WEBVTT - Smart Talks with IBM: The Mayflower Autonomous Ship: AI and Automation at Sea 0:00:00.040 --> 0:00:05.000 Hey everyone, it's Robert and Joe here. Today we've got 0:00:05.040 --> 0:00:06.960 something a little bit different to share with you. It 0:00:07.080 --> 0:00:10.680 is a new edition of the Smart Talks podcast series, 0:00:10.720 --> 0:00:14.319 which is produced in partnership with IBM. This season of 0:00:14.360 --> 0:00:18.640 Smart Talks with IBM is all about new creators, the developers, 0:00:19.040 --> 0:00:22.600 data scientists, c t o s, and other visionaries creatively 0:00:22.640 --> 0:00:27.120 applying technology and business to drive change. They use their 0:00:27.160 --> 0:00:30.640 knowledge and creativity to develop better ways of working, no 0:00:30.720 --> 0:00:34.840 matter the industry. Join hosts from your favorite Pushkin Industries 0:00:34.920 --> 0:00:38.560 podcast as they use their expertise to deepen these conversations. 0:00:39.040 --> 0:00:41.800 Malcolm Gladwell will guide you through this season as your 0:00:41.840 --> 0:00:45.000 host to provide his thoughts and analysis along the way. 0:00:45.320 --> 0:00:48.600 Look out for new episodes of Smart Talks with IBM 0:00:48.680 --> 0:00:52.040 every month on the I Heart Radio app, Apple Podcasts, 0:00:52.159 --> 0:00:55.480 or wherever you get your podcasts. And learn more at 0:00:55.520 --> 0:01:04.000 IBM dot com slash smart Talks. Hello, Hello, Welcome to 0:01:04.080 --> 0:01:07.720 Smart Talks with IBM, a podcast from Pushkin Industries, I 0:01:07.880 --> 0:01:12.560 Heart Radio and IBM. I'm Malcolm Blobwell. This season we're 0:01:12.560 --> 0:01:16.880 talking to new creators, the developers, data scientists, c t 0:01:17.040 --> 0:01:21.000 o s, and other visionaries who are creatively applying technology 0:01:21.000 --> 0:01:24.720 and business to drive change. Channeling their knowledge and expertise, 0:01:24.880 --> 0:01:29.600 they're developing more creative and effective solutions no matter the industry. 0:01:30.200 --> 0:01:34.160 Our guest today are Brett Fanoff and Don Scott. Brett 0:01:34.160 --> 0:01:37.960 and Dawn are responsible for creating the world's first unmanned, 0:01:38.240 --> 0:01:42.480 fully autonomous ship to cross the Atlantic Ocean, a research 0:01:42.560 --> 0:01:46.720 vessel they've dubbed the Mayflower four hundred. Brett is the 0:01:46.840 --> 0:01:51.040 director of the Mayflower Autonomous Ship Project and Dawn is 0:01:51.040 --> 0:01:56.720 the CTO of Marine AI. On June thirty two, the 0:01:56.800 --> 0:02:01.960 Mayflower four hundred successfully completed its voyage from Plymouth, UK 0:02:02.440 --> 0:02:07.280 to Plymouth, Massachusetts. It's both an homage to the original Mayflower, 0:02:07.600 --> 0:02:10.720 which crossed the Atlantic forundered years earlier, and a bell 0:02:10.800 --> 0:02:14.880 weather for the ways autonomous technology will push the boundaries 0:02:14.880 --> 0:02:20.160 of maritime exploration in the next four years. On today's show, 0:02:20.200 --> 0:02:24.880 the Unlikely Origins of a self directed Ship, some motion misadventures, 0:02:24.919 --> 0:02:27.960 and what AI and machine learning will mean for the 0:02:28.000 --> 0:02:32.560 future of seafaring and beyond, Brett and Dawn spoke with 0:02:32.680 --> 0:02:37.119 Lauren Ober, host of the forthcoming Pushkin podcast The Loudest 0:02:37.200 --> 0:02:40.160 Girl in the World. Lauren is a longtime radio host 0:02:40.200 --> 0:02:43.840 and reporter, helming shows like NPRS, The Big Listen and 0:02:44.000 --> 0:02:50.079 Spectacular failures from American public Media. Okay, now let's get 0:02:50.120 --> 0:02:57.600 to the interview with Brett Fanoff and Don Scott. Don 0:02:57.720 --> 0:03:00.280 and Brett, it's really great to be talking with you 0:03:00.320 --> 0:03:03.360 guys today. I was wondering for each of you, what 0:03:03.639 --> 0:03:06.240 is the draw of the sea? I mean, it's like 0:03:06.280 --> 0:03:11.840 this expansive place. It feels so unknown in so many ways. Um, 0:03:11.880 --> 0:03:15.000 but I'm curious, like, what is the allure there for me? 0:03:15.080 --> 0:03:17.239 It's I wanted to be I wanted to do aerospace, 0:03:17.240 --> 0:03:19.480 so I always feel like I'm like the poor cousin 0:03:19.960 --> 0:03:23.519 of aerospace. But it isn't. It's actually it's harder to 0:03:23.520 --> 0:03:26.639 to do the underwater stuff. It's closer. It's just harder 0:03:26.680 --> 0:03:31.200 than being in space. It's it's incredibly hostile and wildly unexplored. 0:03:31.240 --> 0:03:34.000 And why what I like about it is that you know, 0:03:34.160 --> 0:03:35.960 you can take a bucket and go down to the beach, 0:03:36.040 --> 0:03:38.480 get a bucket of water, analyze the bucket of water 0:03:38.680 --> 0:03:41.520 for the next twenty years, and you know, chances are 0:03:41.520 --> 0:03:43.200 pretty high you're gonna have a couple of things in 0:03:43.200 --> 0:03:46.600 there that nobody's ever seen before, and that's every bucket 0:03:46.600 --> 0:03:49.440 of water everywhere in the world, right, So I like 0:03:49.520 --> 0:03:51.560 the idea that you get to discover something new all 0:03:51.600 --> 0:03:54.800 the time. And it's also hard. It's a difficult place 0:03:54.840 --> 0:03:56.840 to work, so it challenges you to come up with 0:03:56.880 --> 0:03:59.640 new ideas and new ways to do things and new materials, 0:03:59.680 --> 0:04:01.640 and that's what I like about it. I don't know, 0:04:01.760 --> 0:04:04.640 don what about you, Yeah, I mean, um, there's obviously 0:04:04.640 --> 0:04:07.760 an allure and draw there's some great descriptions about why 0:04:07.800 --> 0:04:10.480 people are drawn to the ocean. Talk to the authors 0:04:10.480 --> 0:04:12.400 and the poets, you know, it's it's definitely a real 0:04:12.720 --> 0:04:15.160 sort of visceral feeling that people get. I think you're 0:04:15.160 --> 0:04:18.600 find that the people that are involved in ocean engineering 0:04:18.640 --> 0:04:21.719 and or marine sides like that. You don't just sort 0:04:21.720 --> 0:04:25.080 of fall into this career by accident. You make proactive 0:04:25.120 --> 0:04:28.720 decisions to get involved in that environment. So you have 0:04:28.800 --> 0:04:31.919 a bunch of people working there that that want to 0:04:31.920 --> 0:04:35.320 be there and sort of have this uh understanding of 0:04:36.880 --> 0:04:38.919 that this is the place they want to be and 0:04:38.960 --> 0:04:41.520 this is where they want to work. So that becomes 0:04:41.560 --> 0:04:45.960 a very very positive work environment workspace because everyone's they 0:04:46.000 --> 0:04:50.040 want to be there, So there's that. Yeah, it's highly collaborative, 0:04:50.120 --> 0:04:53.760 isn't it. It's um like anything, there's personalities, but it 0:04:54.000 --> 0:04:55.960 tends to be a lot of fun more than anything else. 0:04:56.000 --> 0:04:58.320 It's challenging in all the ways that make life interesting. 0:04:58.360 --> 0:04:59.960 And then it also tends to be a good time. 0:05:00.279 --> 0:05:03.920 And you can't work in the ocean by yourself, like, well, 0:05:03.960 --> 0:05:07.800 you can, but it's kind of hard. So, like Brett said, 0:05:07.800 --> 0:05:11.240 it's an incredibly collaborative environment. I mean, if you want 0:05:11.279 --> 0:05:13.559 to be doing anything of significance, you have to be 0:05:13.760 --> 0:05:16.240 working as a group because you need to rely on 0:05:16.279 --> 0:05:20.680 each other. It is an incredibly dynamic, hostile environment, very humbling. 0:05:21.200 --> 0:05:25.840 So you find you you're going to achieve success as 0:05:25.880 --> 0:05:28.719 a collaborative group as opposed to some sort of lone 0:05:28.760 --> 0:05:32.120 wolf type out to right. Okay, so we're here to 0:05:32.160 --> 0:05:36.760 talk about the Mayflower Autonomous Ship project, which obviously is 0:05:36.880 --> 0:05:41.320 very cool. Um, how exactly did you guys decide to 0:05:41.440 --> 0:05:47.039 build an autonomous ship and then model it after the Mayflower? 0:05:47.600 --> 0:05:49.440 I mean it was just to hold my beer kind 0:05:49.440 --> 0:05:53.240 of thing. Um, I'm sure what it really is, it 0:05:53.279 --> 0:05:56.320 really was, it really was. Yeah, what it really was 0:05:56.400 --> 0:06:00.560 is it was so in meeting with the City of 0:06:00.560 --> 0:06:03.360 Plymouth on something else. They were talking about what they 0:06:03.400 --> 0:06:05.360 were going to do and maybe build a replica ship, 0:06:05.400 --> 0:06:08.440 of which there's already one. And I thought that wasn't 0:06:08.480 --> 0:06:12.520 the best idea. And you're talking for anniversary. Yeah, And 0:06:12.560 --> 0:06:16.560 so I was a little bit indelicate in my comment 0:06:16.640 --> 0:06:19.760 as to how they wanted to proceed with a possible replica. 0:06:19.800 --> 0:06:22.280 Think you said it was a stupid idea, I said, 0:06:22.279 --> 0:06:25.000 I said it was stupid. And uh, and there was 0:06:25.080 --> 0:06:27.280 more I couldn't resist and and and I said, there 0:06:27.279 --> 0:06:29.080 already is one, you know, And it's it's just I 0:06:29.120 --> 0:06:32.160 grew up near there. And and so they said, all right, 0:06:32.240 --> 0:06:33.640 smart guy, what are you gonna do. I was like, oh, 0:06:33.640 --> 0:06:37.360 we should build one that challenges us technologically and from 0:06:37.360 --> 0:06:40.159 an engineering perspective and sort of invokes the spirit of 0:06:40.200 --> 0:06:44.039 the original risk taking and do something that informs the 0:06:44.040 --> 0:06:46.440 next four years. And everybody was like, yeah, you should 0:06:46.480 --> 0:06:48.520 do that, and I was like, you know what, I 0:06:48.560 --> 0:06:52.560 will hold my beer. And so so I called Don 0:06:52.600 --> 0:06:55.359 after the meeting and I was like, oh, Don, we 0:06:55.360 --> 0:06:57.760 we have to build an AI. I need Captain Watson 0:06:57.920 --> 0:06:59.240 because we're going to build an A ton of a 0:06:59.320 --> 0:07:03.400 ship across the Atlantic, and he was like great and 0:07:03.480 --> 0:07:06.719 so yeah, and it was just that literally, that glib, 0:07:06.920 --> 0:07:08.400 but it also I mean, he and I have been 0:07:08.440 --> 0:07:10.960 working on unmanned systems and autonomous systems for a long 0:07:11.000 --> 0:07:14.280 time together, twenty plus years, and so I wanted to 0:07:14.280 --> 0:07:16.040 see where we could get to, like, how hard could 0:07:16.040 --> 0:07:18.600 this be? Right? I mean? And AI, sure, let's do it. Then, 0:07:19.360 --> 0:07:22.960 So we built a ship. You mentioned capturing the spirit 0:07:22.960 --> 0:07:27.640 of the original Mayflower Journey, and I wonder what exactly 0:07:27.680 --> 0:07:30.880 where you're trying to capture. Was it the spirit of 0:07:30.920 --> 0:07:34.280 taking risks or was it doing something that hadn't been 0:07:34.320 --> 0:07:37.960 done before? What we were trying to do. We knew 0:07:37.960 --> 0:07:40.600 it was really hard, right like, and it was a 0:07:40.680 --> 0:07:43.760 huge amount of risk to undertake it. Press the real 0:07:43.840 --> 0:07:46.080 risk taker. He's the one with the big ideas and 0:07:46.320 --> 0:07:48.480 wants to take the risk. I'm I'm a little more 0:07:48.920 --> 0:07:52.720 cautious and sort of pragmatic in the sense of, Okay, 0:07:52.760 --> 0:07:55.720 what's going to take to do that? We we actually 0:07:55.760 --> 0:07:57.360 didn't think we were going to make it, or I 0:07:57.480 --> 0:07:59.760 fully expected at some point the ocean we get annoyed 0:07:59.760 --> 0:08:02.640 and mighte us, you know, pilgrims like that to me 0:08:02.720 --> 0:08:04.640 is what's interesting. The pilgrims took a risk, right, So 0:08:04.720 --> 0:08:08.560 every one of them fully expected that they would die 0:08:09.200 --> 0:08:12.040 if not on the voyage within like the first year. Right, 0:08:12.480 --> 0:08:15.960 That's how it was, and it was worth it to 0:08:16.000 --> 0:08:20.280 them to take that risk. So our risk is infinitesimal 0:08:20.320 --> 0:08:23.480 by comparison, Right, it's tiny. What was our risk, really, 0:08:23.680 --> 0:08:27.440 We'd lose a ship we spent some money on. So 0:08:27.480 --> 0:08:31.680 what the knowledge about how to approach these problems is, 0:08:31.840 --> 0:08:33.720 and the and the experience that you get to give 0:08:33.800 --> 0:08:37.200 people to take risk at that level from an engineering 0:08:37.200 --> 0:08:39.800 perspective is really important. Right, somebody had to do the 0:08:39.840 --> 0:08:43.840 first open heart surgery and took a risk. Now we're 0:08:43.840 --> 0:08:46.000 not doing open heart surgery, right, No one's going to die. 0:08:46.400 --> 0:08:49.040 So what's appealing about the risk thing is it has 0:08:49.040 --> 0:08:52.720 a technical risk and environmental risk, and then there's a 0:08:52.800 --> 0:08:56.160 legislative and regulatory risk. Because we had to have our 0:08:56.240 --> 0:08:58.840 fights with various agencies about the fact that they didn't 0:08:58.840 --> 0:09:00.600 have a law that said we couldn't so they didn't 0:09:00.600 --> 0:09:02.760 get to say no just because they didn't want us to. 0:09:03.520 --> 0:09:06.560 And at the same time trying to create a reliable 0:09:06.600 --> 0:09:09.720 machine and then some sort of an AI machine learning 0:09:09.760 --> 0:09:13.960 based system that would be safe whatever that is in 0:09:14.000 --> 0:09:16.840 the middle of the ocean. It's really interesting and gives 0:09:16.880 --> 0:09:18.880 people a lot to a lot of purchase for different 0:09:18.880 --> 0:09:22.199 people with different skill sets to collaborate. Brett and John 0:09:22.240 --> 0:09:26.520 started developing the Mayflower Autono, a ship in It took 0:09:26.559 --> 0:09:29.480 them six years to figure out both the software and 0:09:29.520 --> 0:09:32.760 the body of the boat itself. In that time, over 0:09:32.840 --> 0:09:37.000 seventy people contributed to the project. Lauren asked Don and 0:09:37.080 --> 0:09:40.040 Brett what it really took to go from hold my 0:09:40.160 --> 0:09:43.520 beer to an actual ship? You know, it is mind 0:09:43.520 --> 0:09:47.359 boggling when you think of how many people are involved, 0:09:47.360 --> 0:09:51.520 how many people are touching this project, how many interesting 0:09:51.559 --> 0:09:54.600 minds doing interesting things, but you have to funnel it 0:09:54.640 --> 0:09:59.000 all into this one project. Well that I don't know 0:09:59.040 --> 0:10:00.560 if it's that way. I mean, I guess you could 0:10:00.559 --> 0:10:03.040 say there was one project, but there were lots of projects, 0:10:03.120 --> 0:10:05.600 and so, you know, there was sort of the hardcore 0:10:05.640 --> 0:10:07.480 group of people that are trying to build the actual 0:10:07.520 --> 0:10:09.839 software that works, and then there's the guys trying to 0:10:09.880 --> 0:10:13.160 build the hardware and they have an interface, but they're 0:10:13.200 --> 0:10:16.840 parallel pursuits that don't have direct overlap. And then we 0:10:16.880 --> 0:10:19.200 said yes a lot to anybody who wanted to help, 0:10:19.840 --> 0:10:22.880 because we learned from experience that most people don't last 0:10:22.960 --> 0:10:25.760 in terms of the ability to stick out four or 0:10:25.800 --> 0:10:28.040 five years focus on the projects very hard. And so 0:10:28.120 --> 0:10:30.480 the people that I wanted to stick it out and 0:10:30.480 --> 0:10:33.760 bring it to fruition ended up, you know, sticking it 0:10:33.800 --> 0:10:35.880 out and that was great, you know. And then there 0:10:35.920 --> 0:10:37.480 are all sorts of different things. There was a group 0:10:37.720 --> 0:10:39.679 making a web interface so that they could show the 0:10:39.720 --> 0:10:41.920 world what we were doing, and you know, then there 0:10:41.960 --> 0:10:44.720 was a PR group that was marketing things and sort 0:10:44.720 --> 0:10:46.920 of talking about how we tell the world about it, 0:10:46.960 --> 0:10:49.960 and we would support them. But it's hard to describe 0:10:49.960 --> 0:10:51.880 it as one project. I guess would be my position. 0:10:51.880 --> 0:10:56.040 It's lots of interlinked programs, right, Sure, I get that, 0:10:56.160 --> 0:10:59.440 I get that. Can you tell me more about how 0:10:59.520 --> 0:11:03.640 automate is built into the ship and how it works. Well, 0:11:03.760 --> 0:11:07.559 there's tons of automation and Mayflow, I mean Mayflower is 0:11:08.080 --> 0:11:12.199 like most robotics systems, right, So you peel it open 0:11:12.200 --> 0:11:15.199 and you find you know, programmable logic controllers and motor 0:11:15.280 --> 0:11:18.760 drives and also its of other things sensors and industrial 0:11:18.800 --> 0:11:21.240 automation that you'd see, you know, in an elevator or 0:11:21.240 --> 0:11:25.360 an escalator or industrial machinery for manufacture. And that's one 0:11:25.640 --> 0:11:27.640 sort of layer of it. Right, So you've got the 0:11:27.640 --> 0:11:30.400 basic analog control, then you've got sort of a veneer 0:11:30.520 --> 0:11:33.839 of automation, and then what I would call sophisticated automation, 0:11:33.880 --> 0:11:36.880 which don and I have worked on for decades in 0:11:36.920 --> 0:11:39.800 the marine space. So all that's in there. And you know, 0:11:40.000 --> 0:11:42.800 Donn and I talked really early on if I just 0:11:42.840 --> 0:11:44.640 wanted to get across the Atlantic, we could have bought 0:11:44.640 --> 0:11:48.280 an old fishing boat, filled up the fisholds with diesel fuel, 0:11:48.320 --> 0:11:50.480 and put a cheap autopilot on it and sent it. 0:11:50.559 --> 0:11:54.480 It probably would have got across. But so what it's 0:11:54.520 --> 0:11:58.960 not reducing risk, and it's not unburdening a person, and 0:11:59.000 --> 0:12:03.280 it's not doing anything really clever or sophisticated. And so 0:12:03.360 --> 0:12:05.600 what we were more interested in was getting to a 0:12:05.600 --> 0:12:08.000 point where instead of having to tell it to do everything, 0:12:08.640 --> 0:12:11.720 saying go do this task right, a goal like go 0:12:11.840 --> 0:12:13.960 to Plymouth right, and then while you're doing that, oh, 0:12:14.000 --> 0:12:16.240 by the way, while you're doing that, collect all this 0:12:16.320 --> 0:12:18.920 science data and if you see anything unusual, tell us 0:12:19.040 --> 0:12:21.880 and and while you're looking for all these unusual things 0:12:21.880 --> 0:12:26.240 and trying to achieve your goal don't hit anything. So 0:12:26.280 --> 0:12:29.520 then what role did IBM s technology play in all 0:12:29.559 --> 0:12:33.559 of this? Yeah, I mean their their technology is all 0:12:33.600 --> 0:12:36.960 over the ship. Probably the main contribution it was the 0:12:37.000 --> 0:12:41.640 decision making process or it's it's an automation TOOLM operational 0:12:41.679 --> 0:12:45.640 decision manager. It's actually a financial services tool. It's for 0:12:46.160 --> 0:12:50.720 your making decisions about the viability of a transaction, whether 0:12:50.760 --> 0:12:54.040 it's fraud or order or alone or let's say, And 0:12:54.480 --> 0:12:58.760 we were being presented this by one of the ODIUM engineers, 0:12:58.840 --> 0:13:00.360 and I remember sitting in the room with Brett thing, 0:13:00.520 --> 0:13:03.880 what what in the world does uh financial services product 0:13:03.960 --> 0:13:06.920 have to do with marine navigation? And they sort of 0:13:06.920 --> 0:13:11.000 were brought to realize by the IBM engineer how this is. 0:13:11.440 --> 0:13:13.920 This isn't really so much about financial services as it 0:13:14.000 --> 0:13:17.720 is about making making really difficult decisions in a really 0:13:17.760 --> 0:13:21.360 complex environment, which is what they do in financial services. 0:13:21.400 --> 0:13:23.760 But it's also exactly what we needed to do in 0:13:24.400 --> 0:13:27.960 re navigation. And when it's when the system was actually undering, 0:13:28.280 --> 0:13:32.800 it would create a log essentially of why that decision 0:13:32.880 --> 0:13:36.400 was made, so they can validate that decision and verify 0:13:36.480 --> 0:13:38.840 and validate that that that was in fact the right decision. 0:13:39.360 --> 0:13:41.640 And um, so that's a that's one of the key 0:13:41.920 --> 0:13:44.320 IVM tools that are on board. Well, one of the 0:13:44.360 --> 0:13:47.640 things you might want to consider about that is the fundamentals, Right, 0:13:47.720 --> 0:13:50.440 the theoretical independence of all the AI that we're deploying 0:13:50.480 --> 0:13:54.240 now have been sort of understood for decades, right, and 0:13:54.280 --> 0:13:56.280 so now we just happened to live in a world 0:13:56.840 --> 0:13:59.520 where the microprocesses are up to snuff that they can 0:13:59.559 --> 0:14:02.600 deplace some of these very sophisticated theoretical and reality and 0:14:02.640 --> 0:14:04.920 all of which IBM has been involved with from inception, 0:14:05.600 --> 0:14:08.160 based on its pedigree is in the national business machines. 0:14:08.600 --> 0:14:11.800 There isn't an IBM product that I can think of 0:14:12.120 --> 0:14:15.839 that we haven't tried to utilize the deploying so it's 0:14:15.920 --> 0:14:18.720 it's it's everywhere in the ship. Yeah, I don't think 0:14:18.720 --> 0:14:22.560 a lot of people think of technology as as as 0:14:22.600 --> 0:14:27.160 a creative pursuit, but I imagine building an autonomous ship 0:14:27.200 --> 0:14:30.480 from scratch takes a lot of creativity. And I'm wondering, 0:14:30.600 --> 0:14:34.520 do you guys think of your work as creative? Yeah, 0:14:34.800 --> 0:14:39.200 engineering is essentially designing technological innovation sort of do you 0:14:39.200 --> 0:14:42.280 think of it as a very logical process, and there 0:14:42.360 --> 0:14:45.080 is that, for sure, but there's an incredible amount of 0:14:45.200 --> 0:14:48.760 innovation involved too, Like there's no template for what we're doing. 0:14:49.000 --> 0:14:51.720 And you know, we call it white paper design, where 0:14:51.720 --> 0:14:54.960 you're basically given a blank piece of paper and a goal, 0:14:55.440 --> 0:14:59.760 which is, okay, ship that's going to cross the Atlantic, Um, okay, 0:14:59.760 --> 0:15:02.280 come up with some ideas, right, So I mean it 0:15:02.400 --> 0:15:06.720 requires major conceptual leaps and then the technical skill to 0:15:06.760 --> 0:15:10.200 realize those those leaps. You're not going to make any 0:15:10.240 --> 0:15:13.440 advances just doing things the way you've always done them. Right. 0:15:13.520 --> 0:15:17.160 You need to stretch right, and the only way it 0:15:17.240 --> 0:15:21.920 stretches what implementing new ideas, like you can spend a decade. 0:15:22.200 --> 0:15:24.440 We call it power point engineering right where you do 0:15:24.520 --> 0:15:26.800 nothing but think of things. We don't actually do anything, 0:15:27.360 --> 0:15:31.080 as opposed to what we call full contact engineering, where 0:15:31.120 --> 0:15:35.480 you actually built the boat, right, the software to go 0:15:35.520 --> 0:15:37.560 on the boat and send it out on the water. 0:15:38.760 --> 0:15:41.400 Get your kick like, get sea sick, you know, all 0:15:41.400 --> 0:15:43.280 that sort of fun stuff that happens when you're dont 0:15:43.320 --> 0:15:47.800 see trials um. And because that's where you that's where 0:15:47.840 --> 0:15:50.480 the actual learning is happening, that's where the actual development 0:15:50.560 --> 0:15:53.880 is happening is being out on the ocean. Crossing the 0:15:53.880 --> 0:15:57.240 Atlantic is no small voyage for any vessel, but the 0:15:57.320 --> 0:16:01.120 Mayflower Autonomous Ship Project is more than just about sailing 0:16:01.160 --> 0:16:05.440 from point A to point B. Automation and AI have 0:16:05.640 --> 0:16:08.880 game changing implications for the way we design the next 0:16:08.960 --> 0:16:12.320 generation of vessels and the way these vessels will behave 0:16:12.680 --> 0:16:16.400 and interact at sea. Ships will be able to gather 0:16:16.520 --> 0:16:20.720 data from the ocean by themselves, providing humans with critical 0:16:20.760 --> 0:16:26.040 information we need to address problems like global warming, ocean pollution, 0:16:26.480 --> 0:16:30.080 and our impact on marine life. For instance, the Mayfire 0:16:30.120 --> 0:16:34.880 four hundred can sample ocean water for microplastics and record 0:16:35.040 --> 0:16:40.080 audio of whale vocalizations. Taking the human factor out of 0:16:40.080 --> 0:16:43.920 a ship allows us to explore new designs and functions 0:16:43.960 --> 0:16:47.920 that haven't been imagined before. Lauren asked bread and Down 0:16:48.320 --> 0:16:51.040 more about this. What are some of the benefits of 0:16:51.080 --> 0:16:55.640 having an unmanned vessel, like, how does automation push the 0:16:55.640 --> 0:16:59.040 boundaries of what we can do out in the ocean. Well, 0:16:59.040 --> 0:17:01.640 the few major apples right or through facets to that 0:17:01.720 --> 0:17:04.840 one is you can do some risky things when you 0:17:04.840 --> 0:17:06.879 don't have the people there right because no one's going 0:17:06.920 --> 0:17:09.760 to be lost at sea. And then the other thing 0:17:09.840 --> 0:17:11.960 is you can drive cost down, and I mean cost 0:17:12.040 --> 0:17:15.480 financially but also environmental cost, right, because you can use 0:17:15.520 --> 0:17:19.000 a far less energy to accomplish a similar goal. And 0:17:19.040 --> 0:17:21.680 then what that allows you to do is have more Right. 0:17:21.720 --> 0:17:26.240 So instead of say having one fifty million dollar hundred 0:17:26.240 --> 0:17:28.680 million dollar research ship, which is the kind of numbers 0:17:28.720 --> 0:17:31.720 you're talking about to take scientists to see, you can 0:17:31.760 --> 0:17:35.679 have twenty or thirty or forty million dollars or two 0:17:35.760 --> 0:17:39.000 million dollar ships that go out and work collaboratively with 0:17:39.040 --> 0:17:42.040 space based assets and with one another and collect vast 0:17:42.040 --> 0:17:44.800 amounts of data from disparate parts of the ocean. And 0:17:44.840 --> 0:17:48.560 then you use that data to create information that informs 0:17:48.560 --> 0:17:51.440 where you send the man vessel, right, so that they 0:17:51.480 --> 0:17:54.239 get the most out of their time at sea. So 0:17:54.240 --> 0:17:57.240 it's about enabling the people. It's about leaving the humans 0:17:57.280 --> 0:17:59.840 to do the uniquely human part, which is have the insight, 0:18:00.080 --> 0:18:04.040 the intuition and and the creativity. And so you know, 0:18:04.160 --> 0:18:07.199 that's why it's important, and we're going to see an 0:18:07.240 --> 0:18:09.440 increasing amount of this, and I think it's also important 0:18:09.440 --> 0:18:11.440 for people to get comfortable with the idea that these 0:18:11.440 --> 0:18:14.920 things will be roaming around and that it's okay. Yeah, 0:18:15.119 --> 0:18:17.720 And and on an interim basis, I mean, we're also 0:18:17.840 --> 0:18:21.159 talking about this same technology that allows a ship to 0:18:21.359 --> 0:18:25.720 sail autonomously also can be used to assist a human 0:18:25.760 --> 0:18:31.320 crew now, you know, basically be another set of eyes 0:18:31.520 --> 0:18:36.480 and years be a watchkeeper for a manned vessel. Right, 0:18:36.840 --> 0:18:40.800 I want to know more about the AI captain. How 0:18:40.840 --> 0:18:44.400 did you build it so that it would be comparable 0:18:44.560 --> 0:18:47.159 to the way a human captain might direct a ship. 0:18:47.560 --> 0:18:49.880 What we're trying to do is augment the person, Right, 0:18:49.880 --> 0:18:53.439 We're trying to let them be more of a person 0:18:53.520 --> 0:18:55.760 than sort of. They don't have to watch the radar, 0:18:55.840 --> 0:18:58.400 they don't have to watch the cameras. Right. The machine 0:18:58.440 --> 0:19:00.240 can do all that, and then if it can't do 0:19:00.400 --> 0:19:02.879 something safely, if it can't come to a solution, it 0:19:03.160 --> 0:19:06.120 can ask a person send a little texic, I don't 0:19:06.119 --> 0:19:08.080 know what to do, and then a person can, in 0:19:08.119 --> 0:19:11.720 a very calm way, with no stress, tell it what 0:19:11.760 --> 0:19:14.280 to do. But in the in the interim, they're doing 0:19:14.359 --> 0:19:18.280 something more important, like looking at all the information that's 0:19:18.320 --> 0:19:21.320 being produced by the instruments and having insight. You know, 0:19:21.400 --> 0:19:23.919 ever since we started sailing, there's been expectation of how 0:19:23.960 --> 0:19:26.800 ships interact with each other. Let's see, you know, they've 0:19:26.800 --> 0:19:30.920 been codified by the the I M O. Right, they're 0:19:30.920 --> 0:19:34.119 called like the regulations to prevent collisions at sea. We 0:19:34.240 --> 0:19:37.520 just called them coal ricks. But they're quite nuanced. Like 0:19:37.560 --> 0:19:39.959 it's not like they're called rules of the road, you know, 0:19:40.040 --> 0:19:42.680 after like the idea of like cars, but they're they're 0:19:42.760 --> 0:19:47.080 much more nuanced than like rules for cars. How you 0:19:47.160 --> 0:19:50.200 act depends on the type of vessels that are interacting, 0:19:50.240 --> 0:19:52.160 like if it's a sail boat or a fishing boat, 0:19:52.400 --> 0:19:56.840 or a container ship or a pleasure craft. Like imagine 0:19:56.840 --> 0:19:58.880 if you're driving your car down the road and you're 0:19:58.880 --> 0:20:01.360 at a stop sign, and then depending whether you could 0:20:01.400 --> 0:20:03.720 go or not depended on whether the other car about 0:20:03.760 --> 0:20:08.560 the stop sign was a bus or you know, or 0:20:08.600 --> 0:20:12.720 something else, Like the rules change anyway. So that's where 0:20:12.880 --> 0:20:16.600 humans are are really really good at. Is this nuanced 0:20:16.720 --> 0:20:24.720 understanding of these these rules, um squshy squishy rules. Yeah. So, 0:20:24.840 --> 0:20:26.639 and that's where we've done. You know, a lot of 0:20:26.640 --> 0:20:29.919 our lot of our work on is in that area. 0:20:30.280 --> 0:20:36.239 And that's the hardest part of this whole puzzle. I 0:20:36.280 --> 0:20:39.280 wonder if the ship ever got into any sticky situations 0:20:39.320 --> 0:20:41.880 that the AI captain was able to get it out of. 0:20:44.000 --> 0:20:46.359 One time, we had a sailboat come at us in 0:20:46.400 --> 0:20:50.600 the night head on reciprocal course, no lights on, no 0:20:50.760 --> 0:20:54.120 radar reflector. Everybody was probably asleep and they just had 0:20:54.119 --> 0:20:58.160 the autopilot on and um, we easily could have speared them, 0:20:58.359 --> 0:21:00.239 or they would have actually hit us because they were 0:21:00.240 --> 0:21:06.120 in violation of regulations. But but that's common, right, And see, 0:21:06.160 --> 0:21:08.440 when you're crossing, it's so unlikely, it's so fast that 0:21:08.480 --> 0:21:11.280 you're going to run into somebody, but it happens. So 0:21:11.320 --> 0:21:14.679 we you know, the ship took appropriate action and moved 0:21:14.680 --> 0:21:17.040 so that that wouldn't happen. But it's not like it 0:21:17.080 --> 0:21:20.040 seems very dramatic at the moment. But you know, you 0:21:20.080 --> 0:21:22.600 see these things coming miles away and it unfolds it 0:21:22.760 --> 0:21:26.639 like five miles an hour or something, right, So it's yeah, 0:21:26.680 --> 0:21:29.439 so it seems more nervous than it is. And I 0:21:29.440 --> 0:21:32.320 mean weather was challenging, and we had some failures technical 0:21:32.320 --> 0:21:35.119 and mechanical failures in the ship that were very very challenging. 0:21:35.840 --> 0:21:38.000 But from the AI captain perspective, the only time that 0:21:38.000 --> 0:21:41.439 we got annoyed was. There was a research ship that 0:21:41.440 --> 0:21:45.440 shall remain nameless from a university that was coming along 0:21:45.480 --> 0:21:47.200 and was going to cross in front of us by 0:21:47.280 --> 0:21:50.159 ten twelve miles, which is fine, and they were going along, 0:21:50.200 --> 0:21:53.480 but they clearly saw us on there, neither their radar 0:21:53.600 --> 0:21:57.200 or their automated identification system which we broadcast, and they 0:21:57.240 --> 0:21:59.439 just at some point turned and came directly at us 0:21:59.480 --> 0:22:03.080 at a angle that it's the it's the I'm messing 0:22:03.080 --> 0:22:05.919 with you angle, Yeah, the angle that allows them to 0:22:06.040 --> 0:22:09.720 maintain right of way but makes it very, very difficult 0:22:09.760 --> 0:22:12.840 to understand their intent and take action. So the ship 0:22:12.960 --> 0:22:15.520 was kind of like, if they had persisted, it would 0:22:15.520 --> 0:22:17.600 have ended up kind of going around in circles trying 0:22:17.600 --> 0:22:21.280 to avoid them. But but fortunately we had a support 0:22:21.280 --> 0:22:23.080