WEBVTT - Smart Talks with IBM - The Mayflower Autonomous Ship: AI and Automation at Sea 0:00:04.400 --> 0:00:07.800 Welcome to Tech Stuff, a production from I Heart Radio. 0:00:11.840 --> 0:00:14.480 This season of Smart Talks with IBM is all about 0:00:14.600 --> 0:00:18.480 new creators, the developers, data scientists, c t o s 0:00:18.560 --> 0:00:23.280 and other visionaries creatively applying technology in business to drive change. 0:00:23.800 --> 0:00:26.680 They use their knowledge and creativity to develop better ways 0:00:26.680 --> 0:00:30.280 of working, no matter the industry. Join hosts from your 0:00:30.320 --> 0:00:33.880 favorite Pushkin Industries podcasts as they use their expertise to 0:00:33.960 --> 0:00:37.480 deepen these conversations, and of course Malcolm Gladwell will guide 0:00:37.520 --> 0:00:39.839 you through the season as your host and provide his 0:00:39.920 --> 0:00:43.000 thoughts and analysis along the way. Look out for new 0:00:43.040 --> 0:00:45.480 episodes of Smart Talks with IBM on the I Heart 0:00:45.560 --> 0:00:49.159 Radio app, Apple Podcasts, or wherever you get your podcasts, 0:00:49.360 --> 0:00:56.040 and learn more at IBM dot com slash smart talks. Hello, Hello, 0:00:56.200 --> 0:00:59.560 Welcome to Smart Talks with IBM, a podcast from Pushkin 0:00:59.600 --> 0:01:03.600 Industry is I Heart Radio and IBM. I'm Malcolm Blobwell. 0:01:04.319 --> 0:01:09.000 This season we're talking to new creators, the developers, data scientists, 0:01:09.319 --> 0:01:12.479 c t o s and other visionaries who are creatively 0:01:12.520 --> 0:01:16.759 applying technology and business to drive change. Channeling their knowledge 0:01:16.760 --> 0:01:21.280 and expertise, they're developing more creative and effective solutions no 0:01:21.319 --> 0:01:24.920 matter the industry. Our guest today are Brett Fanoff and 0:01:25.040 --> 0:01:29.240 Don Scott. Brett and Dawn are responsible for creating the 0:01:29.280 --> 0:01:34.120 world's first unmanned, fully autonomous ship to cross the Atlantic Ocean, 0:01:34.560 --> 0:01:39.160 a research vessel they've dubbed the Mayflower four hundred. Brett 0:01:39.280 --> 0:01:42.680 is a director of the Mayflower Autonomous Ship Project and 0:01:42.760 --> 0:01:49.440 Dawn is the CTO of Marine AI. On June, the 0:01:49.480 --> 0:01:54.640 Mayflower four hundred successfully completed its voyage from Plymouth, UK 0:01:55.120 --> 0:01:59.920 to Plymouth, Massachusetts. It's both an homage to the original Mayflower, 0:02:00.280 --> 0:02:03.400 which crossed the Atlantic forundered years earlier, and a bell 0:02:03.480 --> 0:02:07.560 weather for the ways autonomous technology will push the boundaries 0:02:07.560 --> 0:02:12.839 of maritime exploration in the next four years. On today's show, 0:02:12.880 --> 0:02:17.560 the Unlikely Origins of a self directed Ship, some motion misadventures, 0:02:17.600 --> 0:02:20.640 and what AI and machine learning will mean for the 0:02:20.680 --> 0:02:25.240 future of seafaring and beyond, Brett and Dawn spoke with 0:02:25.360 --> 0:02:29.799 Lauren Ober, host of the forthcoming Pushkin podcast The Loudest 0:02:29.880 --> 0:02:32.839 Girl in the World. Lauren is a longtime radio host 0:02:32.880 --> 0:02:36.520 and reporter, helming shows like NPRS, The Big Listen, and 0:02:36.680 --> 0:02:42.760 Spectacular Failures from American public Media. Okay, now, let's get 0:02:42.800 --> 0:02:50.280 to the interview with Brett Fanoff and Don Scott. Don 0:02:50.400 --> 0:02:52.960 and Brett, it's really great to be talking with you 0:02:53.000 --> 0:02:56.040 guys today. I was wondering for each of you, what 0:02:56.320 --> 0:02:58.880 is the draw of the sea? I mean, it's like 0:02:58.960 --> 0:03:02.560 this explain It's a place. It feels so unknown in 0:03:02.639 --> 0:03:06.160 so many ways. Um, but I'm curious, like, what is 0:03:06.200 --> 0:03:08.600 the allure there for me? It's I wanted to be 0:03:08.680 --> 0:03:10.800 I wanted to do aerospace. So I always feel like 0:03:10.840 --> 0:03:13.960 I'm like like the poor cousin of aerospace, but it isn't. 0:03:14.040 --> 0:03:17.840 It's actually it's harder to to do the underwater stuff. 0:03:17.919 --> 0:03:20.639 It's closer. It's just harder than being in space. It's 0:03:21.240 --> 0:03:24.840 it's incredibly hostile and wildly unexplored. And why what I 0:03:24.880 --> 0:03:27.200 like about it is that you know, you can take 0:03:27.200 --> 0:03:28.919 a bucket and go down to the beach, get a 0:03:28.919 --> 0:03:31.560 bucket of water, analyze the bucket of water for the 0:03:31.600 --> 0:03:34.639 next twenty years, and you know, chances are pretty high 0:03:34.639 --> 0:03:36.160 you're gonna have a couple of things in there that 0:03:36.200 --> 0:03:39.560 nobody's ever seen before. And that's every bucket of water 0:03:39.720 --> 0:03:42.600 everywhere in the world, right, So I like the idea 0:03:42.680 --> 0:03:44.600 that you get to discover something new all the time, 0:03:44.640 --> 0:03:47.839 and it's also hard. It's a difficult place to work, 0:03:47.880 --> 0:03:50.200 so it challenges you to come up with new ideas 0:03:50.240 --> 0:03:52.480 and new ways to do things and new materials. And 0:03:53.000 --> 0:03:54.640 that's what I like about it. I don't know, don 0:03:54.680 --> 0:03:57.880 what about you. Yeah, I mean, there's obviously an allure 0:03:57.880 --> 0:04:00.880 and draw there's some great descriptions about why people are 0:04:00.960 --> 0:04:03.720 drawn to the ocean. Talk to the authors and the poets, 0:04:03.800 --> 0:04:06.240 you know, it's it's definitely a real sort of visceral 0:04:06.280 --> 0:04:08.280 feeling that people get. I think you find that the 0:04:08.320 --> 0:04:12.160 people that are involved in ocean engineering and or marine 0:04:12.200 --> 0:04:15.080 sides like that you'll just sort of fall into this 0:04:15.200 --> 0:04:19.200 career by accident. You make proactive decisions to get involved 0:04:19.480 --> 0:04:22.960 in that environment. So you have a bunch of people 0:04:23.040 --> 0:04:25.760 working there that that want to be there and sort 0:04:25.760 --> 0:04:30.440 of have this uh understanding of that this is the 0:04:30.440 --> 0:04:32.160 place they want to be and this is where they 0:04:32.160 --> 0:04:35.680 want to work. So that becomes a very very positive 0:04:35.800 --> 0:04:39.320 work environment workspace because everyone's they want to be there. 0:04:39.640 --> 0:04:43.360 So there's that. Yeah, it's highly collaborative, isn't it. It's 0:04:43.480 --> 0:04:47.080 um like anything, there's personalities, but it tends to be 0:04:47.120 --> 0:04:49.400 a lot of fun more than anything else. It's challenging 0:04:49.400 --> 0:04:51.240 in all the ways that make life interesting, and then 0:04:51.279 --> 0:04:53.400 it also tends to be a good time. And you 0:04:53.440 --> 0:04:56.920 can't work in the ocean by yourself, like, well, you can, 0:04:57.000 --> 0:05:00.839 but it's kind of hard, so press out. It's an 0:05:00.880 --> 0:05:04.160 incredibly collaborative environment. I mean, if you want to be 0:05:04.240 --> 0:05:07.200 doing anything of significance, you have to be working as 0:05:07.200 --> 0:05:09.360 a group because you need to rely on each other. 0:05:09.640 --> 0:05:14.159 It is an incredibly dynamic, hostile environment, very humbling. So 0:05:15.160 --> 0:05:18.640 you find you you're going to achieve success as a 0:05:18.680 --> 0:05:21.640 collaborative group as opposed to some sort of lone wolf 0:05:21.720 --> 0:05:25.000 type out to right. Okay, so we're here to talk 0:05:25.040 --> 0:05:31.200 about the Mayflower Autonomous Ship project, which obviously is very cool. Um, 0:05:31.240 --> 0:05:36.040 how exactly did you guys decide to build an autonomous 0:05:36.040 --> 0:05:40.520 ship and then model it after the Mayflower? I mean 0:05:40.560 --> 0:05:43.520 it was just to hold my beer kind of thing. Um, 0:05:43.560 --> 0:05:46.600 I'm sure what it really is, it really was, it 0:05:46.640 --> 0:05:49.599 really was. Yeah, what it really was is it was 0:05:51.560 --> 0:05:54.400 so in meeting with the City of Plymouth on something else, 0:05:54.480 --> 0:05:56.560 they were talking about what they were going to do 0:05:56.600 --> 0:05:59.240 and maybe built a replica ship, of which there's already one, 0:05:59.360 --> 0:06:02.280 And I thought that wasn't the best idea, and you're 0:06:02.320 --> 0:06:06.040 talking for anniversary. Yeah, and so I was a little 0:06:06.080 --> 0:06:10.279 bit indelicate in my comment as to how they wanted 0:06:10.320 --> 0:06:13.160 to proceed with a possible replica. You said it was 0:06:13.200 --> 0:06:16.040 a stupid idea, I said, I said it was stupid 0:06:16.440 --> 0:06:19.120 and uh and there was more I couldn't resist and 0:06:19.120 --> 0:06:20.760 and and I said, there already is one, you know, 0:06:20.800 --> 0:06:23.800 and it's it's just I grew up near there. And 0:06:23.800 --> 0:06:25.599 and so they said, all right, smart guy, what are 0:06:25.640 --> 0:06:26.839 you gonna do? I was like, oh, we should build 0:06:26.880 --> 0:06:31.200 one that challenges us technologically and from an engineering perspective 0:06:31.240 --> 0:06:34.080 and sort of invokes the spirit of the original risk 0:06:34.200 --> 0:06:37.760 taking and do something that informs the next four years. 0:06:37.760 --> 0:06:40.240 And everybody was like, yeah, you should do that. And 0:06:40.320 --> 0:06:41.760 I was like, you know what, I will hold my 0:06:41.839 --> 0:06:45.599 beer and uh so, so I called Don after the 0:06:45.640 --> 0:06:48.240 meeting and I was like, oh, Don, we we have 0:06:48.279 --> 0:06:51.000 to build an AI. I need Captain Watson because we're 0:06:51.000 --> 0:06:53.120 going to build an autn of a ship across the Atlantic. 0:06:53.240 --> 0:06:57.600 And he was like great, and so yeah, and it 0:06:57.680 --> 0:07:00.400 was just that literally that glib, but it also I 0:07:00.440 --> 0:07:02.280 mean he and I have been working on unmanned systems 0:07:02.279 --> 0:07:05.440 and autonomous systems for a long time together, twenty plus years, 0:07:05.440 --> 0:07:07.880 and so I wanted to see where we could get to, 0:07:08.000 --> 0:07:09.640 Like how hard could this be? Right I mean? And 0:07:10.000 --> 0:07:12.920 I sure, let's do it. Then, So we built a ship. 0:07:13.400 --> 0:07:17.760 You mentioned capturing the spirit of the original Mayflower journey, 0:07:17.760 --> 0:07:21.400 and I wonder what exactly where you're trying to capture. 0:07:21.560 --> 0:07:25.720 Was it the spirit of taking risks or was it 0:07:25.760 --> 0:07:29.880 doing something that hadn't been done before. What we were 0:07:29.880 --> 0:07:32.240 trying to do we knew was really hard, right, like, 0:07:32.400 --> 0:07:35.480 and it was a huge amount of risk to undertake it. 0:07:35.840 --> 0:07:38.080 Press the real risk taker. He's the one with the 0:07:38.080 --> 0:07:40.600 big ideas and wants to take the risk. I'm I'm 0:07:40.600 --> 0:07:44.600 a little more cautious and sort of pragmatic in the 0:07:44.640 --> 0:07:46.680 sense of, Okay, what's going to take to do that? 0:07:47.440 --> 0:07:49.560 We we actually didn't think we were going to make it, 0:07:49.680 --> 0:07:51.840 or I fully expected at some point the ocean we 0:07:51.920 --> 0:07:55.080 get annoyed and smite us, you know. Pilgrims like that 0:07:55.120 --> 0:07:57.200 to me is what's interesting. Pilgrims took a risk, right, 0:07:57.240 --> 0:08:01.240 so every one of them fully expected that they would die, 0:08:01.880 --> 0:08:04.720 if not on the voyage within like the first year, right, 0:08:05.160 --> 0:08:08.640 That's how it was, and it was worth it to 0:08:08.680 --> 0:08:12.960 them to take that risk. So our risk is infinitesimal 0:08:13.000 --> 0:08:16.160 by comparison, Right, it's tiny. What was our risk really, 0:08:16.360 --> 0:08:20.120 We'd lose a ship we spent some money on. So 0:08:20.160 --> 0:08:24.360 what the knowledge about how to approach these problems is, 0:08:24.520 --> 0:08:26.400 and the and the experience that you get to give 0:08:26.480 --> 0:08:29.880 people to take risk at that level from an engineering 0:08:29.880 --> 0:08:32.480 perspective is really important. Right, somebody had to do the 0:08:32.520 --> 0:08:36.520 first open heart surgery and took a risk. Now we're 0:08:36.520 --> 0:08:38.640 not doing open heart surgery. Right, no one's going to die. 0:08:39.080 --> 0:08:41.719 So what's appealing about the risk thing is it has 0:08:41.720 --> 0:08:45.400 a technical risk and environmental risk, and then there's a 0:08:45.480 --> 0:08:48.840 legislative and regulatory risk because we had to have our 0:08:48.920 --> 0:08:51.520 fights with various agencies about the fact that they didn't 0:08:51.520 --> 0:08:53.280 have a law that said we couldn't so they didn't 0:08:53.280 --> 0:08:55.440 get to say no just because they didn't want us to. 0:08:56.200 --> 0:08:59.240 And at the same time, trying to create a reliable 0:08:59.280 --> 0:09:02.400 machine and then some sort of an AI machine learning 0:09:02.440 --> 0:09:06.640 based system that would be safe whatever that is in 0:09:06.640 --> 0:09:09.520 the middle of the ocean. It's really interesting and gives 0:09:09.559 --> 0:09:11.559 people a lot to a lot of purchase for different 0:09:11.559 --> 0:09:14.880 people with different skill sets to collaborate. Brett and John 0:09:14.920 --> 0:09:18.920 started developing the Mayflower auton of a ship in It 0:09:18.960 --> 0:09:21.800 took them six years to figure out both the software 0:09:22.040 --> 0:09:24.920 and the body of the boat itself. In that time, 0:09:25.240 --> 0:09:29.640 over seventy people contributed to the project. Lauren asked Don 0:09:29.640 --> 0:09:32.640 and Brett what it really took to go from hold 0:09:32.679 --> 0:09:35.880 my beer to an actual ship? You know, it is 0:09:35.960 --> 0:09:40.040 mind boggling when you think of how many people are involved, 0:09:40.040 --> 0:09:44.199 how many people are touching this project, how many interesting 0:09:44.240 --> 0:09:47.280 minds doing interesting things, but you have to funnel it 0:09:47.320 --> 0:09:51.680 all into this one project. Well that I don't know 0:09:51.720 --> 0:09:53.200 if it's that way. I mean, I guess you could 0:09:53.200 --> 0:09:55.719 say there was one project, but there were lots of projects, 0:09:55.800 --> 0:09:58.280 and so, you know, there was sort of the hardcore 0:09:58.320 --> 0:10:00.200 group of people that are trying to build the full 0:10:00.240 --> 0:10:02.520 software that works, and then there's the guys trying to 0:10:02.559 --> 0:10:05.840 build the hardware and they have an interface, but they're 0:10:05.880 --> 0:10:09.520 parallel pursuits that don't have direct overlap. And then we 0:10:09.559 --> 0:10:11.880 said yes a lot to anybody who wanted to help, 0:10:12.520 --> 0:10:15.559 because we learned from experience that most people don't last 0:10:15.640 --> 0:10:18.439 in terms of the ability to stick out four or 0:10:18.480 --> 0:10:20.720 five years focus on the projects very hard, and so 0:10:20.800 --> 0:10:23.160 the people that I wanted to stick it out and 0:10:23.160 --> 0:10:26.440 bring it to fruition ended up you know, sticking it 0:10:26.440 --> 0:10:28.560 out and that was great, you know. And then there 0:10:28.600 --> 0:10:30.160 are all sorts of different things. There was a group 0:10:30.400 --> 0:10:32.360 making a web interface so that they could show the 0:10:32.400 --> 0:10:34.600 world what we were doing, and you know, then there 0:10:34.640 --> 0:10:37.360 was a PR group that was marketing things and sort 0:10:37.400 --> 0:10:39.600 of talking about how we tell the world about it, 0:10:39.600 --> 0:10:42.640 and we would support them. But it's hard to describe 0:10:42.640 --> 0:10:44.560 it as one project. I guess would be my position. 0:10:44.559 --> 0:10:48.720 It's lots of interlinked programs, right, Sure, I get that, 0:10:48.840 --> 0:10:52.120 I get that. Can you tell me more about how 0:10:52.200 --> 0:10:56.320 automation is built into the ship and how it works. Well, 0:10:56.480 --> 0:11:00.000 there's tons of automation and may Far, I mean Mayflower 0:11:00.200 --> 0:11:04.560 is like most robotics systems, right. So you peel it 0:11:04.600 --> 0:11:07.560 open and you find you know, programmable logic controllers and 0:11:07.600 --> 0:11:10.160 motor drives and also its of other things sensors and 0:11:10.880 --> 0:11:13.800 industrial automation that you'd see, you know in an elevator 0:11:13.880 --> 0:11:17.800 or an escalator or industrial machinery for manufacture. And that's 0:11:17.840 --> 0:11:20.200 one sort of layer of it. Right. So you've got 0:11:20.240 --> 0:11:22.679 the basic analog control. Then you've got sort of a 0:11:22.760 --> 0:11:26.520 veneer of automation, and then what I would call sophisticated automation, 0:11:26.559 --> 0:11:29.560 which Don and I have worked on for decades in 0:11:29.600 --> 0:11:32.480 the marine space. So all that's in there. And you know, 0:11:32.679 --> 0:11:35.480 Don and I talked really early on if I just 0:11:35.520 --> 0:11:37.320 wanted to get across the Atlantic, we could have bought 0:11:37.320 --> 0:11:40.200 an old fishing boat, filled up the fish hoolds with 0:11:40.280 --> 0:11:42.800 diesel fuel, and put a cheap autopilot on it and 0:11:42.840 --> 0:11:45.520 sent it. It probably would have got across. But so 0:11:45.679 --> 0:11:50.720 what it's not reducing risk, and it's not unburdening a person, 0:11:51.559 --> 0:11:55.800 and it's not doing anything really clever or sophisticated. And 0:11:55.880 --> 0:11:58.160 so what we were more interested in was getting to 0:11:58.200 --> 0:12:00.040 a point where instead of having to tell it to 0:12:00.040 --> 0:12:03.920 do everything, saying go do this task right, a goal 0:12:04.160 --> 0:12:06.640 like go to Plymouth right, and then while you're doing that, ah, 0:12:06.679 --> 0:12:08.920 by the way, while you're doing that, collect all this 0:12:09.000 --> 0:12:11.600 science data and if you see anything unusual, tell us 0:12:11.720 --> 0:12:14.559 and and while you're looking for all these unusual things 0:12:14.559 --> 0:12:18.920 and trying to achieve your goal, don't hit anything. So 0:12:18.960 --> 0:12:22.199 then what role did IBM S technology play in all 0:12:22.240 --> 0:12:26.240 of this? Yeah? I mean their their technology is all 0:12:26.280 --> 0:12:29.640 over the ship. Probably the main contribution it was the 0:12:29.679 --> 0:12:34.320 decision making process or it's it's an automation TOOLM operational 0:12:34.360 --> 0:12:38.200 decision manager. It's actually a financial services tool. It's for 0:12:38.840 --> 0:12:43.400 your making decisions about the viability of a transaction, whether 0:12:43.440 --> 0:12:46.680 it's fraud or order or alone or let's say, And 0:12:47.200 --> 0:12:51.439 we were being presented this by one of the ODIUM engineers, 0:12:51.520 --> 0:12:53.040 and I remember sitting in the room with Brett thing, 0:12:53.200 --> 0:12:56.679 what what in the world does financial services product have 0:12:56.800 --> 0:12:59.760 to do with marine navigation And they sort of were 0:12:59.760 --> 0:13:03.679 brought to realize by the IBM engineer how this is. 0:13:04.120 --> 0:13:06.600 This isn't really so much about financial services as it 0:13:06.679 --> 0:13:10.400 is about making making really difficult decisions in a really 0:13:10.440 --> 0:13:14.040 complex environment, which is what they do in financial services. 0:13:14.080 --> 0:13:16.400 But it's also exactly what we needed to do in 0:13:17.080 --> 0:13:20.640 re navigation. And when the when the system was actually rounding, 0:13:20.960 --> 0:13:25.480 it would create a log essentially of why that decision 0:13:25.559 --> 0:13:29.080 was made, so they can validate that decision and verify 0:13:29.160 --> 0:13:31.520 and validate that that that was in fact the right decision. 0:13:32.040 --> 0:13:34.319 And um, so that's a that's one of the key 0:13:34.640 --> 0:13:37.000 IVM tools that are on board. Well, one of the 0:13:37.040 --> 0:13:40.320 things you might want to consider about that is the fundamentals, right, 0:13:40.400 --> 0:13:43.120 the theoretical independence of all the AI that we're deploying 0:13:43.160 --> 0:13:46.920 now have been sort of understood for decades, right, and 0:13:46.960 --> 0:13:48.960 so now we just happened to live in a world 0:13:49.520 --> 0:13:52.200 where the microprocesses are up to snuff that they can 0:13:52.240 --> 0:13:55.280 deploy some of these very sophisticated theoretical and reality and 0:13:55.320 --> 0:13:57.600 all of which IBM has been involved with from inception 0:13:58.280 --> 0:14:00.880 based on its pedigree is in a national business machines. 0:14:01.280 --> 0:14:04.480 There isn't an IBM product that I can think of 0:14:04.800 --> 0:14:08.520 that we haven't tried to utilize the deploying so it's 0:14:08.600 --> 0:14:11.400 it's it's everywhere in the ship. Yeah. I don't think 0:14:11.400 --> 0:14:15.240 a lot of people think of technology as as as 0:14:15.240 --> 0:14:19.840 a creative pursuit, but I imagine building an autonomous ship 0:14:19.880 --> 0:14:23.160 from scratch takes a lot of creativity. And I'm wondering, 0:14:23.280 --> 0:14:27.280 do you guys think of your work as creative? Yeah, 0:14:27.480 --> 0:14:32.040 engineering is essentially designing technological innovation sort of. You think 0:14:32.080 --> 0:14:35.240 of it as a very logical process, and there is that, 0:14:35.400 --> 0:14:39.160 for sure, but there's an incredible amount of innovation involved too, 0:14:39.440 --> 0:14:42.200 Like there's no template for what we're doing, and you know, 0:14:42.240 --> 0:14:45.400 we call it white paper design where you're basically given 0:14:45.440 --> 0:14:49.080 a blank piece of paper and a goal, which is, okay, 0:14:49.200 --> 0:14:52.600 ship that's going to cross the Atlantic, Um, okay, come 0:14:52.680 --> 0:14:55.680 up with some ideas, right, So I mean it requires 0:14:56.480 --> 0:14:59.920 major conceptual leaps and then the technical skill to realize 0:15:00.280 --> 0:15:03.440 those those sleeps. You're not going to make any advances 0:15:03.520 --> 0:15:06.120 just doing things the way you've always done them. Right. 0:15:06.200 --> 0:15:09.840 You need to stretch, right, and the only way it 0:15:09.880 --> 0:15:13.680 stretch is what implementing new ideas like you can spend 0:15:13.920 --> 0:15:16.960 a decade. We call it power point engineering right where 0:15:16.960 --> 0:15:18.840 you do nothing but think of things. We don't actually 0:15:18.920 --> 0:15:23.560 do anything, as opposed to what we call full contact engineering, 0:15:23.560 --> 0:15:28.040 where you actually built the boat right the software to 0:15:28.080 --> 0:15:30.240 go on the boat and send it out on the water, 0:15:31.440 --> 0:15:34.080 get your kicked, like, get sea sick, you know, all 0:15:34.080 --> 0:15:35.960 that sort of fun stuff that happens when you don't 0:15:36.000 --> 0:15:40.480 see trials. Um. And because that's where you that's where 0:15:40.480 --> 0:15:43.160 the actual learning is happening, that's where the actual development 0:15:43.240 --> 0:15:46.560 is happening, is being out on the ocean. Crossing the 0:15:46.560 --> 0:15:49.920 Atlantic is no small voyage for any vessel, but the 0:15:50.000 --> 0:15:53.760 Mayflower Autonomous Ship Project is more than just about sailing 0:15:53.840 --> 0:15:58.120 from point A to point B. Automation and AI have 0:15:58.320 --> 0:16:01.560 game changing implications for the way we design the next 0:16:01.640 --> 0:16:05.000 generation of vessels and the way these vessels will behave 0:16:05.360 --> 0:16:09.080 and interact at sea. Ships will be able to gather 0:16:09.200 --> 0:16:13.400 data from the ocean by themselves, providing humans with critical 0:16:13.440 --> 0:16:18.720 information we need to address problems like global warming, ocean pollution, 0:16:19.160 --> 0:16:22.720 and our impact on marine life. For instance, the Mayfire 0:16:22.800 --> 0:16:27.560 four hundred can sample ocean water from microplastics and record 0:16:27.720 --> 0:16:32.760 audio of whale vocalizations. Taking the human factor out of 0:16:32.760 --> 0:16:36.600 a ship allows us to explore new designs and functions 0:16:36.640 --> 0:16:40.600 that haven't been imagined before. Lauren asked bread and Down 0:16:41.000 --> 0:16:43.720 more about this. What are some of the benefits of 0:16:43.760 --> 0:16:48.280 having an unmanned vessel, like, how does automation push the 0:16:48.320 --> 0:16:51.720 boundaries of what we can do out in the ocean? Well, 0:16:51.720 --> 0:16:54.320 the few major variables right or true facets to that. 0:16:54.400 --> 0:16:57.520 One is you can do some risky things when you 0:16:57.520 --> 0:16:59.520 don't have the people there, right, because no one's going 0:16:59.560 --> 0:17:02.280 to be law cost at sea. And then the other 0:17:02.320 --> 0:17:04.320 thing is you can drive cost down, and I mean 0:17:04.359 --> 0:17:07.600 cost financially but also environmental cost RCT because you can 0:17:08.000 --> 0:17:10.920 use a far less energy to accomplish a similar goal. 0:17:11.600 --> 0:17:14.360 And then what that allows you to do is have more. Right, 0:17:14.400 --> 0:17:18.919 So instead of say having one fifty million dollar hundred 0:17:18.920 --> 0:17:21.399 million dollar research ship, which is the kind of numbers 0:17:21.400 --> 0:17:24.360 you're talking about to take scientists to see, you can 0:17:24.440 --> 0:17:28.359 have twenty or thirty or forty million dollars or two 0:17:28.440 --> 0:17:31.679 million dollar ships that go out and work collaboratively with 0:17:31.720 --> 0:17:34.720 space based assets and with one another and collect vast 0:17:34.720 --> 0:17:37.479 amounts of data from disparate parts of the ocean. And 0:17:37.520 --> 0:17:41.240 then you use that data to create information that informs 0:17:41.240 --> 0:17:44.120 where you send the man vessel, right, so that they 0:17:44.160 --> 0:17:46.919 get the most out of their time at sea. So 0:17:46.920 --> 0:17:49.919 it's about enabling the people. It's about leaving the humans 0:17:49.960 --> 0:17:52.080 to do the uniquely human part, which is have the 0:17:52.160 --> 0:17:56.080 insight and the intuition and and the creativity. And so 0:17:56.520 --> 0:17:59.520 you know, that's why it's important. And we're going to 0:17:59.560 --> 0:18:01.360 see an freezing amount of this. And I think it's 0:18:01.359 --> 0:18:03.800 also important for people to get comfortable with the idea 0:18:03.840 --> 0:18:07.600 that these things will be roaming around and that it's okay. Yeah, 0:18:07.800 --> 0:18:10.400 And and on an insim basis, I mean, we're also 0:18:10.520 --> 0:18:13.840 talking about this same technology that allows a ship to 0:18:14.040 --> 0:18:18.399 sail autonomously also can be used to assist a human 0:18:18.440 --> 0:18:24.000 crew now, you know, basically be another set of eyes 0:18:24.200 --> 0:18:29.160 and years be a watchkeeper for a manned vessel. Right, 0:18:29.520 --> 0:18:33.480 I want to know more about the AI captain. How 0:18:33.520 --> 0:18:37.040 did you build it so that it would be comparable 0:18:37.200 --> 0:18:39.840 to the way a human captain might direct a ship. 0:18:40.240 --> 0:18:42.560 What we're trying to do is augment the person, right, 0:18:42.560 --> 0:18:46.119 We're trying to let them be more of a person 0:18:46.200 --> 0:18:48.440 than sort of. They don't have to watch the radar, 0:18:48.480 --> 0:18:51.080 they don't have to watch the cameras. Right. The machine 0:18:51.119 --> 0:18:52.959 can do all that, and then if you can't do 0:18:53.040 --> 0:18:55.560 something safely, if it can't come to a solution, it 0:18:55.840 --> 0:18:58.800 can ask a person send a little texic, I don't 0:18:58.800 --> 0:19:00.879 know what to do, and a person can, in a 0:19:01.000 --> 0:19:04.840 very calm way, with no stress, tell it what to do. 0:19:05.080 --> 0:19:08.679 But in the in the interim, they're doing something more important, 0:19:08.760 --> 0:19:11.679 like looking at all the information that's being produced by 0:19:11.680 --> 0:19:14.600 the instruments and having insight. You know, Ever since we 0:19:14.680 --> 0:19:17.480 started sailing, there's been expectation of how ships interact with 0:19:17.520 --> 0:19:21.080 each other. Let's see, you know, they've been codified by 0:19:21.200 --> 0:19:24.040 the what the I M O. Right, they're called like 0:19:24.119 --> 0:19:27.119 the regulations to prevent collisions at sea. We just call 0:19:27.200 --> 0:19:30.560 them coal ricks. But they're quite nuanced. Like it's not 0:19:30.640 --> 0:19:33.000 like they're called rules of the road, you know, after 0:19:33.119 --> 0:19:35.600 like the idea of like cars, but they're they're much 0:19:35.640 --> 0:19:40.080 more nuanced than like rules for cars. How you act 0:19:40.160 --> 0:19:43.000 depends on the type of vessels that are interacting, like 0:19:43.040 --> 0:19:45.159 if it's a sail boat or a fishing boat, or 0:19:45.200 --> 0:19:49.520 a a container ship or a pleasure craft. Like imagine 0:19:49.520 --> 0:19:51.560 if you're driving your car down the road and you're 0:19:51.560 --> 0:19:54.040 at a stop sign, and then depending whether you could 0:19:54.040 --> 0:19:56.399 go or not, depending on whether the other car about 0:19:56.440 --> 0:20:00.320 the stop sign was a thrust, a bus or you know, 0:20:01.119 --> 0:20:05.240 or something else, like, the rules change anyway. So that's 0:20:05.240 --> 0:20:08.520 where humans are are really really good at. Is this 0:20:08.720 --> 0:20:17.399 nuanced understanding of these these rules, um squashy rules. Yeah. So, 0:20:17.520 --> 0:20:19.320 and that's where we've done. You know a lot of 0:20:19.320 --> 0:20:22.600 our lot of our work on is in that area. 0:20:22.960 --> 0:20:27.800 And that's the hardest part of this whole possit r. 0:20:28.800 --> 0:20:31.160 I wonder if the ship ever got into any sticky 0:20:31.240 --> 0:20:34.119 situations that the AI captain was able to get it 0:20:34.160 --> 0:20:38.560 out of. One time we had a sailboat come at 0:20:38.640 --> 0:20:42.920 us in the night head on reciprocal course, no lights on, 0:20:43.200 --> 0:20:46.600 no radar reflector. Everybody was probably asleep and they just 0:20:46.640 --> 0:20:50.280 had the autopilot on and um, we easily could have 0:20:50.320 --> 0:20:52.639 speared them, or they would have actually hit us because 0:20:52.640 --> 0:20:58.359 they were in violation of race regulations. But but that's common, right. 0:20:58.400 --> 0:21:00.720 Let's see, when you're crossing, it's so likely, it's so 0:21:00.760 --> 0:21:03.800 fast that you're going to run into somebody, but it happens, 0:21:03.800 --> 0:21:06.959 so we you know, the ship took appropriate action and 0:21:07.000 --> 0:21:09.480 moved so that that wouldn't happen. But it's not like 0:21:09.640 --> 0:21:12.560 it seems very dramatic at the moment. But you know, 0:21:12.640 --> 0:21:15.240 you see these things coming miles away and it unfolds 0:21:15.240 --> 0:21:18.000 it like five miles an hour or something, right, So 0:21:18.040 --> 0:21:21.240 it's yeah, so it seems more nervous than it is. 0:21:21.320 --> 0:21:23.959 And I mean, weather was challenging, and we had some 0:21:24.080 --> 0:21:26.600 failures technical and mechanical failures in the ship that were 0:21:26.720 --> 0:21:30.159 very very challenging. But from the AI captain perspective, the 0:21:30.200 --> 0:21:33.280 only time that we got annoyed was there was a 0:21:33.359 --> 0:21:36.680 research ship that shall remain nameless from a university that 0:21:36.760 --> 0:21:39.359 was coming along and was going to cross in front 0:21:39.359 --> 0:21:41.800 of us by ten twelve miles, which is fine, and 0:21:41.960 --> 0:21:44.520 they were going along, but they clearly saw us on there, 0:21:45.320 --> 0:21:49.000 neither their radar or their automated identification system which we broadcast, 0:21:49.080 --> 0:21:51.760 and they just at some point turned and came directly 0:21:51.800 --> 0:21:54.960 at us at at an angle that it's the it's 0:21:55.000 --> 0:21:57.760 the I'm messing with you angle, Yeah, the angle that 0:21:57.800 --> 0:22:01.080 allows them to maintain right of way but makes it 0:22:01.359 --> 0:22:04.479 very very difficult to understand their intent and take action. 0:22:05.000 --> 0:22:07.880 So the ship was kind of like, if they had persisted, 0:22:07.920 --> 0:22:09.600 it would have ended up kind of going around in 0:22:09.640 --> 0:22:13.520 circles trying to avoid them. But but fortunately we had 0:22:13.520 --> 0:22:15.399 a support boat that was coming out of Halifax to 0:22:15.480 --> 0:22:18.879 meet it, and it physically got in between the Mayflower 0:22:18.920 --> 0:22:21.560 and this research boat and so what are you doing? Oh, 0:22:21.800 --> 0:22:23.719