replication of your particular space, 0:06:13.640 --> 0:06:17.320 so it's a real world and digital combination. That's always 0:06:17.360 --> 0:06:17.720 the key. 0:06:18.000 --> 0:06:21.360 So those are very basic, simple applications that people use 0:06:21.560 --> 0:06:23.440 and don't even realize. They don't think about them as 0:06:23.480 --> 0:06:26.760 digital twins, but they're already getting used to this relationship 0:06:26.760 --> 0:06:29.480 between the real world and the digital world. 0:06:29.960 --> 0:06:30.560 Yes, I saw. 0:06:30.600 --> 0:06:33.760 Intel has a software platform called Scenscape that can transform 0:06:33.839 --> 0:06:36.520 data from this world of senses to create a real 0:06:36.560 --> 0:06:39.480 time digital twin of your physical space. Can you tell 0:06:39.480 --> 0:06:41.000 me a little bit more of how that works? 0:06:41.560 --> 0:06:44.840 So there's really three basic steps. One is mapping your space. 0:06:45.360 --> 0:06:48.800 The key though in the type of real time digital 0:06:48.839 --> 0:06:54.000 twinning that we pursue is it is a coordinate, accurate space, 0:06:54.200 --> 0:06:56.560 So it's not just taking a random space. We know 0:06:56.680 --> 0:06:58.800 that that room is twenty feet by twenty five feet, 0:06:58.800 --> 0:07:02.240 and we also know that the cameras are six feet 0:07:02.320 --> 0:07:06.120 up on the wall. We know the actual XYZ of 0:07:06.160 --> 0:07:08.920 the space, So that's the first step. Second step is 0:07:09.400 --> 0:07:12.680 calibrate the space. So calibrate meaning I have the space, 0:07:13.080 --> 0:07:15.880 where are my sensors? So my sensor is ten feet up, 0:07:15.920 --> 0:07:19.040 four feet over in that corner, etc. Now you turn 0:07:19.080 --> 0:07:22.760 on your sensors and you ingest that into scenescape. Notice 0:07:22.800 --> 0:07:26.800 I haven't actually visualized necessarily anything. So the key for 0:07:26.840 --> 0:07:29.840 people to realize in real time digital twinning. There are 0:07:29.840 --> 0:07:32.360 some applications where someone's not actually going to be sitting 0:07:32.400 --> 0:07:35.920 there watching the digital twin of the store. They don't 0:07:35.960 --> 0:07:40.680 need to do that real time. The AI and computing obviously, 0:07:40.720 --> 0:07:45.080 the AI tools and the actual AI models, the inferencing 0:07:45.160 --> 0:07:50.520 capability of scenescape is doing the work. You are configuring 0:07:50.560 --> 0:07:53.160 it so you could add things like heat maps or 0:07:53.200 --> 0:07:57.960 trip wise so that you can actually have events based 0:07:58.000 --> 0:08:01.880 on whatever policy you want to implement, so that you 0:08:01.920 --> 0:08:04.720 don't have to actually monitor. So I'll know that over 0:08:04.760 --> 0:08:08.040 in this area of the meat department, if there's more 0:08:08.080 --> 0:08:11.360 than twenty people for twenty seconds, there's something that happens. 0:08:11.800 --> 0:08:13.920 I don't even have to watch anything for that. The 0:08:13.960 --> 0:08:15.800 intelligence is making it happen. 0:08:15.840 --> 0:08:16.320 Gotcha. 0:08:16.440 --> 0:08:20.200 Now, if what I want to do later is now 0:08:20.440 --> 0:08:23.520 hit the rewind button. The founder and creator for this 0:08:23.520 --> 0:08:25.520 particular product, he has a phrase I'd love to use. 0:08:25.560 --> 0:08:29.200 It's called the DVR for the real world. AI is 0:08:29.240 --> 0:08:33.520 happening real time, but if you want additional analysis afterwards, 0:08:33.600 --> 0:08:34.800 you have that capability. 0:08:35.400 --> 0:08:38.000 I can imagine there's a lot of challenges trying to 0:08:38.200 --> 0:08:41.120 come up with these digital twins. What are some of 0:08:41.120 --> 0:08:45.160 the top challenges or issues that people who are looking 0:08:45.200 --> 0:08:48.080 to try and deploy these sorts of systems would have 0:08:48.120 --> 0:08:48.680 to consider. 0:08:49.440 --> 0:08:53.720 The most prominent one, to be honest with you, is 0:08:53.880 --> 0:08:58.200 the mindset more than anything technical. You think about some 0:08:58.320 --> 0:09:02.760 of the technology that's growing in our own home, Siri, Alexa, 0:09:03.440 --> 0:09:07.440 are cars. There's so much technology and most people really 0:09:07.440 --> 0:09:11.360 don't understand you're already using AI. In many cases, you're 0:09:11.360 --> 0:09:14.360 already using some sort of digital twin technology. There was 0:09:14.400 --> 0:09:16.800 one demo we had for Sea Escape and the executive 0:09:16.880 --> 0:09:18.920 loved it. It's like, this is amazing. I can do 0:09:19.000 --> 0:09:21.600 motion tracking. I see where people are. I can have 0:09:21.720 --> 0:09:26.079 multiple cameras monitoring the same asset, our person or object, 0:09:26.080 --> 0:09:28.840 but I only see one, so it deduplicates the person. 0:09:29.440 --> 0:09:32.080 I can track withf somebody's been in a space. Maybe 0:09:32.120 --> 0:09:34.920 I have a radiation sensor and I can actually track 0:09:35.000 --> 0:09:37.000 how long that person has been in the space, and 0:09:37.040 --> 0:09:39.800 I can set triggers. There's so much he saw that 0:09:39.880 --> 0:09:43.080 can be done, and he was so excited and he said, 0:09:43.080 --> 0:09:46.000 where's the AI, right, Well, it's the AI that's doing 0:09:46.000 --> 0:09:49.600 everything you just described. That's right, you just like and 0:09:49.640 --> 0:09:52.240 it actually set us back for a second. We're like, well, clearly, 0:09:52.800 --> 0:09:54.920 we need to make sure we understand where people are 0:09:54.960 --> 0:09:58.319 starting from. We can't assume they already know there's a 0:09:58.400 --> 0:10:02.280 level of technology and integration of their technology. 0:10:03.760 --> 0:10:05.720 And that's one of the biggest challenges when it comes 0:10:05.720 --> 0:10:09.880 to understanding digital twin technology. It's the messaging some of 0:10:09.880 --> 0:10:12.640 the very tools that you're accustomed to right now, like 0:10:12.800 --> 0:10:15.000 the cell phone or the smart speaker that you or 0:10:15.080 --> 0:10:18.600 listening to this podcast with essential when we consider the 0:10:18.640 --> 0:10:21.120 future of digital twinning. So when it comes to a 0:10:21.160 --> 0:10:25.079 future that incorporates AI into our daily lives, we've actually 0:10:25.200 --> 0:10:30.480 already taken the first steps down that path. One of 0:10:30.480 --> 0:10:34.000 the things I like to examine is the way that 0:10:34.480 --> 0:10:38.600 technology actually helps democratize. And maybe you have some sense 0:10:38.640 --> 0:10:42.640 of the type of customers. Are they sort of large enterprises, 0:10:42.760 --> 0:10:45.440 because I'm really keen to see this sorts of technology 0:10:45.520 --> 0:10:49.640 really get pushed down to the smaller businesses and make 0:10:49.679 --> 0:10:52.320 it affordable for them to adopt and use. Do you 0:10:52.320 --> 0:10:54.400 have any thoughts about that particular trend? 0:10:54.720 --> 0:10:54.960 Yeah? 0:10:55.000 --> 0:11:00.319 Absolutely, I'd say they're all generally larger enterprises, but they 0:11:00.360 --> 0:11:03.600 may be larger enterprises with smaller facilities, so they have 0:11:03.679 --> 0:11:06.880 to think about the implementation at the store level, and 0:11:06.920 --> 0:11:08.880 then they can step back and look at it at 0:11:08.920 --> 0:11:12.079 an operational level for the entire business that they're trying 0:11:12.120 --> 0:11:15.679 to run. When you think about physical security, well, physical 0:11:15.679 --> 0:11:18.199 security can happen on a construction site, it can happen 0:11:18.200 --> 0:11:20.880 in an office space, it can happen anywhere. But the 0:11:20.880 --> 0:11:24.480 companies we're dealing with are generally the companies that one 0:11:24.720 --> 0:11:27.560 have the actual technology, so they may be the camera vendors, 0:11:27.600 --> 0:11:31.000 et cetera, but whereas actually being implemented. They're targeting a 0:11:31.120 --> 0:11:35.080 broad range in particular segments like I mentioned, but the 0:11:35.120 --> 0:11:37.920 actual implementation may happen at a different level. So it's 0:11:37.960 --> 0:11:42.520 the companies that apply technology across specific segments and then 0:11:42.600 --> 0:11:46.400 they actually tear those down. Cities can be large or 0:11:46.400 --> 0:11:50.080 they can be smaller, but you're implementing generally starting at 0:11:50.160 --> 0:11:54.280 an intersection level, so that could be maybe four cameras max. 0:11:54.920 --> 0:11:58.600 But now I've got a thousand intersections, so it grows 0:11:58.679 --> 0:12:00.600 in scales. And what we're saying, being back to that 0:12:00.679 --> 0:12:03.400 early adopter, we see the big picture. Let's start with 0:12:03.440 --> 0:12:07.240 three intersections and let's see and understand where technology can 0:12:07.280 --> 0:12:09.760 be applied there. Because one of the ways I like 0:12:09.840 --> 0:12:13.400 to explain to people, you need to understand the environment 0:12:13.480 --> 0:12:17.160 the scene. That's what it's called scenescape the scene, the area, 0:12:17.240 --> 0:12:19.920 your environment better. That's one way to think about digital 0:12:19.920 --> 0:12:21.079 twin being able to enable that. 0:12:24.400 --> 0:12:27.960 Coming out next on Technically Speaking and Intel podcast. 0:12:28.760 --> 0:12:31.120 I am the ultimate digital twin that I want. I 0:12:31.120 --> 0:12:33.880 don't care about an avatar that's fun and fancy. I 0:12:34.040 --> 0:12:36.880 was something that helps improve my quality of life. 0:12:37.520 --> 0:12:39.920 We'll be right back after a brief message from our partner. 0:12:39.960 --> 0:12:52.880 Is that Intel? Welcome back to Technically Speaking an Intel Podcast. 0:12:53.160 --> 0:12:58.840 I'm here now with the Intel's own Tony Fenklin. Do 0:12:58.880 --> 0:13:02.640 you have any other example of benefits that your customers 0:13:02.679 --> 0:13:07.120 have seen, whether it be productivity, increase, revenue, better, safety. 0:13:07.800 --> 0:13:09.160 Yeah, I'll go on reverse ands. 0:13:09.200 --> 0:13:11.880 You said safety last, because that's one that is so 0:13:12.160 --> 0:13:14.720 common yep to people. In fact one, I think it 0:13:14.760 --> 0:13:18.520 was the university in Texas that is doing some pilots 0:13:18.600 --> 0:13:22.120 with the cities and with smart vehicles, and it's a 0:13:22.200 --> 0:13:24.959 device called a roadside unit. Again, most people don't even 0:13:25.000 --> 0:13:27.480 realize that you pull up to an intersection there's normally 0:13:27.559 --> 0:13:30.280 a smaller box on the side. You already have the 0:13:30.400 --> 0:13:33.440 box that controls the lights, et cetera. Well, I want 0:13:33.440 --> 0:13:36.240 to do more so you can make that unit more intelligent. 0:13:36.280 --> 0:13:39.480 You can actually allow that roadside unit to communicate with cars. 0:13:39.480 --> 0:13:41.800 As cars become more intelligent, they have five G they 0:13:41.800 --> 0:13:45.400 have wireless communications. So they implemented a pilot where there 0:13:45.440 --> 0:13:47.760 was a particular intersection. So as the car pulls up, 0:13:47.800 --> 0:13:51.680 imagine an alley off to the left, so the car 0:13:51.760 --> 0:13:54.679 can't see down the alley clearly, but there's a poll 0:13:54.840 --> 0:13:56.920 on the right that has a camera. The camera can 0:13:56.960 --> 0:13:59.360 see the car coming. The camera can see down the alley. 0:13:59.360 --> 0:14:03.200 The camera has roadside unit with Intel processing equipment. It's 0:14:03.240 --> 0:14:07.080 running scenescape. Again, they don't even need to visualize this. 0:14:08.080 --> 0:14:12.400 The camera sees someone walking down the alley, the car 0:14:12.480 --> 0:14:15.600 is coming forward. It can communicate to the car because 0:14:15.640 --> 0:14:18.240 even the cars with the cameras can't see around corners, 0:14:18.360 --> 0:14:21.400 so the camera can communicate there's somebody walking. You need 0:14:21.520 --> 0:14:23.960 to slow down. Knowing the speed of the car is 0:14:24.000 --> 0:14:27.760 great acceleration, we understand that, but knowing where that car 0:14:27.840 --> 0:14:29.240 is at the speed of a car coming down the 0:14:29.320 --> 0:14:31.400 highway is one thing. The speed of a car coming 0:14:31.440 --> 0:14:34.480 down that street where there's an alley is a totally 0:14:34.520 --> 0:14:36.920 different scenario. I need to know the location of that 0:14:37.000 --> 0:14:39.880 car relative to the camera and relative to the person 0:14:39.920 --> 0:14:42.800 around the corner, both coming at the same time. So 0:14:42.920 --> 0:14:45.200 three D is also a key aspect and value of 0:14:45.240 --> 0:14:48.840 digital twin that translates to end benefit like you're talking about. 0:14:48.880 --> 0:14:51.280 So that's safety right there, and that safety translates to 0:14:51.440 --> 0:14:52.840 insurance as an example. 0:14:53.400 --> 0:14:58.880 Yeah, just feeding off that safety theme, can technologies like 0:14:58.960 --> 0:15:04.240 scenescape and having those sort of cameras help with worker safety, 0:15:04.320 --> 0:15:09.200 say in a factory or warehouse, where they can detect 0:15:09.320 --> 0:15:12.120 or even predict, you know, if something's going to go 0:15:12.200 --> 0:15:15.920 wrong and actually warn a worker that something's going to happen. 0:15:16.440 --> 0:15:17.239 Yeah. Absolutely. 0:15:17.320 --> 0:15:20.760 Robot interaction is a common one also, so think about 0:15:20.960 --> 0:15:24.840 robots with cameras and the cameras and sensors that are 0:15:24.920 --> 0:15:28.480 around Mobile World Congress is going on right now, and 0:15:28.520 --> 0:15:30.680 I think it was last year we did a Scenescape 0:15:30.680 --> 0:15:33.280 demo there and it was purely an industrial We had 0:15:33.280 --> 0:15:36.880 the robotic arms that were moving and they were building something, 0:15:37.280 --> 0:15:39.200 and then you have a sensor doesn't even need to 0:15:39.240 --> 0:15:42.400 be a camera that has a digital n scenescape to tripwire, 0:15:42.640 --> 0:15:45.920 so we know if somebody crosses this point, then it's 0:15:45.920 --> 0:15:48.160 a tripwire. So that was the actual demo. So there 0:15:48.160 --> 0:15:50.320 was a safety zone and then there was crossing the 0:15:50.360 --> 0:15:52.480 safety zone. So if you enter the safety zone, there 0:15:52.480 --> 0:15:53.920 could be a warning light to go off. You don't 0:15:53.920 --> 0:15:56.040 have to stop anything, but I know someone's in the 0:15:56.080 --> 0:15:58.080 safety zone, I know how long they've been in the 0:15:58.120 --> 0:16:00.800 safety zone, and if they cross past that, then I 0:16:00.840 --> 0:16:03.480 know I can start to shut down automatically equipment if 0:16:03.480 --> 0:16:06.640 that's the policy that that particular site chooses to use, 0:16:06.640 --> 0:16:11.280 so they can execute another one in a more constrained environment. 0:16:11.440 --> 0:16:16.840 Warehouse that we've seen is where there's actually a controlled space, 0:16:17.480 --> 0:16:21.000 so radiation. Actually, the earlier example I talked about is 0:16:21.040 --> 0:16:24.080 a real example where there's an area that it needs 0:16:24.080 --> 0:16:26.920 to be climate controlled and it literally has radiation. So 0:16:26.960 --> 0:16:30.280 they have a radiation sensor both inside outside and commnitor. 0:16:30.360 --> 0:16:32.760 Do you have the equipment on how long has a 0:16:32.760 --> 0:16:35.920 person been in this particular space, and I could set 0:16:35.960 --> 0:16:38.400 timers and triggers so I know that they can only 0:16:38.440 --> 0:16:40.640 be in for so long, and I can also track 0:16:40.720 --> 0:16:43.920 that so that's real time action and control, and I 0:16:43.920 --> 0:16:47.280 can also use that for later analysis and prediction. Maybe 0:16:47.280 --> 0:16:49.240 I need to change the configuration of the room, maybe 0:16:49.240 --> 0:16:51.280 I need to put more signs up. But you can 0:16:51.320 --> 0:16:55.200 have real time action and decisions and also post analysis. 0:16:55.800 --> 0:16:59.040 Yeah, what you said there about the simulation is quite 0:16:59.240 --> 0:17:02.280 interesting because you know, as you're talking else, you know, 0:17:02.520 --> 0:17:05.480 it came back to the gaming side of things, playing 0:17:05.480 --> 0:17:09.399 SimCity or roller Coaster Tycoon, being able to sort of 0:17:09.440 --> 0:17:11.879 simulate you know, if I put this thing here, is 0:17:11.920 --> 0:17:13.680 it going to be dangerous? If I put that over there? 0:17:13.760 --> 0:17:16.480 Does that help the workers? Does it help with productivity? 0:17:16.960 --> 0:17:20.920 Maybe talk a little bit of some examples of using 0:17:20.960 --> 0:17:24.600 real world data to kind of do what if analysis 0:17:24.640 --> 0:17:30.000 of various scenarios that management and workers together can can 0:17:30.040 --> 0:17:33.000 simulate and potentially improve the workplace. 0:17:33.920 --> 0:17:36.399 So let's take something like a gaming site, I mean 0:17:36.480 --> 0:17:41.600 like a football or soccer So clearly those are massive 0:17:41.640 --> 0:17:44.600 events with a lot of people, a lot of insurances, 0:17:44.680 --> 0:17:49.360 there's safety concerns, there's access to medical professionals that need 0:17:49.400 --> 0:17:52.840 to get in and out. So can I take existing 0:17:53.080 --> 0:17:57.280 data that has already been captured using existing cameras and 0:17:57.359 --> 0:17:59.760 I can actually run simulations on that, I could also 0:18:00.560 --> 0:18:02.440 ideally what I want and I need it. If I'm 0:18:02.440 --> 0:18:04.160 going to do a digital twin, I need some sort 0:18:04.160 --> 0:18:07.200 of digital twin of the environment. The level of depth 0:18:07.280 --> 0:18:09.439 is just depending upon the level of analysis that you 0:18:09.480 --> 0:18:12.480 want to conduct. Now, what I need is what's the 0:18:12.560 --> 0:18:14.920 data that I've been able to collect, Because most of 0:18:14.960 --> 0:18:17.000 these places they're already going to have some data, even 0:18:17.000 --> 0:18:19.520 if it's just camera feed data. I could take that 0:18:19.920 --> 0:18:22.760 and actually start to run models on Okay, where are 0:18:22.760 --> 0:18:26.560 people congregating. I can actually post camera feed and apply 0:18:26.760 --> 0:18:29.840 inference data to that, so I can use the AI 0:18:29.920 --> 0:18:33.160 to identify, well, that's a person, and that's an animal, 0:18:33.280 --> 0:18:35.320 that's a car over there. And now I can start 0:18:35.359 --> 0:18:37.919 to look at, okay, how often are they in these spaces? 0:18:37.920 --> 0:18:40.680 Where am I getting congregation? Where am I getting long 0:18:40.760 --> 0:18:44.520 kelling lies? So I can do analysis all on existing data. 0:18:44.840 --> 0:18:47.600 Now I can start to reconfigure whatever actions need to 0:18:47.640 --> 0:18:50.880 be taken, so all of that can happen before I've 0:18:50.920 --> 0:18:52.320 shown up physically at the space. 0:18:54.400 --> 0:18:58.439 Just think about all the personal identifiable information involved in 0:18:58.480 --> 0:19:00.760 some of the tasks we're talking about today. Well, the 0:19:00.800 --> 0:19:03.080 sheer amount of streaming data coming in from a host 0:19:03.080 --> 0:19:06.640 of senses required to implement digital twining. Keeping that data 0:19:06.640 --> 0:19:11.320 secure is paramount to the future of this industry. I'd 0:19:11.400 --> 0:19:14.240 like to get your thoughts around the whole privacy side 0:19:14.280 --> 0:19:16.320 of things, and you know, what can be done to 0:19:16.440 --> 0:19:19.720 make sure that as individuals we don't feel like we're 0:19:20.400 --> 0:19:21.800 our privacy is getting invaded. 0:19:22.480 --> 0:19:24.280 It's a very good topic and we thought about that 0:19:24.400 --> 0:19:27.920 from the beginning. So one of the ways that we've 0:19:27.920 --> 0:19:31.080 defined scenescape is we primarily work on metadata. And what 0:19:31.119 --> 0:19:33.920 metadata simply means is, for instance, we don't do any 0:19:33.960 --> 0:19:36.879 facial recognition. I need to know that that's a person, 0:19:37.080 --> 0:19:38.199 or I need to know. In fact, we had an 0:19:38.240 --> 0:19:41.639 actual scenario where customer had a particular area and they 0:19:41.680 --> 0:19:43.960 knew people were around, but at night there were objects 0:19:44.000 --> 0:19:45.720 and they didn't know what it was. They were animals, 0:19:46.000 --> 0:19:47.919 and the model hadn't been trained for animals. So the 0:19:47.920 --> 0:19:50.600 model can say, hey, there's something there. I can't say 0:19:50.680 --> 0:19:53.760 that it's a deer versus or whatever, but it's not 0:19:53.800 --> 0:19:59.080 a human, you know, And so think about the simplicity 0:19:59.080 --> 0:20:01.920 of that. Now, I don't have to try trans every movement, 0:20:02.160 --> 0:20:06.359 every aspect. I'm only transmitting what's critical to make the 0:20:06.440 --> 0:20:10.040 decisions that are needed real time and for post analysis. 0:20:10.520 --> 0:20:15.199 We talked a little bit about fulfillment centers and warehouses. I, 0:20:15.400 --> 0:20:19.040 like everyone else, use ecommace sites like Amazon Prime. I'm 0:20:19.080 --> 0:20:21.600 just wondering if you could maybe paint a picture of 0:20:21.720 --> 0:20:24.160 how from the time that I hit that buy now 0:20:24.200 --> 0:20:26.800 button to the time that I get my pair of 0:20:26.840 --> 0:20:32.479 socks at my doorstep. Perhaps take me through how digital 0:20:32.520 --> 0:20:37.879 twins could be used. How would a system help that process, 0:20:38.240 --> 0:20:41.320 both as an in consumer and also for the business. 0:20:41.600 --> 0:20:43.679 Actually to be honest, One of the first examples that 0:20:43.680 --> 0:20:47.560 came to mind is the delivery truck and why location 0:20:47.800 --> 0:20:51.960 intelligence is so important. All of us use location based 0:20:52.000 --> 0:20:54.880 services today. There was a study I read I think 0:20:54.920 --> 0:20:58.400 it was UPS is saving a lot of money per 0:20:58.440 --> 0:21:03.760 truck because they realize the location intelligence they were getting more. Particularly, 0:21:03.760 --> 0:21:06.439 this was when hotels were putting in their addresss because 0:21:06.560 --> 0:21:10.280 they use Amazon Prime to and they're getting these packages 0:21:10.320 --> 0:21:15.320 shipped to them. The location data of that hotel relative 0:21:15.359 --> 0:21:17.800 to where the truck is coming from, and then mapping 0:21:17.840 --> 0:21:21.640 the route were not good routes, so it was costing 0:21:21.720 --> 0:21:25.639 the company so much money to get from point A 0:21:25.680 --> 0:21:28.000 to point B. So now I can start to identify 0:21:28.040 --> 0:21:29.960 where are the hotel. And if they discovered this and 0:21:30.000 --> 0:21:33.199 they started taking copies which they have, this would go. 0:21:33.240 --> 0:21:35.520 We can take copies of the maps, I can start 0:21:35.560 --> 0:21:37.800 to locate where am I going. I can start to 0:21:37.840 --> 0:21:41.359 figure out the routes. So they're using the twin of 0:21:41.440 --> 0:21:44.680 the maps and the data they already have. Think about 0:21:44.720 --> 0:21:47.719 they have tons of data on their routes and the locations, 0:21:47.720 --> 0:21:50.240 and where are they normally congregating, and which truck should 0:21:50.240 --> 0:21:53.000 they send, what time should they be. They did all 0:21:53.040 --> 0:21:55.960 of that analysis to figure out just on the back 0:21:56.080 --> 0:21:58.639 end of when I actually dropped the packets off to 0:21:58.680 --> 0:22:01.840 you and what makes sense. That's saving money for them 0:22:01.960 --> 0:22:04.080 completely and again it's location based. 0:22:04.560 --> 0:22:06.720 Yeah, and can you give me an example of how 0:22:06.760 --> 0:22:09.480 digital twinning might already be in use for the consumer 0:22:09.840 --> 0:22:12.960