1 00:00:04,200 --> 00:00:07,520 Speaker 1: Get in text with technology with text Stuff from stuff 2 00:00:07,800 --> 00:00:14,000 Speaker 1: dot com either everyone, and welcome to Tech Stuff. I'm 3 00:00:14,080 --> 00:00:18,400 Speaker 1: Jonathan Strickland and I'm joined by a special guest host today, 4 00:00:18,520 --> 00:00:22,599 Speaker 1: someone who is on the most popular podcast in the 5 00:00:22,680 --> 00:00:27,159 Speaker 1: How Stuff Works suite of shows, Josh Clark Glow, co 6 00:00:27,360 --> 00:00:29,840 Speaker 1: host of Stuff You Should Know. Josh, thank you so 7 00:00:29,920 --> 00:00:32,560 Speaker 1: much for joining us. Thank you for having me here. 8 00:00:32,760 --> 00:00:35,880 Speaker 1: And Josh has been very kind. He's had me on 9 00:00:36,200 --> 00:00:37,879 Speaker 1: Stuff you Should Know. Way back in the day when 10 00:00:37,920 --> 00:00:40,680 Speaker 1: you guys were doing one on the Necronomicon. Yeah, we 11 00:00:40,680 --> 00:00:43,680 Speaker 1: were starting to get knee deep into it and realizing 12 00:00:43,720 --> 00:00:46,320 Speaker 1: that we were going to get a lot, a lot 13 00:00:46,440 --> 00:00:49,480 Speaker 1: of listener mail, so we came and got you. You 14 00:00:49,479 --> 00:00:51,680 Speaker 1: know what was funny was that no warning, you came 15 00:00:51,720 --> 00:00:55,160 Speaker 1: to me asking about pronunciation I think two times, and 16 00:00:55,200 --> 00:00:57,120 Speaker 1: then on the third time you're like, just come on 17 00:00:57,160 --> 00:01:00,320 Speaker 1: inside the studio and you came and said down and 18 00:01:00,360 --> 00:01:05,280 Speaker 1: talked about the Necronomicon like a promicron. I know this 19 00:01:05,360 --> 00:01:10,080 Speaker 1: by the way, Yeah, Nickronomicon, Necronomicon. Okay, Yeah, and um 20 00:01:10,640 --> 00:01:12,760 Speaker 1: I am still to this day impressed. And that was 21 00:01:13,080 --> 00:01:15,640 Speaker 1: five years ago. Yeah, yeah, and then they haven't had 22 00:01:15,640 --> 00:01:18,720 Speaker 1: me on since But anyway, we had Josh on today. No, 23 00:01:19,880 --> 00:01:22,760 Speaker 1: you guys are super busy even out. Yeah, I know, 24 00:01:22,959 --> 00:01:25,840 Speaker 1: I was the one dragging my feet. Yeah, And I 25 00:01:25,840 --> 00:01:28,080 Speaker 1: asked Josh what he would like to cover because with 26 00:01:28,360 --> 00:01:30,160 Speaker 1: the fact that I've got all these guests coming in 27 00:01:30,200 --> 00:01:32,720 Speaker 1: to sit down with me. Um. You know, some people 28 00:01:32,880 --> 00:01:35,680 Speaker 1: like to come up with their own suggestions. Some people 29 00:01:35,720 --> 00:01:38,600 Speaker 1: preferred if I pick a topic and then they research it. 30 00:01:38,959 --> 00:01:40,639 Speaker 1: I asked Josh what he would like to talk about, 31 00:01:40,840 --> 00:01:44,640 Speaker 1: and you were really interested in the idea of humanoid robots. Well, 32 00:01:44,720 --> 00:01:48,840 Speaker 1: you have this awesome spreadsheet of um of listeners suggestions 33 00:01:49,520 --> 00:01:51,440 Speaker 1: and it might as well have been a neon when 34 00:01:51,440 --> 00:01:53,640 Speaker 1: it was going down the sheet. I'm like humanoid robots, 35 00:01:53,640 --> 00:01:57,320 Speaker 1: of course, and this is a great topic. In order 36 00:01:57,400 --> 00:01:59,160 Speaker 1: to really get into it, I was going to define 37 00:01:59,240 --> 00:02:01,320 Speaker 1: a few terms, even though a lot of these are 38 00:02:01,920 --> 00:02:03,520 Speaker 1: ones that I think most of us just kind of 39 00:02:04,480 --> 00:02:07,360 Speaker 1: understand just from the fact that this is in our 40 00:02:07,400 --> 00:02:10,360 Speaker 1: culture now. It's not just not just a reality as 41 00:02:10,360 --> 00:02:12,440 Speaker 1: far as technology goes, but it plays a large part 42 00:02:12,520 --> 00:02:15,040 Speaker 1: in fiction. In fact, that's where the term robot comes 43 00:02:15,080 --> 00:02:20,119 Speaker 1: from is from fiction. Uh, it was from Carrel Chopeck, 44 00:02:20,800 --> 00:02:25,640 Speaker 1: a Czechoslovakian playwright. I did, in fact listen to it 45 00:02:25,840 --> 00:02:29,080 Speaker 1: a couple of times. Correl Chope Yeah, because it's his 46 00:02:29,120 --> 00:02:31,760 Speaker 1: last name, is spelled c A p e k. And 47 00:02:31,800 --> 00:02:36,919 Speaker 1: it includes uh symbols that are not in the English alphabet, 48 00:02:36,960 --> 00:02:40,960 Speaker 1: like squiggly lines and little UFOs and things he wrote. 49 00:02:41,280 --> 00:02:45,040 Speaker 1: Are you are also known as Rossum's Universal Robots, and 50 00:02:45,080 --> 00:02:47,679 Speaker 1: the word robot comes from the check word robot to, 51 00:02:48,240 --> 00:02:53,000 Speaker 1: which means forced labor. Yeah, so a robot is a 52 00:02:53,000 --> 00:02:57,760 Speaker 1: an entity, a synthetic construct that is forced to do work. 53 00:02:58,639 --> 00:03:01,639 Speaker 1: Then we have humanoid, which just means resembling a human being. 54 00:03:02,840 --> 00:03:06,919 Speaker 1: That's a term that is relatively young. It started showing 55 00:03:06,960 --> 00:03:10,720 Speaker 1: up around the turn of the twentieth century, and uh 56 00:03:10,880 --> 00:03:13,840 Speaker 1: it started I think the first few times it was 57 00:03:13,880 --> 00:03:17,120 Speaker 1: ever mentioned was around nineteen twelve, and it was mostly 58 00:03:17,240 --> 00:03:20,920 Speaker 1: used then to describe fossils, saying these are humanoid fossils, 59 00:03:21,520 --> 00:03:26,520 Speaker 1: like yeah. And then we have android, which is we're 60 00:03:26,520 --> 00:03:28,520 Speaker 1: probably not gonna be using that word very often, but 61 00:03:28,880 --> 00:03:31,520 Speaker 1: android is a robot that's in the form of a human. 62 00:03:32,040 --> 00:03:35,320 Speaker 1: So all androids or robots, but not all robots are androids. 63 00:03:35,360 --> 00:03:37,680 Speaker 1: And you know, I ran into I looked up android 64 00:03:37,720 --> 00:03:40,200 Speaker 1: as well. Yeah, and apparently that's from like the early 65 00:03:40,320 --> 00:03:45,040 Speaker 1: eighteenth century. It's a little odd that it actually predates robots. Yeah, 66 00:03:45,080 --> 00:03:48,800 Speaker 1: but uh, when we look at myths and legends, there's 67 00:03:48,840 --> 00:03:52,480 Speaker 1: so many stories that involve a human like entity that's 68 00:03:52,520 --> 00:03:55,040 Speaker 1: not actually a person that you can see where it 69 00:03:55,080 --> 00:03:58,000 Speaker 1: gets translated in there. This gets a little confusing too, 70 00:03:58,000 --> 00:04:01,920 Speaker 1: because Star Wars they called all their abouts droids, but 71 00:04:02,040 --> 00:04:04,280 Speaker 1: there they aren't androids are two? T two is not 72 00:04:04,360 --> 00:04:08,440 Speaker 1: an android because he's not um or it's not human shaped. 73 00:04:09,000 --> 00:04:10,840 Speaker 1: You could even argue that C three Po is not 74 00:04:10,920 --> 00:04:13,440 Speaker 1: a true android because some people say to be an 75 00:04:13,440 --> 00:04:16,440 Speaker 1: android you have to appear, at least on casual glance 76 00:04:16,560 --> 00:04:20,360 Speaker 1: to be human. He's way too shiny, way too shiny. 77 00:04:20,440 --> 00:04:24,560 Speaker 1: Data from Star Trek next Generation might be uh android, 78 00:04:24,640 --> 00:04:27,799 Speaker 1: but he's an android who's had, you know, a long 79 00:04:27,880 --> 00:04:31,080 Speaker 1: time in the man cave. He hasn't seen much sun, right, Yeah, 80 00:04:31,080 --> 00:04:34,360 Speaker 1: because he's definitely got a weird complexion. Thing goes the 81 00:04:34,440 --> 00:04:37,680 Speaker 1: kid in a I would be an android David yes, 82 00:04:37,839 --> 00:04:40,800 Speaker 1: which turns out to be a popular name for droids 83 00:04:41,480 --> 00:04:43,680 Speaker 1: because there was well, there's David in AI and there 84 00:04:43,720 --> 00:04:46,240 Speaker 1: was also David and Prometheus. Oh you know, I never 85 00:04:46,279 --> 00:04:49,839 Speaker 1: saw Prometheus. I don't know if your listeners are going 86 00:04:49,920 --> 00:04:52,119 Speaker 1: to agree with me or not, because I could see 87 00:04:52,360 --> 00:04:55,599 Speaker 1: um getting shouted down. But I thought Prometheus was a 88 00:04:55,640 --> 00:04:58,600 Speaker 1: great movie. Even even upon second viewing, I thought it 89 00:04:58,640 --> 00:05:01,680 Speaker 1: was good. You know, I know that the from the 90 00:05:01,760 --> 00:05:04,200 Speaker 1: artistic level, a lot of people really loved it. And 91 00:05:04,240 --> 00:05:05,919 Speaker 1: then there were some people who said, how can you 92 00:05:05,960 --> 00:05:09,480 Speaker 1: get lost if you have a three dimensional map with 93 00:05:09,520 --> 00:05:12,039 Speaker 1: you at all time? But you know, plot versus artists, 94 00:05:12,680 --> 00:05:16,239 Speaker 1: I don't know. Then you've got replicants from Blade Runner. 95 00:05:16,320 --> 00:05:18,800 Speaker 1: These are more like cyborgs because they have some sort 96 00:05:18,800 --> 00:05:24,040 Speaker 1: of organic material attached to them. They're not completely you know, 97 00:05:24,440 --> 00:05:28,800 Speaker 1: synthetic material. So Terminator is another example. They have a 98 00:05:28,839 --> 00:05:32,560 Speaker 1: fleshy over skin on top of their metallic bodies. But 99 00:05:32,720 --> 00:05:35,640 Speaker 1: was that real skin that he had there was synthetic skin, 100 00:05:35,640 --> 00:05:37,560 Speaker 1: because that would make a difference. That's a good question. 101 00:05:37,640 --> 00:05:40,080 Speaker 1: And I uh, you know, I know that they referred 102 00:05:40,080 --> 00:05:42,400 Speaker 1: to them as cyborgs at least a few times in 103 00:05:42,440 --> 00:05:45,400 Speaker 1: the movies, which would suggest that it's actual skin. Maybe 104 00:05:45,480 --> 00:05:52,080 Speaker 1: it's lab grown human skin. So you know, there's some 105 00:05:52,320 --> 00:05:56,120 Speaker 1: fuzzy lines around these definitions. I would think that cyborgs 106 00:05:56,120 --> 00:05:59,960 Speaker 1: would be the hardest of all of the the humanoid 107 00:06:00,120 --> 00:06:03,680 Speaker 1: robots to make, because the flesh were just rot Like 108 00:06:03,760 --> 00:06:07,919 Speaker 1: you have your normal looking humanoid robot, your cyborg, and 109 00:06:07,960 --> 00:06:10,640 Speaker 1: it's ear would just fall off. Yeah, and it's not 110 00:06:10,800 --> 00:06:14,520 Speaker 1: as easy as you might think to wire together the 111 00:06:14,560 --> 00:06:18,080 Speaker 1: wet wear that's in our heads with hardware that runs 112 00:06:18,080 --> 00:06:22,200 Speaker 1: on circuits. We will often think of computers working in 113 00:06:22,200 --> 00:06:24,160 Speaker 1: a way that's similar to our brains, but in fact 114 00:06:24,240 --> 00:06:27,120 Speaker 1: the two work in very different ways. Well, it seems 115 00:06:27,120 --> 00:06:31,839 Speaker 1: like running into this, though Strickland um. The the more 116 00:06:32,240 --> 00:06:35,760 Speaker 1: we got into humanoid robotics, the more we started to 117 00:06:35,839 --> 00:06:38,760 Speaker 1: understand just how complex we are. Yeah, that's one of 118 00:06:38,800 --> 00:06:41,760 Speaker 1: the things that I think is a benefit of study 119 00:06:41,800 --> 00:06:45,520 Speaker 1: of humanoid robotics. The idea of pursuing the goal of 120 00:06:45,520 --> 00:06:48,159 Speaker 1: creating a humanoid robot is not just that we learn 121 00:06:48,600 --> 00:06:51,560 Speaker 1: more about all the different areas and robotics, and they're 122 00:06:51,600 --> 00:06:53,560 Speaker 1: a lot, and we'll talk about some of them, but 123 00:06:53,640 --> 00:06:57,120 Speaker 1: we also learn more about ourselves. We're trying to figure out, okay, 124 00:06:57,160 --> 00:06:59,920 Speaker 1: if we're going to make something that is able to 125 00:07:00,040 --> 00:07:02,840 Speaker 1: performed tasks the way human does. Then we really got 126 00:07:02,839 --> 00:07:06,000 Speaker 1: to take a close look at humans. That's that's the 127 00:07:06,040 --> 00:07:11,760 Speaker 1: first place to start. So what makes a humanoid robot? 128 00:07:12,000 --> 00:07:14,760 Speaker 1: And generally speaking, we're talking about a robot that has 129 00:07:15,280 --> 00:07:19,120 Speaker 1: basic features, usually at minimum a torso, arms and legs, 130 00:07:19,240 --> 00:07:22,760 Speaker 1: and is walking up right. Uh. It may have a 131 00:07:22,760 --> 00:07:26,000 Speaker 1: head or it might not. Early humanoid robots didn't, or 132 00:07:26,000 --> 00:07:31,600 Speaker 1: at least their sensory uh, instruments were all located within 133 00:07:31,640 --> 00:07:34,640 Speaker 1: the top part of the torso there wasn't like a 134 00:07:34,680 --> 00:07:37,880 Speaker 1: separate head. Did you see a picture of Minerva at 135 00:07:37,880 --> 00:07:40,520 Speaker 1: the Smithsonian. No? I did not. It's a robot to 136 00:07:40,560 --> 00:07:43,920 Speaker 1: her guide, But um, she came up in the humanoid 137 00:07:44,000 --> 00:07:47,560 Speaker 1: robot research and I think she's stretching it a little bit. Yeah, 138 00:07:47,600 --> 00:07:50,360 Speaker 1: she looks a bit like a washing machine with a 139 00:07:50,360 --> 00:07:55,360 Speaker 1: couple of UM cameras on top. So just those alone, 140 00:07:55,400 --> 00:07:59,240 Speaker 1: I guess makes her eligible for the humanoid robot realm. 141 00:07:59,320 --> 00:08:02,200 Speaker 1: But to stretching that, that seems like that's a bit 142 00:08:02,240 --> 00:08:04,520 Speaker 1: of a you know, if it has an appendage, that 143 00:08:04,560 --> 00:08:06,760 Speaker 1: doesn't necessarily make a humanoid. I mean you could look 144 00:08:06,800 --> 00:08:10,320 Speaker 1: at the Mars Curiosity rover, which has several appendages. But 145 00:08:10,360 --> 00:08:15,080 Speaker 1: I don't think anyone would ever describe it as humanoid, right, So, uh, 146 00:08:15,120 --> 00:08:18,880 Speaker 1: ideally a humanoid robot would be able to interact with 147 00:08:18,960 --> 00:08:23,440 Speaker 1: humans within a human environment. Because here's the thing about we, 148 00:08:23,440 --> 00:08:26,559 Speaker 1: we people, we have defined our environments to a large extent, 149 00:08:26,680 --> 00:08:30,440 Speaker 1: especially in developed nations, where the stuff that's around us 150 00:08:30,480 --> 00:08:35,479 Speaker 1: we have shaped so that it works within our capabilities, 151 00:08:36,040 --> 00:08:39,079 Speaker 1: right with our with our human environment. Thus far, if 152 00:08:39,120 --> 00:08:42,199 Speaker 1: you look at technology though, on the whole, we've pretty 153 00:08:42,280 --> 00:08:45,600 Speaker 1: much been forced to adapt to it. So for example, 154 00:08:45,640 --> 00:08:49,280 Speaker 1: like a keyboard, we don't normally, naturally you know, um 155 00:08:49,600 --> 00:08:53,360 Speaker 1: express ideas through our fingers on a little a little board, right, 156 00:08:53,600 --> 00:08:55,559 Speaker 1: we don't normally do that, So we had to adapt 157 00:08:55,559 --> 00:08:57,640 Speaker 1: to the technology and learn to type and get good 158 00:08:57,679 --> 00:09:02,199 Speaker 1: at it. With humanoid robots, it's basically going the exact opposite. 159 00:09:02,240 --> 00:09:05,640 Speaker 1: It's saying we already have an environment, We already are um, 160 00:09:05,679 --> 00:09:07,480 Speaker 1: you know, good at all this other stuff. If we're 161 00:09:07,520 --> 00:09:10,080 Speaker 1: gonna make humanoid robots, one of the great benefits is 162 00:09:10,480 --> 00:09:13,920 Speaker 1: they can adapt to us. Right, Yeah, we don't have 163 00:09:14,000 --> 00:09:17,640 Speaker 1: to uh create a unitask or robot that's really good 164 00:09:17,640 --> 00:09:20,480 Speaker 1: at one thing. Um that may or may not be 165 00:09:20,559 --> 00:09:23,640 Speaker 1: something that humans can do easily. We can make a 166 00:09:23,720 --> 00:09:27,640 Speaker 1: robot that's good lots of things. Uh. I also think 167 00:09:28,080 --> 00:09:30,800 Speaker 1: usually when I think of humanoid robots, when I think 168 00:09:30,800 --> 00:09:33,640 Speaker 1: of robots in general, I normally think that they are 169 00:09:33,679 --> 00:09:37,040 Speaker 1: at least semi autonomous. That's that's one of the things 170 00:09:37,160 --> 00:09:39,320 Speaker 1: I usually think of. It doesn't necessarily have to be. 171 00:09:39,400 --> 00:09:43,560 Speaker 1: You could have a tel operated robot, but I almost 172 00:09:43,600 --> 00:09:47,120 Speaker 1: think of that closer to the realm of like a 173 00:09:47,160 --> 00:09:51,000 Speaker 1: remote controlled car or a puppet even um So I 174 00:09:51,080 --> 00:09:54,439 Speaker 1: often one of the definitions I use is that it's 175 00:09:54,480 --> 00:10:00,679 Speaker 1: an autonomous or semi autonomous machine in human form, mechanical 176 00:10:01,000 --> 00:10:05,480 Speaker 1: and electronic, and it can thus do the sort of 177 00:10:05,480 --> 00:10:08,679 Speaker 1: things humans do, but do it in a totally synthetic way. 178 00:10:08,920 --> 00:10:11,840 Speaker 1: And you have to be careful when you say autonomous 179 00:10:11,880 --> 00:10:14,400 Speaker 1: or semi autonomous, because the state of the art right 180 00:10:14,400 --> 00:10:18,400 Speaker 1: now appears to be that robots display autonomy because they 181 00:10:18,440 --> 00:10:20,839 Speaker 1: just kind of wander off in places they're not supposed to. 182 00:10:21,520 --> 00:10:24,160 Speaker 1: But it's not because they want to. It's because their 183 00:10:24,280 --> 00:10:27,880 Speaker 1: their program just ran a foul of program. Right. There's 184 00:10:27,880 --> 00:10:31,000 Speaker 1: no determination there on the part of the robot. It's 185 00:10:31,040 --> 00:10:35,680 Speaker 1: not exploring its environment on its own accord. It's someone 186 00:10:35,720 --> 00:10:38,240 Speaker 1: made a mistake in the code somewhere and where the 187 00:10:38,320 --> 00:10:40,600 Speaker 1: robot was supposed to take a left hand turn at 188 00:10:40,600 --> 00:10:45,320 Speaker 1: this one you know, predetermined spot, and instead continued forward 189 00:10:45,400 --> 00:10:48,439 Speaker 1: or something exactly. Um, So I wanted to talk a 190 00:10:48,480 --> 00:10:51,480 Speaker 1: little bit about the history of humanoid robots and if 191 00:10:51,480 --> 00:10:55,280 Speaker 1: you wanna look way way way back, I mean, we're 192 00:10:55,280 --> 00:10:58,040 Speaker 1: talking about the first people to really kind of attempt 193 00:10:58,120 --> 00:11:03,160 Speaker 1: to build a humanoid machine that could mimic are the 194 00:11:03,200 --> 00:11:05,600 Speaker 1: movements at least of a person. You gotta go all 195 00:11:05,640 --> 00:11:08,920 Speaker 1: the way back to Greece between the years ten and 196 00:11:09,160 --> 00:11:14,240 Speaker 1: seventy Common era. That's when Hero of Alexandria started to 197 00:11:14,520 --> 00:11:17,160 Speaker 1: create various machines. He's also the person who made the 198 00:11:17,200 --> 00:11:23,040 Speaker 1: first working steam engine style tool, which is pretty impressive. Yeah. 199 00:11:23,120 --> 00:11:25,120 Speaker 1: He he had come up with a lot of very 200 00:11:25,120 --> 00:11:29,680 Speaker 1: clever designs. Whether they were built or not depends upon uh, 201 00:11:29,760 --> 00:11:33,240 Speaker 1: certain accounts and and if they're true. But the stuff 202 00:11:33,280 --> 00:11:37,160 Speaker 1: he designed is completely build a bowl. So he didn't 203 00:11:37,160 --> 00:11:40,360 Speaker 1: come up with any ideas where it was so you know, outlandish, 204 00:11:40,400 --> 00:11:42,440 Speaker 1: that was impossible. He wasn't just like drawing in the 205 00:11:42,480 --> 00:11:44,839 Speaker 1: margins of his diary or something. No, Yeah, he came 206 00:11:44,920 --> 00:11:48,120 Speaker 1: up with specific plans that people today have recreated, they 207 00:11:48,120 --> 00:11:51,560 Speaker 1: built their own versions. Yeah. So he created a lot 208 00:11:51,640 --> 00:11:55,480 Speaker 1: of designs for automata, although these are things that were 209 00:11:55,520 --> 00:11:59,480 Speaker 1: controlled by pulleys and ropes and cogged wheels, and uh 210 00:11:59,720 --> 00:12:02,960 Speaker 1: needed some form of outside influence to make them work, 211 00:12:03,040 --> 00:12:07,720 Speaker 1: so they're not all fully self contained like the show 212 00:12:07,720 --> 00:12:11,680 Speaker 1: biz pizza rockefire explosion band. Yeah exactly. Yeah, yeah, some 213 00:12:11,800 --> 00:12:16,320 Speaker 1: one of those audio animatronic figures that that looks very robotic, 214 00:12:16,360 --> 00:12:19,200 Speaker 1: but you realize it's really just one tiny piece of 215 00:12:19,200 --> 00:12:23,440 Speaker 1: a giant system. Uh. In fourteen, we get up to 216 00:12:23,520 --> 00:12:26,360 Speaker 1: Leonardo da Vinci. He designed an automaton in the form 217 00:12:26,440 --> 00:12:31,280 Speaker 1: of a mechanical night which uh again supposedly he built. 218 00:12:31,440 --> 00:12:34,720 Speaker 1: There's no actual record of an existing one from history, 219 00:12:34,920 --> 00:12:39,000 Speaker 1: but they have created ones based on the design since then, 220 00:12:39,520 --> 00:12:41,360 Speaker 1: and it could do things like move its arms and 221 00:12:41,440 --> 00:12:45,000 Speaker 1: raise its visor. Who's doing this? Who's doing this? Crazy 222 00:12:45,080 --> 00:12:50,200 Speaker 1: engineers who are also uh, very excited about history and 223 00:12:50,320 --> 00:12:53,600 Speaker 1: very wealthy too, I would imagine. Yeah, so in this case, 224 00:12:53,640 --> 00:12:59,880 Speaker 1: you're talking about Mark Rossheim, who recreated this particular machine 225 00:13:00,080 --> 00:13:02,520 Speaker 1: and it it's a night. It's a night in German 226 00:13:02,559 --> 00:13:07,640 Speaker 1: medieval armor. And it can sit down, it can stand up, 227 00:13:07,679 --> 00:13:09,600 Speaker 1: it can move its arms, it can raise a visor, 228 00:13:09,720 --> 00:13:15,040 Speaker 1: it can work its jaw. Um, I imagine. So I 229 00:13:15,120 --> 00:13:18,719 Speaker 1: tried to find video of Rossheim's version working, and I 230 00:13:18,760 --> 00:13:22,400 Speaker 1: couldn't find it. He did, however, make another of da 231 00:13:22,480 --> 00:13:27,480 Speaker 1: Vinci's inventions, which was a self driving cart that used Yeah, 232 00:13:27,520 --> 00:13:31,120 Speaker 1: you you wound a spring and it had cam stops 233 00:13:31,160 --> 00:13:33,800 Speaker 1: that would allow it to steer a predetermined path. You 234 00:13:33,800 --> 00:13:37,760 Speaker 1: would actually program the cart by putting cam stops in 235 00:13:37,800 --> 00:13:40,600 Speaker 1: particular locations along the cam and that would tell it 236 00:13:40,679 --> 00:13:42,520 Speaker 1: when to turn left or when to turn right. So 237 00:13:43,200 --> 00:13:47,960 Speaker 1: it couldn't it couldn't navigate through uh an obstacle course 238 00:13:48,080 --> 00:13:50,719 Speaker 1: unless you had already previously seen the obstacle course and 239 00:13:50,760 --> 00:13:53,319 Speaker 1: you could figure out when it needed to turn ahead 240 00:13:53,360 --> 00:13:57,000 Speaker 1: of time. So you're essentially programming the device. Um. There 241 00:13:57,040 --> 00:14:00,280 Speaker 1: are lots of examples in the renaissance of automata and 242 00:14:00,400 --> 00:14:03,280 Speaker 1: semi automata, things that are really more like puppets. You've 243 00:14:03,320 --> 00:14:08,760 Speaker 1: heard about the mechanical turk, the chess playing robot uh 244 00:14:08,840 --> 00:14:10,840 Speaker 1: So it looked like it was a robot that could 245 00:14:10,840 --> 00:14:13,640 Speaker 1: play chess and was really really good at playing chess 246 00:14:13,880 --> 00:14:16,200 Speaker 1: and it turned out eventually to be a hoax. It 247 00:14:16,280 --> 00:14:18,480 Speaker 1: was actually it was actually a puppet, and there was 248 00:14:18,520 --> 00:14:22,680 Speaker 1: an actual chess master hidden in a cabinet beneath the 249 00:14:23,120 --> 00:14:27,320 Speaker 1: mechanical turk who sat kind of Indian style with a 250 00:14:27,440 --> 00:14:30,080 Speaker 1: chessboard in front of him and could move the pieces 251 00:14:30,120 --> 00:14:31,640 Speaker 1: to where it needed to be. But it was all 252 00:14:31,640 --> 00:14:34,000 Speaker 1: being guided by an actual chess master who was hidden 253 00:14:34,080 --> 00:14:40,440 Speaker 1: under When that that was late Renaissance early Enlightenment, pretty impressive, Yeah, 254 00:14:40,520 --> 00:14:43,040 Speaker 1: it was. It was neat that people were thinking about 255 00:14:43,040 --> 00:14:45,760 Speaker 1: these sort of things. Uh. By ninety six we get 256 00:14:45,800 --> 00:14:49,440 Speaker 1: the first humanoid robot to appear on film, uh Metropolis, 257 00:14:49,760 --> 00:14:53,520 Speaker 1: the character of Maria and at nine at the World's Fair, 258 00:14:53,560 --> 00:14:58,080 Speaker 1: Westinghouse Electric Corporation showed off a robot called Electro. Now 259 00:14:58,120 --> 00:15:00,880 Speaker 1: have you ever seen this? So he kind of looks 260 00:15:00,960 --> 00:15:03,680 Speaker 1: like the ten Man from the Wizard of Oz film. 261 00:15:03,840 --> 00:15:07,080 Speaker 1: I have seen him. Yes, he smokes. I have seen 262 00:15:07,120 --> 00:15:09,000 Speaker 1: one of the things he can do. He had a 263 00:15:09,000 --> 00:15:13,120 Speaker 1: little bellows in his head that allowed him to puff smoke. 264 00:15:13,520 --> 00:15:16,560 Speaker 1: He could also kind of speak. He had a seventy 265 00:15:16,560 --> 00:15:22,320 Speaker 1: eight revolution per minute UH record player essentially inside of him. 266 00:15:23,360 --> 00:15:25,400 Speaker 1: I suppose if the if the needles skipped, it would 267 00:15:25,440 --> 00:15:28,640 Speaker 1: at least sound like it. Um. He would repeat himself over. 268 00:15:28,720 --> 00:15:35,479 Speaker 1: He called the audience Twitts. That was Grandpa. Yeah, he's apparently. 269 00:15:35,680 --> 00:15:39,280 Speaker 1: The main reason he was retired from being shown off 270 00:15:39,280 --> 00:15:42,840 Speaker 1: at exhibitions was because it was very dated kind of lingo. 271 00:15:43,520 --> 00:15:46,160 Speaker 1: But he was used at the ninety nine World's Fair, 272 00:15:47,480 --> 00:15:50,240 Speaker 1: which was It's funny because I'll be talking about that 273 00:15:50,280 --> 00:15:53,520 Speaker 1: again in another episode very shortly. The World's Fair would 274 00:15:53,520 --> 00:15:57,000 Speaker 1: have been an amazing thing to visit. Um, I'm more 275 00:15:57,000 --> 00:16:00,800 Speaker 1: of I can understand that. But if you're if you're 276 00:16:00,800 --> 00:16:02,480 Speaker 1: going to get to the point where you're looking at 277 00:16:02,840 --> 00:16:06,520 Speaker 1: full scale anthropomorphic robots, you gotta get up to about nine. 278 00:16:08,000 --> 00:16:12,560 Speaker 1: That's when the Waybot one from the Waseda University came out. 279 00:16:12,880 --> 00:16:16,040 Speaker 1: That was the first full scale anthropomorphic robot developed in 280 00:16:16,080 --> 00:16:19,840 Speaker 1: the world which had limb control, a vision system, so 281 00:16:19,880 --> 00:16:22,760 Speaker 1: I had an optical system that could recognize its environment 282 00:16:22,760 --> 00:16:26,680 Speaker 1: and objects and measure distance, and it also had a 283 00:16:26,680 --> 00:16:30,640 Speaker 1: conversation system. Uh. It was actually a collection of a 284 00:16:30,640 --> 00:16:34,080 Speaker 1: bunch of very complex machinery. Like its hands had been 285 00:16:34,120 --> 00:16:37,880 Speaker 1: previously developed independently of the robots, so had its legs. 286 00:16:38,560 --> 00:16:41,160 Speaker 1: So it's like all these people coming up with these 287 00:16:41,240 --> 00:16:44,400 Speaker 1: various pieces saying, all right, let's connect all this together 288 00:16:44,440 --> 00:16:47,720 Speaker 1: and see what happens. So that was a huge, huge 289 00:16:47,840 --> 00:16:50,240 Speaker 1: leap forward. Yeah. You know, if you'll notice, we went 290 00:16:50,320 --> 00:16:55,480 Speaker 1: basically from um, HOAXI chess playing turks to you know, 291 00:16:55,840 --> 00:16:58,920 Speaker 1: a robot that could converse and interact with its environment, 292 00:16:59,400 --> 00:17:02,600 Speaker 1: and then um, it seems like we we kind of 293 00:17:02,640 --> 00:17:04,400 Speaker 1: went off course for a little bit and now we're 294 00:17:04,400 --> 00:17:06,960 Speaker 1: coming full circle back to that where, like you said, 295 00:17:07,160 --> 00:17:11,000 Speaker 1: a lot of different disciplines are contributing these different pieces 296 00:17:11,000 --> 00:17:13,959 Speaker 1: to what will eventually be all of the best practices 297 00:17:14,040 --> 00:17:17,479 Speaker 1: from each little sub discipline put together in you know, 298 00:17:17,600 --> 00:17:20,520 Speaker 1: the true humanoid robot. Well yeah, I mean, if we're 299 00:17:20,520 --> 00:17:24,080 Speaker 1: talking about a humanoid robot that's capable of interacting with people, 300 00:17:24,720 --> 00:17:27,399 Speaker 1: uh as if they were you know, their own person, 301 00:17:27,520 --> 00:17:29,960 Speaker 1: even though maybe an odd person, not like the kind 302 00:17:29,960 --> 00:17:33,600 Speaker 1: of person you would typically run into. There's it's a 303 00:17:33,680 --> 00:17:38,520 Speaker 1: multidisciplinary approach. I mean, artificial intelligence by itself is multidisciplinary 304 00:17:39,000 --> 00:17:42,440 Speaker 1: because you have sensing, you have so all the perception, 305 00:17:42,800 --> 00:17:46,520 Speaker 1: there's all these different just that's multi disciplinary. Then you've 306 00:17:46,520 --> 00:17:51,800 Speaker 1: got the processing, the cognition, things like planning, navigation. There 307 00:17:51,840 --> 00:17:54,919 Speaker 1: are so many things that come together to make a 308 00:17:54,960 --> 00:17:59,600 Speaker 1: humanoid robot a a possibility. And that's just the the 309 00:17:59,720 --> 00:18:02,879 Speaker 1: men toll side, right. Then you have all the physical side, 310 00:18:02,920 --> 00:18:05,080 Speaker 1: the how do you make it walk? How do you 311 00:18:05,080 --> 00:18:08,280 Speaker 1: make it keep its balance? So lots of stuff to 312 00:18:08,400 --> 00:18:11,920 Speaker 1: consider there. Waybot two came out in nineteen eighty that 313 00:18:12,040 --> 00:18:14,560 Speaker 1: was a specialist robot. It could play a keyboard trying 314 00:18:14,560 --> 00:18:18,640 Speaker 1: to keyboard. He could read sheet music and play music. Uh. 315 00:18:18,680 --> 00:18:21,240 Speaker 1: It was because it was a specialist. It was not 316 00:18:21,320 --> 00:18:24,959 Speaker 1: able to do the general functions that it's predecessor could do. 317 00:18:25,320 --> 00:18:27,760 Speaker 1: And that's why of the issues in robotics today is 318 00:18:27,800 --> 00:18:32,520 Speaker 1: that it's very challenging to build a general purpose robot. 319 00:18:32,760 --> 00:18:35,840 Speaker 1: It's much easier to take a specific task that you 320 00:18:35,880 --> 00:18:37,639 Speaker 1: need to have done and to sign a robot to 321 00:18:37,720 --> 00:18:41,840 Speaker 1: do that, because I mean, we already have those rombas 322 00:18:41,640 --> 00:18:45,720 Speaker 1: and rovers. I mean, you know, there's there's also all 323 00:18:45,760 --> 00:18:50,520 Speaker 1: the robots and manufacturing, all the welding robots things like that. Uh. 324 00:18:51,200 --> 00:18:55,159 Speaker 1: Nine Pacific Northwest National Laboratory built a robot called Manny 325 00:18:56,560 --> 00:18:59,280 Speaker 1: that was the first full scale android body and it 326 00:18:59,359 --> 00:19:02,880 Speaker 1: had forty degrees of freedom, but no AI or autonomy. 327 00:19:02,920 --> 00:19:06,040 Speaker 1: It was completely teleoperated. And um, it took me a 328 00:19:06,040 --> 00:19:08,960 Speaker 1: couple of times to figure out what degrees of freedom meant. Yeah, um, 329 00:19:09,000 --> 00:19:11,320 Speaker 1: I thought it meant like the it could move its 330 00:19:11,440 --> 00:19:16,080 Speaker 1: arm forty two degrees basically. But a degree of freedom 331 00:19:16,200 --> 00:19:18,040 Speaker 1: is say, like it can move its wrist. That's a 332 00:19:18,080 --> 00:19:21,159 Speaker 1: degree of freedom. It can turn its head left and right. 333 00:19:21,200 --> 00:19:23,240 Speaker 1: That's a degree of freedom right right. And if you 334 00:19:23,280 --> 00:19:26,240 Speaker 1: look at the human hand, the human hand has about 335 00:19:26,320 --> 00:19:29,960 Speaker 1: thirty degrees of freedom, meaning that you look at the 336 00:19:30,000 --> 00:19:32,640 Speaker 1: way each finger and your thumb can move. You look 337 00:19:32,640 --> 00:19:34,400 Speaker 1: at the way you can clench a fist, you can 338 00:19:34,440 --> 00:19:38,159 Speaker 1: twist your hand with your wrist. Um, those are all 339 00:19:38,200 --> 00:19:41,320 Speaker 1: different degrees of freedom. And uh. In fact, one of 340 00:19:41,359 --> 00:19:44,200 Speaker 1: the cool things about robots is that as we get 341 00:19:44,240 --> 00:19:47,120 Speaker 1: better and better at designing them, we can create robots 342 00:19:47,119 --> 00:19:49,240 Speaker 1: that have far more degrees of freedom than the human 343 00:19:49,280 --> 00:19:52,920 Speaker 1: body does. So I like the idea of a humanoid 344 00:19:53,080 --> 00:19:56,639 Speaker 1: robot in the future that has sty degree motion with 345 00:19:56,680 --> 00:19:58,959 Speaker 1: its wrist and then just having it changed light bulbs 346 00:19:59,680 --> 00:20:02,080 Speaker 1: is spin and not have to do the little twisty 347 00:20:02,119 --> 00:20:04,560 Speaker 1: turning motion. How many robots does it take to change 348 00:20:04,560 --> 00:20:07,120 Speaker 1: the light bulbs. Just just the one, just that one, 349 00:20:07,440 --> 00:20:10,720 Speaker 1: just one billion dollar room. Yeah. Yeah, I'm not saying 350 00:20:10,720 --> 00:20:14,800 Speaker 1: it's a fishing system. I'm just saying I'm a supremely 351 00:20:14,880 --> 00:20:19,359 Speaker 1: lazy human being with tall ceilings. Uh In nine, Honda 352 00:20:19,400 --> 00:20:22,240 Speaker 1: introduced the P two Robot, which was a self contained 353 00:20:22,320 --> 00:20:25,760 Speaker 1: robotic humanoid. It could walk and climb stairs. The P 354 00:20:25,960 --> 00:20:29,000 Speaker 1: three followed in nine and in two thousand two, Honda 355 00:20:29,119 --> 00:20:33,639 Speaker 1: introduced My good buddy as Emo. As the first article 356 00:20:33,680 --> 00:20:38,320 Speaker 1: I wrote for How Stuff Works as works an episode 357 00:20:38,320 --> 00:20:40,439 Speaker 1: on it. I have not done a full episode on 358 00:20:40,600 --> 00:20:44,160 Speaker 1: as Amo. I even was offered the opportunity to meet 359 00:20:44,240 --> 00:20:46,560 Speaker 1: as Amo when I first wrote the article, but it 360 00:20:46,560 --> 00:20:48,919 Speaker 1: would have meant having to travel to Disneyland to do it, 361 00:20:49,000 --> 00:20:51,120 Speaker 1: and at the time How Stuff Works was not prepared 362 00:20:51,160 --> 00:20:55,359 Speaker 1: to do such a I went to Disneyland by myself, 363 00:20:55,840 --> 00:20:59,080 Speaker 1: uh well with my wife, and we went and saw 364 00:20:59,359 --> 00:21:01,920 Speaker 1: the Asimo production. And at the end of it, I 365 00:21:02,359 --> 00:21:05,200 Speaker 1: talked to one of the disney cast members and I said, yeah, 366 00:21:05,320 --> 00:21:07,320 Speaker 1: I wrote the article about how Asthma works for How 367 00:21:07,320 --> 00:21:09,520 Speaker 1: Stuff Works, and she said, hang on a minute. And 368 00:21:09,520 --> 00:21:11,440 Speaker 1: I got to meet Asthma and it was a man 369 00:21:11,520 --> 00:21:14,160 Speaker 1: in a suit. Right. It was actually it was actually 370 00:21:14,200 --> 00:21:17,040 Speaker 1: a collection of cats that the duct taped together and 371 00:21:17,040 --> 00:21:20,600 Speaker 1: then plastic. No, it was a working robot that's pretty new. 372 00:21:20,640 --> 00:21:23,320 Speaker 1: Blown away, I was very much blown away. It was 373 00:21:23,440 --> 00:21:25,399 Speaker 1: cool seeing it up close. I mean, it looks like 374 00:21:25,400 --> 00:21:28,240 Speaker 1: a little tiny astronaut, right, because he's got like the 375 00:21:28,280 --> 00:21:30,600 Speaker 1: face plate. Especially. I love the people call it he 376 00:21:31,680 --> 00:21:33,800 Speaker 1: people give And I do this all the time too 377 00:21:33,960 --> 00:21:37,080 Speaker 1: with robots. I'll assign a gender even though technically many 378 00:21:37,119 --> 00:21:40,360 Speaker 1: of them are specifically genderless. As amo is is supposed 379 00:21:40,400 --> 00:21:42,879 Speaker 1: to be genderless, but I often refer to asthmosa he 380 00:21:42,960 --> 00:21:44,760 Speaker 1: as well. Well, you know why. It's the shoulders, I 381 00:21:44,760 --> 00:21:47,399 Speaker 1: would guess. Yeah, they go straight across and and and 382 00:21:47,520 --> 00:21:51,600 Speaker 1: far out. That's very masculine no matter what. Yeah, and 383 00:21:51,680 --> 00:21:53,879 Speaker 1: you need that, I would guess you need shoulders in 384 00:21:53,920 --> 00:21:58,480 Speaker 1: a humanoid robot with flexible arms. Well, and also, I'm 385 00:21:58,520 --> 00:22:02,160 Speaker 1: sure every single element Asimo is built with the balance 386 00:22:02,200 --> 00:22:05,840 Speaker 1: in mind, because Asimo is the first robot that can run. Yes, 387 00:22:05,880 --> 00:22:09,040 Speaker 1: I've seen him run. It's gawky. Yeah, it kind of 388 00:22:09,080 --> 00:22:10,840 Speaker 1: looks like someone who really needs to get to the 389 00:22:10,840 --> 00:22:13,680 Speaker 1: bathroom as a little bit of a hoppy kind of run. 390 00:22:14,080 --> 00:22:16,840 Speaker 1: But the the definition of run here is that there 391 00:22:16,880 --> 00:22:20,480 Speaker 1: are moments where both feet are off the ground. So 392 00:22:20,800 --> 00:22:23,359 Speaker 1: walking you always have one foot in contact with the ground, 393 00:22:23,359 --> 00:22:27,160 Speaker 1: and running both feet at some point are out of contact. 394 00:22:27,240 --> 00:22:30,840 Speaker 1: And that's a huge deal for robotics, right. I mean, 395 00:22:31,359 --> 00:22:34,679 Speaker 1: you have a machine that completely separates itself from contact 396 00:22:34,680 --> 00:22:37,680 Speaker 1: on the ground. It has no propulsion to keep it upright, 397 00:22:38,160 --> 00:22:39,960 Speaker 1: you know, it doesn't have like propellers or jets or 398 00:22:40,000 --> 00:22:42,719 Speaker 1: anything like that, so you have to design it so 399 00:22:42,760 --> 00:22:45,760 Speaker 1: it can it can propel itself off the ground and 400 00:22:45,800 --> 00:22:48,520 Speaker 1: then catch itself when it comes back down without falling over. 401 00:22:48,640 --> 00:22:51,800 Speaker 1: And that is a non trivial challenge, No, it's an 402 00:22:51,880 --> 00:22:55,520 Speaker 1: enormous challenge that robot is just UM really kind of 403 00:22:55,640 --> 00:22:58,879 Speaker 1: started to tackle lately. Um. One of the ways that 404 00:22:58,960 --> 00:23:02,159 Speaker 1: they've overcome it is with rounded feet, which are very 405 00:23:02,160 --> 00:23:05,120 Speaker 1: helpful in keeping balanced and allowing it to run. UM. 406 00:23:05,160 --> 00:23:08,840 Speaker 1: But there's drawbacks to it as well, Like the robot 407 00:23:08,880 --> 00:23:12,720 Speaker 1: can't start itself, it also can't stop, so it can't 408 00:23:12,760 --> 00:23:15,880 Speaker 1: stop moving, which is not something you want. Like, there's 409 00:23:15,920 --> 00:23:19,040 Speaker 1: still some challenges there ahead of the robotists who are 410 00:23:19,119 --> 00:23:21,399 Speaker 1: learning to teach a robot to walk, and even the 411 00:23:21,440 --> 00:23:25,520 Speaker 1: ones that have taught robots to walk, um, they typically 412 00:23:25,560 --> 00:23:28,680 Speaker 1: can just walk over flat surfaces with no obstacles. When 413 00:23:28,680 --> 00:23:31,280 Speaker 1: they encounter stairs, there in trouble. But then you have 414 00:23:31,400 --> 00:23:34,600 Speaker 1: robots that know how to go upstairs, but they can't 415 00:23:34,600 --> 00:23:38,159 Speaker 1: walk on a flat surface. Eventually, all this information, all 416 00:23:38,200 --> 00:23:40,359 Speaker 1: this knowledge will be brought together and you'll have a 417 00:23:40,440 --> 00:23:43,320 Speaker 1: robot that can walk, no problem. Right. In fact, this 418 00:23:43,400 --> 00:23:48,639 Speaker 1: kind of transitions nicely into those challenges that face designers 419 00:23:48,640 --> 00:23:52,840 Speaker 1: of humanoid robots and and locomotion is the probably one 420 00:23:52,840 --> 00:23:55,680 Speaker 1: of the top ones, at least from the physical engineering side. 421 00:23:56,080 --> 00:23:58,359 Speaker 1: For example, you know, as Amo can can go up 422 00:23:58,359 --> 00:24:02,040 Speaker 1: and downstairs, but that is a little deceptive because as 423 00:24:02,080 --> 00:24:05,520 Speaker 1: Amo has to be programmed to go up or down 424 00:24:05,520 --> 00:24:08,520 Speaker 1: the staircase and know exactly how many stairs are involved. 425 00:24:09,040 --> 00:24:11,960 Speaker 1: It's not so much it's not a case of Asimo 426 00:24:12,080 --> 00:24:16,120 Speaker 1: detecting a staircase and then uh and then navigating through 427 00:24:16,119 --> 00:24:19,520 Speaker 1: oh up or down. It it's the fact that all 428 00:24:19,600 --> 00:24:25,240 Speaker 1: right now we're initiating your stair climbing programs. Yeah, exactly. 429 00:24:25,320 --> 00:24:29,880 Speaker 1: It's kind of like smoke and mirrors robotics. Basically, it's 430 00:24:29,920 --> 00:24:32,879 Speaker 1: at but that's you know, those are the little no 431 00:24:32,880 --> 00:24:34,760 Speaker 1: no pun intended, Those are the little steps you have 432 00:24:34,800 --> 00:24:36,760 Speaker 1: to take in order to get to the destination. What 433 00:24:36,800 --> 00:24:38,560 Speaker 1: do you mean, no pun intended. I don't buy that 434 00:24:38,720 --> 00:24:41,480 Speaker 1: at all. I started saying it without thinking about it, 435 00:24:41,520 --> 00:24:44,200 Speaker 1: and then I mean, but then I did follow through 436 00:24:44,240 --> 00:24:45,880 Speaker 1: with it, so I guess there was some intention there 437 00:24:45,920 --> 00:24:49,040 Speaker 1: at the end. But uh yeah. They're also not very 438 00:24:49,080 --> 00:24:54,680 Speaker 1: good at going across any kind of uneven terrain, right, So, 439 00:24:55,800 --> 00:24:59,040 Speaker 1: humanoid robots in particular find it very difficult to maintain 440 00:24:59,080 --> 00:25:02,480 Speaker 1: balance over anything that's not either a flat surface or, 441 00:25:02,560 --> 00:25:04,720 Speaker 1: in the case of robots, that can go up or 442 00:25:04,720 --> 00:25:07,520 Speaker 1: downstairs and stairs. So if you're talking about like a 443 00:25:07,920 --> 00:25:11,280 Speaker 1: sidewalk that is not completely even, that would be enough 444 00:25:11,320 --> 00:25:13,639 Speaker 1: to give a robot trouble because it's going to try 445 00:25:13,680 --> 00:25:16,520 Speaker 1: and put its foot down to where it would believe 446 00:25:16,800 --> 00:25:18,919 Speaker 1: the ground to be, and if the ground is not 447 00:25:19,040 --> 00:25:23,600 Speaker 1: exactly level, then that's yeah, because they can't really catch 448 00:25:23,680 --> 00:25:27,040 Speaker 1: their balance very well. There are robots that can, but 449 00:25:27,200 --> 00:25:31,159 Speaker 1: they are four legged. Yeah, you've seen you've seen the 450 00:25:31,160 --> 00:25:36,200 Speaker 1: Big Dog video. No, I saw the Army. It's very similar. 451 00:25:36,440 --> 00:25:39,439 Speaker 1: Big Dog is essentially a robo mule type development. It 452 00:25:39,520 --> 00:25:43,439 Speaker 1: is a four legged robot that is able to maintain 453 00:25:43,520 --> 00:25:47,440 Speaker 1: its balance even when pushed. And the famous video shows 454 00:25:47,840 --> 00:25:52,800 Speaker 1: the robot dog, the big dog kind of jogging, and 455 00:25:52,840 --> 00:25:56,200 Speaker 1: then a guy just casually lifts his leg up and 456 00:25:56,520 --> 00:26:00,040 Speaker 1: kicks the robot dog like he puts essentially puts a 457 00:26:00,040 --> 00:26:01,760 Speaker 1: bomb of his foot against the side of it and 458 00:26:01,760 --> 00:26:06,040 Speaker 1: pushes really hard, and you see the big dog stumble. 459 00:26:06,359 --> 00:26:09,520 Speaker 1: It actually stumbles and then catches itself and then rights 460 00:26:09,560 --> 00:26:14,240 Speaker 1: itself and continues on. And almost everyone has an emotional 461 00:26:14,280 --> 00:26:17,480 Speaker 1: reaction to this, like, how dare that evil man kick 462 00:26:17,600 --> 00:26:21,960 Speaker 1: that poor, defenseless robot. The robot can't feel anything, but 463 00:26:22,119 --> 00:26:27,480 Speaker 1: that robot is um gasoline powered, so oh yeah, that's right, 464 00:26:27,560 --> 00:26:30,920 Speaker 1: that's one of the big keeping it inside. Yeah, you 465 00:26:30,960 --> 00:26:33,800 Speaker 1: wouldn't want to have one of these indoors. No, you 466 00:26:33,800 --> 00:26:37,840 Speaker 1: don't bring indoor no. And uh and the the pistons 467 00:26:37,960 --> 00:26:41,399 Speaker 1: that allow it to do this are quite loud. You know. 468 00:26:41,440 --> 00:26:44,480 Speaker 1: It's not not a subtle system at all. So a 469 00:26:44,520 --> 00:26:47,600 Speaker 1: lot of work has to go into creating better systems 470 00:26:47,720 --> 00:26:50,679 Speaker 1: for robots to maintain their balance in order for the 471 00:26:50,720 --> 00:26:53,800 Speaker 1: locomotion problem to really be solved. And again, I mean, 472 00:26:53,840 --> 00:26:56,399 Speaker 1: like anybody who's seen short circuit knows that you can 473 00:26:56,400 --> 00:26:59,159 Speaker 1: build a robot like Johnny five with arms in the 474 00:26:59,280 --> 00:27:02,400 Speaker 1: head and a tore so and then like traction um 475 00:27:03,440 --> 00:27:07,439 Speaker 1: shreds uh, and it can go anywhere over terrain, it 476 00:27:07,480 --> 00:27:10,359 Speaker 1: can go up steps. Probably. The thing is is, again 477 00:27:10,520 --> 00:27:13,639 Speaker 1: you have to remember when it comes to humanoid robots, 478 00:27:13,720 --> 00:27:15,919 Speaker 1: you're trying to make the robot that can adapt to 479 00:27:15,960 --> 00:27:19,160 Speaker 1: the human world. So if you had somebody like Johnny 480 00:27:19,200 --> 00:27:21,960 Speaker 1: five as your house butler or something, you you couldn't 481 00:27:23,280 --> 00:27:25,520 Speaker 1: You couldn't have an island in your kitchen, and who 482 00:27:25,520 --> 00:27:28,359 Speaker 1: doesn't love an island in their kitchen. Johnny five couldn't 483 00:27:28,359 --> 00:27:30,560 Speaker 1: maneuver around it because he's too wide. Yeah, you wouldn't 484 00:27:30,600 --> 00:27:32,760 Speaker 1: have You wouldn't be able to have any any space 485 00:27:32,800 --> 00:27:35,960 Speaker 1: that would be narrower than the robot's body. Exactly. That's 486 00:27:35,960 --> 00:27:39,320 Speaker 1: not what you want with humanoid robots. It wouldn't work 487 00:27:39,359 --> 00:27:42,240 Speaker 1: well in my house. I've got a I've got a 488 00:27:42,240 --> 00:27:47,680 Speaker 1: a flat style house where there's three floors. Yeah, it's 489 00:27:47,760 --> 00:27:51,080 Speaker 1: like flat like European flat. Uh, not flat as in 490 00:27:51,760 --> 00:27:54,280 Speaker 1: there's only one level. They're actually three of them, four 491 00:27:54,320 --> 00:27:56,960 Speaker 1: if you count the rooftop Denck, So that counts. It 492 00:27:57,040 --> 00:27:59,280 Speaker 1: makes it. You know, any robot that would not be 493 00:27:59,320 --> 00:28:02,520 Speaker 1: able to navig it stairs easily would definitely have an issue, 494 00:28:02,560 --> 00:28:04,439 Speaker 1: which is the main reason why I don't have a roomba, 495 00:28:04,480 --> 00:28:05,920 Speaker 1: because I don't want to hear the sound of a 496 00:28:06,000 --> 00:28:10,320 Speaker 1: room bag going falling down a flight of stairs. Um. 497 00:28:10,359 --> 00:28:13,520 Speaker 1: But at any rate, Uh, that's a great point. Moving 498 00:28:13,520 --> 00:28:17,240 Speaker 1: on from locomotion, there's also dexterous manipulation. Yeah, I think 499 00:28:17,320 --> 00:28:20,840 Speaker 1: we should. I think that point bears repeating. What we 500 00:28:20,960 --> 00:28:23,240 Speaker 1: just talked about was locomotion. Yeah, and this is you 501 00:28:23,320 --> 00:28:26,560 Speaker 1: and I a couple of non robot experts talking about 502 00:28:26,600 --> 00:28:30,600 Speaker 1: the problem with locomotion. That's just one of myriad challenges 503 00:28:30,680 --> 00:28:36,080 Speaker 1: facing humanoid robotics designers. Yeah, yeah, exactly. It's It's one 504 00:28:36,119 --> 00:28:40,160 Speaker 1: that's easy to point to because it's something that we all, 505 00:28:40,440 --> 00:28:45,720 Speaker 1: you know, end up at least observing or participating in 506 00:28:45,760 --> 00:28:48,120 Speaker 1: all the time. Can we take it for granted? But 507 00:28:48,160 --> 00:28:49,680 Speaker 1: then when you think, okay, well, how do I make 508 00:28:49,680 --> 00:28:51,880 Speaker 1: a machine that does that? You start to realize this 509 00:28:51,960 --> 00:28:54,240 Speaker 1: is you know, even if I have a leg that 510 00:28:54,320 --> 00:28:58,080 Speaker 1: has lots of different degrees of freedom and points of articulation. 511 00:28:58,840 --> 00:29:00,560 Speaker 1: I still have to design the upper part of the 512 00:29:00,640 --> 00:29:03,480 Speaker 1: robots so that it does not unbalanced the lower part, 513 00:29:03,680 --> 00:29:05,960 Speaker 1: and if it does unbalance, that it's able to catch itself. 514 00:29:06,800 --> 00:29:09,800 Speaker 1: You know, some people just describe walking as falling and 515 00:29:09,840 --> 00:29:14,440 Speaker 1: catching yourself over and over again. Yeah, yeah, they're walking 516 00:29:14,600 --> 00:29:18,800 Speaker 1: right now. No, I I described walking as something that 517 00:29:18,840 --> 00:29:22,280 Speaker 1: other people do. I like to keep my walking to 518 00:29:22,320 --> 00:29:24,480 Speaker 1: a minimum. I thought you walked alot, Actually I do. 519 00:29:24,800 --> 00:29:28,480 Speaker 1: I just joke about being lazy. I think moving forward, 520 00:29:28,880 --> 00:29:32,560 Speaker 1: falling down and catching your balance every time it's lurching. Yeah, 521 00:29:32,600 --> 00:29:37,000 Speaker 1: that's well. As an Adam's family fan, I'm okay with that. Yeah, 522 00:29:37,040 --> 00:29:40,720 Speaker 1: but uh, Dexter's manipulation would be the ability to pick 523 00:29:40,840 --> 00:29:43,960 Speaker 1: up and manipulate objects. Now, we're really good at that, 524 00:29:44,040 --> 00:29:46,320 Speaker 1: we humans, You know. We can we can feel an 525 00:29:46,320 --> 00:29:50,200 Speaker 1: object and decide at that point how to handle it, 526 00:29:50,400 --> 00:29:52,960 Speaker 1: even if we've never encountered that kind of object before. 527 00:29:53,320 --> 00:29:55,680 Speaker 1: So if I encounter something I've never seen before, and 528 00:29:55,760 --> 00:29:58,400 Speaker 1: i've I've ascertained it's safe for me to touch it, 529 00:29:58,960 --> 00:30:00,440 Speaker 1: I can touch it. I can feel like, I can 530 00:30:00,480 --> 00:30:01,920 Speaker 1: get a feel for how heavy it is, I can 531 00:30:02,040 --> 00:30:04,560 Speaker 1: get a feel for how delicate it might be, and 532 00:30:04,560 --> 00:30:07,600 Speaker 1: then I can adjust on the fly so that I 533 00:30:07,640 --> 00:30:10,320 Speaker 1: can handle it appropriately. Well, I'm not gonna hurt myself. 534 00:30:10,320 --> 00:30:13,000 Speaker 1: I'm not gonna hurt the object. Robots are not so 535 00:30:13,040 --> 00:30:17,120 Speaker 1: good at that, Yeah, exactly, even if they don't mean 536 00:30:17,120 --> 00:30:19,760 Speaker 1: to right, Yeah, if the robots, If the robots grip 537 00:30:19,840 --> 00:30:21,960 Speaker 1: is too strong, it can break the object. If it's 538 00:30:21,960 --> 00:30:26,040 Speaker 1: too weak, the object slips from its grip and it falls. Uh. 539 00:30:26,120 --> 00:30:29,240 Speaker 1: And it may not be able to distinguish between different types. 540 00:30:29,320 --> 00:30:33,680 Speaker 1: So getting those tactile sensors where a robot can tell 541 00:30:34,080 --> 00:30:37,280 Speaker 1: how tightly it's gripping something and how much pressure a 542 00:30:37,280 --> 00:30:40,600 Speaker 1: particular object can take before you've reached the failure point 543 00:30:41,240 --> 00:30:42,840 Speaker 1: is a big deal. Now, this is also a big 544 00:30:42,880 --> 00:30:46,320 Speaker 1: deal for just making robots safe for humans to be around. 545 00:30:46,480 --> 00:30:48,400 Speaker 1: It is a big deal. You know that the first 546 00:30:48,840 --> 00:30:53,280 Speaker 1: fatality by robot occurred um at the business end of 547 00:30:53,280 --> 00:30:57,560 Speaker 1: a robotic arm in a flat rock, Michigan in nine nine. 548 00:30:57,560 --> 00:30:59,640 Speaker 1: A man named Robert Williams, who's working on a Ford 549 00:31:00,040 --> 00:31:03,600 Speaker 1: line YEA, his robot arm was moving a little slow 550 00:31:03,680 --> 00:31:06,760 Speaker 1: for his taste in getting supplies down, so he climbed 551 00:31:06,840 --> 00:31:09,560 Speaker 1: up to where the supplies were the robot arms suddenly 552 00:31:09,600 --> 00:31:11,400 Speaker 1: sped up and hit him in the head and killed 553 00:31:11,440 --> 00:31:15,520 Speaker 1: him instantly. Wow. Yeah, I've I've had a chance to 554 00:31:15,720 --> 00:31:18,640 Speaker 1: see some of these industrial robots. Uh. And I would 555 00:31:18,640 --> 00:31:22,200 Speaker 1: say up close, but you can't because because of instances 556 00:31:22,280 --> 00:31:26,760 Speaker 1: like that, industrial robots usually have lots of of safety 557 00:31:26,800 --> 00:31:30,960 Speaker 1: barriers around them because it's not safe to be near 558 00:31:31,280 --> 00:31:35,920 Speaker 1: those robots when they're in operation. They they can't react exactly. 559 00:31:36,000 --> 00:31:37,800 Speaker 1: So you leave it up to the humans to stay 560 00:31:37,840 --> 00:31:39,960 Speaker 1: away from the robots because the road we haven't gotten 561 00:31:39,960 --> 00:31:42,280 Speaker 1: to the point where the robots no, did not crush 562 00:31:42,320 --> 00:31:43,960 Speaker 1: you or hit you in the head. Right, Yeah, I 563 00:31:44,000 --> 00:31:45,920 Speaker 1: got the robots fall. I'm looking forward to that day 564 00:31:45,920 --> 00:31:48,800 Speaker 1: when they figure out not to crush me. Yes, it's 565 00:31:48,840 --> 00:31:52,040 Speaker 1: been pretty lousy days so far. Uh. Yeah. When I 566 00:31:52,120 --> 00:31:56,120 Speaker 1: when I toured the Georgia Tech Robotics Lab, they talked 567 00:31:56,120 --> 00:31:59,160 Speaker 1: specifically about this. This is a real challenge having robots 568 00:31:59,200 --> 00:32:01,800 Speaker 1: recognize and react in a way that's going to be 569 00:32:02,200 --> 00:32:06,520 Speaker 1: safe around humans. And uh, but dexterous manipulation is only 570 00:32:06,600 --> 00:32:08,920 Speaker 1: that's only a part of dextrous manipulation. Obviously, the rest 571 00:32:08,960 --> 00:32:12,280 Speaker 1: of it is again that object recognition and handling so 572 00:32:12,320 --> 00:32:14,120 Speaker 1: that you're not destroying whatever it is you're trying to 573 00:32:14,160 --> 00:32:19,280 Speaker 1: pick up. Um. Another big challenge in designing robots in general, 574 00:32:19,600 --> 00:32:22,760 Speaker 1: not just humanoid robots, is just the the perception, the 575 00:32:22,800 --> 00:32:27,520 Speaker 1: sensory perception of the robot. Yeah, so you know, whether 576 00:32:27,680 --> 00:32:31,720 Speaker 1: it's optical systems like actual cameras in the place of eyes, 577 00:32:31,880 --> 00:32:34,760 Speaker 1: or infrared so that you can see even in low 578 00:32:34,840 --> 00:32:38,800 Speaker 1: light situations, radar, light ar. I mean, there's tons of 579 00:32:38,800 --> 00:32:43,760 Speaker 1: different ways of sensing. Yep, there's uh, there's you know 580 00:32:43,800 --> 00:32:45,960 Speaker 1: sensing obviously, it's not just site. Then you have to 581 00:32:46,040 --> 00:32:49,240 Speaker 1: have the sound. That's a really tricky one actually, because 582 00:32:49,680 --> 00:32:53,040 Speaker 1: for us humans, we we can kind of zero in 583 00:32:53,160 --> 00:32:55,800 Speaker 1: on what's important, right, So if we're if you and 584 00:32:55,840 --> 00:32:58,480 Speaker 1: I were at a party, which you know, someone made 585 00:32:58,520 --> 00:33:01,560 Speaker 1: a mistake and invited me, we could have a conversation 586 00:33:01,880 --> 00:33:05,080 Speaker 1: and be able to carry that conversation on even within 587 00:33:05,120 --> 00:33:08,160 Speaker 1: the context of a big, bustling party because we can 588 00:33:08,200 --> 00:33:10,360 Speaker 1: focus on what the other person is saying. It's called 589 00:33:10,560 --> 00:33:14,680 Speaker 1: latent inhibition. Yeah, so when you don't have that, that schizophrenia, Yeah, 590 00:33:14,720 --> 00:33:17,920 Speaker 1: you you can't separate the the signal from the noise 591 00:33:18,040 --> 00:33:21,640 Speaker 1: and everything either. Becomes noise or everything becomes signal. Um. 592 00:33:21,720 --> 00:33:25,840 Speaker 1: So for a robot that might, for example, require verbal commands, 593 00:33:26,480 --> 00:33:28,920 Speaker 1: that's really tricky. What if you have the television on 594 00:33:29,440 --> 00:33:34,280 Speaker 1: and someone's saying something on TV and uh, you are 595 00:33:34,320 --> 00:33:36,440 Speaker 1: trying to get your robot to do something, and it's 596 00:33:36,440 --> 00:33:38,400 Speaker 1: not quite sure what to do because it's hearing these 597 00:33:38,400 --> 00:33:42,200 Speaker 1: different commands and isn't sure who to obey you the 598 00:33:42,320 --> 00:33:45,680 Speaker 1: person pitching the bacon bowl right right exactly. Let's say 599 00:33:45,680 --> 00:33:47,240 Speaker 1: that you are, you know, trying to get some help 600 00:33:47,280 --> 00:33:50,240 Speaker 1: in the kitchen, but it just keeps hearing uh C 601 00:33:50,480 --> 00:33:52,720 Speaker 1: s I Miami and say kill Billy. And then next 602 00:33:52,720 --> 00:33:54,920 Speaker 1: thing you know, you're like, you're just desperately trying to 603 00:33:54,960 --> 00:33:59,240 Speaker 1: kill the robot. Please don't kill Billy. Um. Yeah, well 604 00:33:59,280 --> 00:34:02,160 Speaker 1: that's a silly example. It's a real problem. Uh. And 605 00:34:02,200 --> 00:34:06,000 Speaker 1: then there's the tactile the responses, the tactile sensors, like 606 00:34:06,040 --> 00:34:08,800 Speaker 1: the making sure you don't crush something that's delicate that 607 00:34:09,200 --> 00:34:13,480 Speaker 1: falls into perception. Smell can also fall into perception. You 608 00:34:13,800 --> 00:34:16,720 Speaker 1: might want to have humanoid robots that work in areas 609 00:34:16,719 --> 00:34:20,880 Speaker 1: where the humanoid robot can alert humans to the presence 610 00:34:20,920 --> 00:34:23,440 Speaker 1: of things that might be toxic. You know, this isn't 611 00:34:23,480 --> 00:34:27,040 Speaker 1: necessarily just the robot Butler we're talking about. This could 612 00:34:27,040 --> 00:34:31,279 Speaker 1: be robots that work in areas that might be dangerous 613 00:34:31,320 --> 00:34:34,160 Speaker 1: for humans, and that would be an important element too. 614 00:34:34,640 --> 00:34:37,000 Speaker 1: It's not a robot, but NASA already has a sensor 615 00:34:37,239 --> 00:34:40,960 Speaker 1: that senses things like ammonia or smoke. It can actually 616 00:34:41,200 --> 00:34:46,400 Speaker 1: sense smoke artificially, smell smoke before the fire has actually 617 00:34:46,520 --> 00:34:51,759 Speaker 1: started ignited. Interesting because you know it's such a dangerous proposition, right, yes, 618 00:34:51,840 --> 00:34:55,720 Speaker 1: clearly for for anything NASA related. But they can also 619 00:34:55,800 --> 00:34:58,080 Speaker 1: sense ammonia because you know a lot of the refrigeration 620 00:34:58,160 --> 00:35:01,680 Speaker 1: systems run on ammonia and you can't have a pneumonia 621 00:35:01,760 --> 00:35:05,279 Speaker 1: leak on the space basis, right right, And I mean 622 00:35:05,280 --> 00:35:07,200 Speaker 1: the same thing is true for I mean I've heard 623 00:35:07,200 --> 00:35:11,480 Speaker 1: of of robots that are used in in mining operations, 624 00:35:12,280 --> 00:35:14,239 Speaker 1: which you know, if you come upon a pocket of 625 00:35:14,280 --> 00:35:16,759 Speaker 1: natural gas that can be a real danger that sort 626 00:35:16,760 --> 00:35:19,799 Speaker 1: of stuff. Then you've got the the back end of 627 00:35:19,840 --> 00:35:24,560 Speaker 1: the sensory perception. That's where you have the actual interpretation 628 00:35:24,680 --> 00:35:27,279 Speaker 1: of the data. Where that's the big one. That's huge, 629 00:35:27,320 --> 00:35:29,120 Speaker 1: because not only do you need to have a robot 630 00:35:29,200 --> 00:35:32,279 Speaker 1: that can have that has binocular vision, so it has 631 00:35:32,320 --> 00:35:35,480 Speaker 1: a depth of field. Right. Um, it also has to 632 00:35:35,560 --> 00:35:39,719 Speaker 1: know what it's doing, what what the information means, and 633 00:35:39,760 --> 00:35:44,160 Speaker 1: how to apply it to adapted changes, right right. So, 634 00:35:44,160 --> 00:35:47,840 Speaker 1: so if I were to show you, Josh a series 635 00:35:47,880 --> 00:35:50,960 Speaker 1: of pictures of various types of dogs, you would very 636 00:35:51,000 --> 00:35:54,719 Speaker 1: quickly pick up on the the things that mean mean 637 00:35:54,840 --> 00:35:58,360 Speaker 1: dog like. You would understand the concept of dog pretty quickly. 638 00:35:59,239 --> 00:36:03,239 Speaker 1: Robots and various other computers machines they have a lot 639 00:36:03,320 --> 00:36:06,360 Speaker 1: harder problem with this. If whatever they're looking at doesn't 640 00:36:06,360 --> 00:36:10,960 Speaker 1: exactly match the parameters of the example, it's very difficult 641 00:36:11,000 --> 00:36:14,040 Speaker 1: for a machine to extrapolate and say, oh, this other 642 00:36:14,080 --> 00:36:16,759 Speaker 1: thing I'm looking at relates to this thing I know, 643 00:36:17,000 --> 00:36:21,640 Speaker 1: even though the two examples don't aren't identical. So the 644 00:36:21,680 --> 00:36:24,000 Speaker 1: same thing could be true for any object. Let's let's 645 00:36:24,000 --> 00:36:26,880 Speaker 1: just use a coffee mug. And let's say that you 646 00:36:27,040 --> 00:36:31,000 Speaker 1: use a a plain white coffee mug of average size 647 00:36:31,560 --> 00:36:35,160 Speaker 1: as h the example for the robot, and then the 648 00:36:35,239 --> 00:36:39,520 Speaker 1: robot encounters a larger blue coffee mug and the handles 649 00:36:39,560 --> 00:36:42,640 Speaker 1: turned the other way. The robot might be completely befuddled 650 00:36:42,719 --> 00:36:46,120 Speaker 1: by this. So this is a real problem in artificial 651 00:36:46,160 --> 00:36:51,040 Speaker 1: intelligence is object identification, so that a robot knows what 652 00:36:51,080 --> 00:36:54,520 Speaker 1: it's looking at and also understands the context that that 653 00:36:54,600 --> 00:36:59,160 Speaker 1: object fills within the environment. So it's not just that, oh, 654 00:36:59,239 --> 00:37:02,200 Speaker 1: that's a mug, it's oh, that's a mug. A mug 655 00:37:02,239 --> 00:37:04,560 Speaker 1: is a container. I can put things into that mug. 656 00:37:04,719 --> 00:37:06,200 Speaker 1: Here are the things that can go in the mug. 657 00:37:06,239 --> 00:37:08,080 Speaker 1: You are the things that absolutely should not not go 658 00:37:08,160 --> 00:37:10,480 Speaker 1: in the mug, like Billy. Those are the kind of 659 00:37:10,520 --> 00:37:12,799 Speaker 1: things that yeah, Billy, well, you know we're gonna need 660 00:37:12,840 --> 00:37:16,960 Speaker 1: another Billy. Um, we'll make a robot, which in which 661 00:37:17,000 --> 00:37:19,120 Speaker 1: case you can just turn those suckers out right mass 662 00:37:19,120 --> 00:37:23,280 Speaker 1: production of Billy. But yeah, artificial intelligence an enormous problem. 663 00:37:23,280 --> 00:37:25,359 Speaker 1: And that, of course is not just with robotics. That's 664 00:37:25,520 --> 00:37:28,959 Speaker 1: that's a field unto itself, and robotics is just one 665 00:37:29,000 --> 00:37:33,880 Speaker 1: branch that relies upon artificial intelligence. And it's from what 666 00:37:34,000 --> 00:37:36,560 Speaker 1: I came across, it looked like just out of the gate, 667 00:37:36,680 --> 00:37:40,000 Speaker 1: I guess that was said a university they tried to 668 00:37:40,040 --> 00:37:43,240 Speaker 1: build a robot that was just like high functioning, yeah, 669 00:37:43,320 --> 00:37:47,520 Speaker 1: and they realized, like, we have no idea what we're doing. Yeah, 670 00:37:47,560 --> 00:37:51,120 Speaker 1: that that Waybot one was able to converse at the 671 00:37:51,239 --> 00:37:54,799 Speaker 1: level or was able to have a a a cognitive 672 00:37:54,800 --> 00:37:58,840 Speaker 1: function equivalent to a one and a half year old person, 673 00:37:58,960 --> 00:38:02,080 Speaker 1: which I have to when you're talking right out of 674 00:38:02,080 --> 00:38:05,799 Speaker 1: the gate. Very impressive, Very impressive because we're not that 675 00:38:05,880 --> 00:38:09,760 Speaker 1: much further along now. But what they found from making 676 00:38:09,760 --> 00:38:13,680 Speaker 1: way about one was, Okay, this is way more difficult 677 00:38:13,719 --> 00:38:17,799 Speaker 1: than we thought. You can't just program every kind of 678 00:38:17,840 --> 00:38:20,760 Speaker 1: coffee cup in the world, and even if you could, 679 00:38:21,239 --> 00:38:23,640 Speaker 1: then you also have to program every kind of table 680 00:38:23,920 --> 00:38:26,399 Speaker 1: and every kind of light. And we need to come 681 00:38:26,440 --> 00:38:29,680 Speaker 1: at this in a different way. And so they realized, 682 00:38:29,800 --> 00:38:34,520 Speaker 1: number one, humans are extraordinarily more complex than we thought before. 683 00:38:35,320 --> 00:38:38,400 Speaker 1: And then number two, humans make a pretty good model 684 00:38:38,520 --> 00:38:41,719 Speaker 1: for a humanoid robot in the realm of things like 685 00:38:41,800 --> 00:38:48,200 Speaker 1: perception and UM information systems and UH learning. So they 686 00:38:48,239 --> 00:38:54,000 Speaker 1: went to these different these different disciplines like neurobiology, neurology, 687 00:38:54,120 --> 00:38:57,839 Speaker 1: UM psychology, and they said, what can we learn from 688 00:38:57,880 --> 00:39:00,279 Speaker 1: you guys about how humans do this that we can 689 00:39:00,320 --> 00:39:04,880 Speaker 1: apply to robots. And since they started taking those steps, 690 00:39:04,920 --> 00:39:09,359 Speaker 1: it seems like, uh, humanoid robotics has gotten it's it's 691 00:39:09,360 --> 00:39:12,200 Speaker 1: footing a little more. Yeah, and we're seeing so many 692 00:39:12,239 --> 00:39:15,560 Speaker 1: developments in other areas of a I that are really promising. 693 00:39:15,880 --> 00:39:20,000 Speaker 1: I always bring up IBMS Watson because it's natural language 694 00:39:20,040 --> 00:39:24,960 Speaker 1: recognition was phenomenal, the ability for it to parse clues 695 00:39:25,120 --> 00:39:27,919 Speaker 1: in Jeopardy and come up with the appropriate answer, knowing 696 00:39:27,960 --> 00:39:31,759 Speaker 1: that Jeopardy those clues are not always straightforward. Uh. And 697 00:39:31,840 --> 00:39:36,280 Speaker 1: it again illustrates the complexity that we humans navigate without 698 00:39:36,400 --> 00:39:39,719 Speaker 1: much trouble because this is the world we've created. But 699 00:39:39,840 --> 00:39:42,640 Speaker 1: then we realize if we make a machine that's mostly 700 00:39:42,760 --> 00:39:45,319 Speaker 1: when you get down to it based on yes or no, 701 00:39:45,920 --> 00:39:48,640 Speaker 1: a one or a zero, true or false, and you're 702 00:39:48,640 --> 00:39:51,440 Speaker 1: trying to build complex behaviors off of something that is 703 00:39:51,480 --> 00:39:54,720 Speaker 1: incredibly simple. When you boil it down to its basic element, 704 00:39:55,239 --> 00:39:57,319 Speaker 1: that's where you're like, oh, this is this is gonna 705 00:39:57,360 --> 00:39:59,759 Speaker 1: require a lot of work. I mean, IBMS Watson was 706 00:39:59,800 --> 00:40:05,359 Speaker 1: an enormous machine with with thousands of microprocessors just so 707 00:40:05,440 --> 00:40:08,719 Speaker 1: it could be able to play Jeopardy. That's a very 708 00:40:08,760 --> 00:40:12,520 Speaker 1: specific function too. So creating a robot that is able 709 00:40:12,560 --> 00:40:16,480 Speaker 1: to navigate and interact with a human environment and be 710 00:40:16,520 --> 00:40:18,600 Speaker 1: able to interact with humans in a way that makes 711 00:40:18,640 --> 00:40:21,440 Speaker 1: sense is a big challenge. Also, just the way that 712 00:40:21,719 --> 00:40:25,440 Speaker 1: a robot would socialize with humans is a huge challenge. 713 00:40:25,480 --> 00:40:27,360 Speaker 1: How do how do you make a robot that is 714 00:40:27,400 --> 00:40:33,319 Speaker 1: able to respond to commands and cues in an appropriate way? Uh? 715 00:40:33,400 --> 00:40:35,919 Speaker 1: An appropriate way is the key there, because there are 716 00:40:36,120 --> 00:40:38,520 Speaker 1: humans are pretty complex and we can be very subtle 717 00:40:38,600 --> 00:40:43,600 Speaker 1: in many ways. Yeah, we speak unplainly, we use sarcasm, 718 00:40:43,640 --> 00:40:47,799 Speaker 1: we we uh yeah, we use a lot of gestures 719 00:40:48,600 --> 00:40:51,080 Speaker 1: rather than just words. Yep. There's a lot that goes 720 00:40:51,120 --> 00:40:54,480 Speaker 1: into human communication that, if you are a human is 721 00:40:54,520 --> 00:40:56,879 Speaker 1: pretty much natural, especially I mean if you're a human 722 00:40:56,920 --> 00:40:59,680 Speaker 1: within that particular culture and you're familiar with that culture, 723 00:40:59,719 --> 00:41:03,680 Speaker 1: because anyone who has traveled extensively knows there are cultures 724 00:41:03,680 --> 00:41:07,520 Speaker 1: where things that would be commonplace at home are very 725 00:41:07,520 --> 00:41:09,560 Speaker 1: different in the place where you happen to be, right then, 726 00:41:10,040 --> 00:41:13,000 Speaker 1: and it may be that something that is completely innocent 727 00:41:13,040 --> 00:41:17,120 Speaker 1: at home is an uh, offensive gesture in the place 728 00:41:17,120 --> 00:41:20,240 Speaker 1: where you are. Now, we'll imagine a robot that is 729 00:41:20,600 --> 00:41:24,919 Speaker 1: not programmed to handle these kind of subtle uh communication 730 00:41:25,040 --> 00:41:32,200 Speaker 1: methods and exact Yeah, he doesn't know, he's just he's 731 00:41:32,239 --> 00:41:35,719 Speaker 1: just doing as he was programmed. But even even beyond that, 732 00:41:36,000 --> 00:41:38,279 Speaker 1: something that you brought up in our research when we 733 00:41:38,280 --> 00:41:42,799 Speaker 1: were planning this was the Uncanny Valley. It's a big one. Yeah. 734 00:41:42,880 --> 00:41:45,000 Speaker 1: I've never read that paper before, and I'm glad I did. 735 00:41:45,360 --> 00:41:48,080 Speaker 1: It's really interesting, right, Yeah, So the Uncanny Valley. For 736 00:41:48,080 --> 00:41:50,759 Speaker 1: those who are not familiar with the term, uh, it's 737 00:41:50,840 --> 00:41:55,920 Speaker 1: it describes when we start to approach artificial humans that 738 00:41:55,960 --> 00:41:59,759 Speaker 1: look almost but not quite like real humans. And and 739 00:41:59,800 --> 00:42:02,640 Speaker 1: by look, I don't necessarily just mean the physical appearance. 740 00:42:02,680 --> 00:42:06,239 Speaker 1: I also mean their behaviors, their movements. So if you 741 00:42:06,280 --> 00:42:09,120 Speaker 1: are if you were to look out and see a 742 00:42:09,480 --> 00:42:12,080 Speaker 1: figure that from the from a distance looked like it 743 00:42:12,120 --> 00:42:14,520 Speaker 1: was a human figure, and you start walking towards it, 744 00:42:14,560 --> 00:42:16,520 Speaker 1: just thinking this is another person, and then they start 745 00:42:16,560 --> 00:42:19,840 Speaker 1: moving in a very herky jerky motion, very mechanical motion, 746 00:42:20,440 --> 00:42:24,719 Speaker 1: then you're likely going to have a negative emotional response. 747 00:42:24,920 --> 00:42:29,839 Speaker 1: Um often, revulsion is one of the words used very frequentness. Yeah, 748 00:42:30,960 --> 00:42:34,120 Speaker 1: I mean I remember the C G I movies that 749 00:42:34,160 --> 00:42:38,280 Speaker 1: would that were almost to the point of photo realism, 750 00:42:38,280 --> 00:42:41,440 Speaker 1: where they look like people for the most part, but 751 00:42:41,480 --> 00:42:43,879 Speaker 1: there's not something is just not quite right with the eye. 752 00:42:45,960 --> 00:42:51,280 Speaker 1: There's a good example. And polar express polar expresses they 753 00:42:51,840 --> 00:42:54,160 Speaker 1: do very well because of the Uncanny Valley. That's what 754 00:42:54,200 --> 00:42:56,120 Speaker 1: they blame it on. Yeah, and the same thing applies 755 00:42:56,160 --> 00:42:59,239 Speaker 1: to robots. So in fact, I saw a robot that 756 00:43:00,120 --> 00:43:02,759 Speaker 1: was really disturbing to me. It was really as an 757 00:43:02,960 --> 00:43:07,160 Speaker 1: um art exhibit, an installation, and um it was a 758 00:43:07,239 --> 00:43:12,040 Speaker 1: robot of Confucius in a cell filled with monkeys, and 759 00:43:12,320 --> 00:43:15,959 Speaker 1: uh they're live monkeys, real monkeys, and the robot would 760 00:43:15,960 --> 00:43:21,440 Speaker 1: just thrash around wildly. It was It was the stuff 761 00:43:21,440 --> 00:43:25,160 Speaker 1: of nightmares. I'll show it to you after the show. Yeah. 762 00:43:25,280 --> 00:43:28,439 Speaker 1: So these are all big challenges and some of them 763 00:43:28,480 --> 00:43:30,960 Speaker 1: are going to be harder for us than others. And 764 00:43:31,000 --> 00:43:34,759 Speaker 1: maybe that the engineering challenges of locomotion are solved well 765 00:43:34,840 --> 00:43:37,480 Speaker 1: before we ever get a real grip on all the 766 00:43:37,560 --> 00:43:40,240 Speaker 1: artificial intelligence problems. Or it could be the other way around. 767 00:43:40,680 --> 00:43:45,080 Speaker 1: Uh we but it is multidisciplinary. It's a big, big issue. 768 00:43:45,800 --> 00:43:49,240 Speaker 1: So there are some people who argue for humanoid robots, 769 00:43:49,239 --> 00:43:54,760 Speaker 1: there are people who argue against humanoid robots. Um. I think. 770 00:43:55,000 --> 00:43:58,320 Speaker 1: I think research and development with humanoid robots is important 771 00:43:58,760 --> 00:44:02,120 Speaker 1: because by having the goal of creating a humanoid robot, 772 00:44:02,440 --> 00:44:05,680 Speaker 1: you drive the research and development process. You have a 773 00:44:05,719 --> 00:44:08,560 Speaker 1: specific goal in mind, and in order to achieve that goal, 774 00:44:08,760 --> 00:44:11,160 Speaker 1: you know what sort of problems you have to solve. 775 00:44:11,640 --> 00:44:14,800 Speaker 1: And even if we never enter a future where humanoid 776 00:44:14,840 --> 00:44:19,960 Speaker 1: robots are a common thing, even if they are mostly 777 00:44:20,080 --> 00:44:24,840 Speaker 1: used as something in an exhibition or uh for pr 778 00:44:24,920 --> 00:44:27,759 Speaker 1: or whatever, even if that's the only use for them, 779 00:44:27,800 --> 00:44:31,279 Speaker 1: we're going to benefit from the research and development of 780 00:44:31,360 --> 00:44:35,279 Speaker 1: making that possible in ways we can't anticipate. Well. Yeah, 781 00:44:35,320 --> 00:44:38,480 Speaker 1: and then the more we get into humanoid robotics, the 782 00:44:38,520 --> 00:44:42,920 Speaker 1: more we understand humans, which is pretty much the only 783 00:44:43,239 --> 00:44:47,040 Speaker 1: argument I've seen that stands up in favor of doing 784 00:44:47,120 --> 00:44:50,560 Speaker 1: humanoid robots. Yeah, because it's it's expensive, and it's hard. 785 00:44:50,880 --> 00:44:53,839 Speaker 1: I mean, it's it's really a difficult problem, and it's 786 00:44:54,120 --> 00:44:56,399 Speaker 1: and and to build a humanoid robot something that is 787 00:44:56,800 --> 00:45:01,200 Speaker 1: capable of being a general purpose robot, it's you know, 788 00:45:01,360 --> 00:45:03,560 Speaker 1: it's hard to anticipate all the things you're going to 789 00:45:03,640 --> 00:45:05,920 Speaker 1: need to be able to do. If you're talking general 790 00:45:05,920 --> 00:45:09,200 Speaker 1: purpose and adaptable, that's really tough. I mean, we didn't 791 00:45:09,200 --> 00:45:12,120 Speaker 1: even talk about the adaptability problem very much. We talked 792 00:45:12,120 --> 00:45:14,560 Speaker 1: a little bit about a robot capable of learning from 793 00:45:14,640 --> 00:45:18,319 Speaker 1: other people, which I find fascinating. Um you know, that's 794 00:45:18,360 --> 00:45:22,520 Speaker 1: one way. Just watching humans and then mimicking humans, that's 795 00:45:22,600 --> 00:45:27,680 Speaker 1: one way of robot learning. There's also, um the way 796 00:45:27,680 --> 00:45:31,320 Speaker 1: where it's controlled through virtual reality by human and it 797 00:45:31,440 --> 00:45:34,279 Speaker 1: just kind of logs the motions the humans making it do. 798 00:45:34,520 --> 00:45:36,960 Speaker 1: Like there's a NASA has a robot not that learns 799 00:45:37,040 --> 00:45:41,319 Speaker 1: like that. So I think I think there's a lot 800 00:45:41,360 --> 00:45:46,399 Speaker 1: of benefit to investigating artificial intelligence. Like you want your 801 00:45:46,480 --> 00:45:49,320 Speaker 1: nest at home to learn so you don't have to 802 00:45:49,400 --> 00:45:53,680 Speaker 1: keep adjusting the thermostat that counts. That's the that's machine learning. 803 00:45:54,520 --> 00:45:59,440 Speaker 1: To me. The big argument against having humanoid robots, and 804 00:45:59,480 --> 00:46:03,759 Speaker 1: the quag meyer that seems to begin, is sociability. That 805 00:46:03,840 --> 00:46:07,080 Speaker 1: seems to be the whole reason anybody wants a humanoid robot, 806 00:46:07,120 --> 00:46:10,640 Speaker 1: because you can make you know, you have a ruma vacuums, 807 00:46:10,840 --> 00:46:14,280 Speaker 1: you can make a driverless car um As Olivia Solan 808 00:46:14,400 --> 00:46:18,200 Speaker 1: wrote and wired a couple of years back. Um, you know, 809 00:46:18,320 --> 00:46:20,160 Speaker 1: why why do you have to make a robot butler 810 00:46:20,200 --> 00:46:22,680 Speaker 1: to park the car? Just make a car that parks itself. 811 00:46:23,280 --> 00:46:27,000 Speaker 1: And it seems like that's where we're going right now. Um. 812 00:46:27,360 --> 00:46:30,799 Speaker 1: So when you add this extra layer of humanoid, you 813 00:46:30,880 --> 00:46:35,920 Speaker 1: add all of this additional problems and troubles and redundancies, 814 00:46:35,960 --> 00:46:38,560 Speaker 1: like like, for example, if you're gonna make a humanoid 815 00:46:38,600 --> 00:46:42,560 Speaker 1: robot that throws a ball, this this humanoid robot to 816 00:46:42,640 --> 00:46:46,879 Speaker 1: appear real needs to have a little bit of follow through. 817 00:46:48,120 --> 00:46:50,320 Speaker 1: But as far as the robot, the machine is concerned, 818 00:46:50,360 --> 00:46:53,200 Speaker 1: it can throw the ball and just stop right where 819 00:46:53,200 --> 00:46:55,319 Speaker 1: the releases. It doesn't need to go anymore. But it's 820 00:46:55,320 --> 00:46:58,279 Speaker 1: gonna look weird and robotic if you want to get 821 00:46:58,320 --> 00:47:01,520 Speaker 1: past that uncanny valley, which is an other problem, um, 822 00:47:01,600 --> 00:47:05,200 Speaker 1: the thing has to have followed through. That's totally unnecessary. 823 00:47:05,440 --> 00:47:07,480 Speaker 1: You can make a robot that can throw a ball 824 00:47:07,840 --> 00:47:10,759 Speaker 1: and the goal is to throw the ball. You don't 825 00:47:10,840 --> 00:47:13,480 Speaker 1: have to add the follow through, but you do when 826 00:47:13,480 --> 00:47:17,200 Speaker 1: you're making it a sociable humanoid robots. So it seems 827 00:47:17,200 --> 00:47:20,680 Speaker 1: like that's the path that will lead everyone is straight 828 00:47:20,800 --> 00:47:23,720 Speaker 1: that I don't get. Yeah. I I like the idea 829 00:47:23,760 --> 00:47:27,880 Speaker 1: of designing robots for specific tasks because you can really 830 00:47:27,920 --> 00:47:30,640 Speaker 1: focus on getting the task done. So there I see 831 00:47:30,640 --> 00:47:33,480 Speaker 1: this as two separate branches. I see the branch of 832 00:47:33,520 --> 00:47:37,120 Speaker 1: developing the humanoid robot as pushing forward a lot of 833 00:47:37,160 --> 00:47:41,440 Speaker 1: different areas of thought. That could be applied in multiple disciplines, 834 00:47:41,880 --> 00:47:45,280 Speaker 1: so that will benefit from that. I see the development 835 00:47:45,280 --> 00:47:49,360 Speaker 1: of robots as unitaskers as being important to actually handle 836 00:47:49,360 --> 00:47:53,080 Speaker 1: the jobs that are the three D s. That's dirty, difficult, 837 00:47:53,120 --> 00:47:57,359 Speaker 1: and dangerous, all right, So those are the jobs that 838 00:47:58,040 --> 00:48:01,560 Speaker 1: maybe they revolve a lot of repetition, which can cause 839 00:48:01,640 --> 00:48:04,920 Speaker 1: injury over time, or it can lead to mistakes because 840 00:48:05,000 --> 00:48:07,080 Speaker 1: you've done the same task so many times that you 841 00:48:07,080 --> 00:48:11,360 Speaker 1: start to kind of zone out. Robots will never zone out. Um. 842 00:48:11,400 --> 00:48:14,640 Speaker 1: If it's a dirty job where it's something that's undesirable 843 00:48:14,640 --> 00:48:17,799 Speaker 1: by people, robots don't care. They'll do that. Or if 844 00:48:17,840 --> 00:48:21,520 Speaker 1: it's dangerous, if it's bomb disposal, or if it's something 845 00:48:21,560 --> 00:48:25,840 Speaker 1: like the Mars curiosity rover. These are dangerous jobs that 846 00:48:25,880 --> 00:48:29,359 Speaker 1: you wouldn't necessarily want to put a human into if 847 00:48:29,440 --> 00:48:33,240 Speaker 1: you had the alternative. So all of these things, those 848 00:48:33,280 --> 00:48:36,360 Speaker 1: that's where robots really makes sense to me UM to 849 00:48:36,360 --> 00:48:38,480 Speaker 1: to go to the places that are difficult for us 850 00:48:38,480 --> 00:48:41,279 Speaker 1: to go to. Maybe that's you know, deep sea exploration, 851 00:48:41,360 --> 00:48:45,080 Speaker 1: space exploration, that kind of thing, or to do jobs 852 00:48:45,120 --> 00:48:47,720 Speaker 1: that might be dangerous, having a first respond to robot 853 00:48:47,800 --> 00:48:51,040 Speaker 1: to survey a scene, to make sure that a structure 854 00:48:51,160 --> 00:48:54,360 Speaker 1: is remaining uh solid while maybe there was a fire 855 00:48:54,440 --> 00:48:57,319 Speaker 1: and it has to make sure that the it's it's 856 00:48:57,360 --> 00:49:01,200 Speaker 1: not going to collapse in on rescue mission that kind 857 00:49:01,239 --> 00:49:03,799 Speaker 1: of stuff. Um, but do you need those things to 858 00:49:03,960 --> 00:49:06,000 Speaker 1: be to come out and be able to tell a 859 00:49:06,080 --> 00:49:09,680 Speaker 1: joke or something? And most of them don't need to 860 00:49:09,719 --> 00:49:14,240 Speaker 1: be any sort of humanoid form factor either, which greatly 861 00:49:14,280 --> 00:49:17,680 Speaker 1: simplifies the actual development of the robot and thus cuts 862 00:49:17,719 --> 00:49:20,200 Speaker 1: down on the cost, so you can you can achieve 863 00:49:20,239 --> 00:49:23,520 Speaker 1: the task you're trying to achieve for less money than 864 00:49:23,560 --> 00:49:26,160 Speaker 1: if you are trying to build this this general purpose machine. 865 00:49:26,200 --> 00:49:33,160 Speaker 1: So then we come to this ultimate question, why what's 866 00:49:33,200 --> 00:49:36,279 Speaker 1: the purpose of humanoid robot? Well, I think the I 867 00:49:36,320 --> 00:49:39,920 Speaker 1: think the purposes too fold. One is again to have 868 00:49:40,080 --> 00:49:45,719 Speaker 1: that specific goal in mind that allows you to define 869 00:49:45,920 --> 00:49:49,360 Speaker 1: where your in point is. I believe that when you 870 00:49:49,440 --> 00:49:52,640 Speaker 1: have that defined in goal, it makes it easier for 871 00:49:52,680 --> 00:49:54,960 Speaker 1: you to build on the things you need to achieve it, 872 00:49:54,960 --> 00:49:57,480 Speaker 1: as opposed to having an open goal where it's just 873 00:49:57,680 --> 00:50:01,160 Speaker 1: I want to approve improve a I that's so open 874 00:50:01,200 --> 00:50:03,120 Speaker 1: that it's hard to get direction from it. But if 875 00:50:03,160 --> 00:50:06,120 Speaker 1: you think I need to have an artificial intelligence that 876 00:50:06,120 --> 00:50:09,840 Speaker 1: will allow a robot to Uh, here's a great example. 877 00:50:09,880 --> 00:50:12,160 Speaker 1: Let's say that the challenge is to have a robot 878 00:50:12,880 --> 00:50:16,640 Speaker 1: leave a room, go down a flight of stairs, leave 879 00:50:16,680 --> 00:50:20,080 Speaker 1: a building, get into a vehicle, drive the vehicle to 880 00:50:20,080 --> 00:50:23,640 Speaker 1: a different location, get out of the vehicle, go into 881 00:50:23,680 --> 00:50:27,240 Speaker 1: another building, break through a wall, and put out a fire. 882 00:50:27,840 --> 00:50:32,880 Speaker 1: That's a real, actual robotics challenge challenge. Yeah. Dr Henrik 883 00:50:32,960 --> 00:50:35,439 Speaker 1: Kristensen told me about this. Is I mean, it really 884 00:50:35,480 --> 00:50:37,719 Speaker 1: is a challenge. It's not just a real challenge. It's 885 00:50:37,719 --> 00:50:42,120 Speaker 1: a real challenge. It's like a DARPA challenge. So it's 886 00:50:42,200 --> 00:50:44,680 Speaker 1: a uh he was telling me about this, and you 887 00:50:44,719 --> 00:50:46,600 Speaker 1: start to think about all the things that have to 888 00:50:46,640 --> 00:50:48,160 Speaker 1: fall in line for you to be able to achieve 889 00:50:48,200 --> 00:50:50,279 Speaker 1: the skull. That is a valuable thing. But I think 890 00:50:50,320 --> 00:50:52,360 Speaker 1: the other thing is the social aspect. I think that 891 00:50:52,400 --> 00:50:55,879 Speaker 1: there are people who would benefit from a robot that 892 00:50:56,120 --> 00:50:59,759 Speaker 1: is able to give some form of social comfort. Let's 893 00:50:59,760 --> 00:51:04,239 Speaker 1: say for the elderly who need to have some form 894 00:51:04,280 --> 00:51:08,080 Speaker 1: of interaction. Um, you know, that could actually be a 895 00:51:08,120 --> 00:51:10,520 Speaker 1: really valuable tool. And in fact, there's a lot of 896 00:51:10,520 --> 00:51:14,040 Speaker 1: work that's going into robotics to help people like the 897 00:51:14,080 --> 00:51:20,680 Speaker 1: elderly who may have real emotional and psychological problems, Um, 898 00:51:20,760 --> 00:51:23,880 Speaker 1: due to loneliness. Do you think that robots are the 899 00:51:23,920 --> 00:51:27,440 Speaker 1: answer to that? I think that robots can help. I 900 00:51:27,480 --> 00:51:29,400 Speaker 1: don't know. I would never go so far as to 901 00:51:29,400 --> 00:51:32,680 Speaker 1: say answer. But couldn't you also make the argument that 902 00:51:33,200 --> 00:51:39,640 Speaker 1: if you created robots that displaced human jobs and also 903 00:51:39,719 --> 00:51:46,520 Speaker 1: simultaneously said, hey, this, this nursing home sector is about 904 00:51:46,560 --> 00:51:49,000 Speaker 1: to explode because we've got a bunch of baby boomers 905 00:51:49,000 --> 00:51:52,840 Speaker 1: and ways the society of now decided that our elderly 906 00:51:52,920 --> 00:51:58,520 Speaker 1: need human interaction more than we've more than we've carried 907 00:51:58,520 --> 00:52:01,840 Speaker 1: it out before. So let's create this whole other industry. 908 00:52:01,920 --> 00:52:06,320 Speaker 1: Or let's expand this industry of elderly caretakers and fill 909 00:52:06,680 --> 00:52:10,640 Speaker 1: those jobs with people who have been displaced by roots. 910 00:52:11,160 --> 00:52:15,640 Speaker 1: Wouldn't that be better? That might be? Or you could again, 911 00:52:15,880 --> 00:52:18,560 Speaker 1: looking at the way a lot of roboticists framed this, 912 00:52:19,200 --> 00:52:21,839 Speaker 1: they say, all right, well, it is a reality that 913 00:52:21,960 --> 00:52:27,480 Speaker 1: robots are taking over actual jobs, but the hope is 914 00:52:27,520 --> 00:52:31,160 Speaker 1: that it also ends up creating new jobs that are 915 00:52:31,200 --> 00:52:36,520 Speaker 1: better paying jobs, less dangerous jobs friendly, more old books friendly. 916 00:52:37,400 --> 00:52:40,600 Speaker 1: But yeah, like um, the idea being that that it 917 00:52:40,719 --> 00:52:45,000 Speaker 1: frees up people and encourages the pursuit of jobs and 918 00:52:45,080 --> 00:52:50,120 Speaker 1: engineering in computer science. Now we live in the real 919 00:52:50,160 --> 00:52:53,520 Speaker 1: world and we understand that it's a lot more complex 920 00:52:53,560 --> 00:52:56,640 Speaker 1: than telling someone who's been working on a manufacturing line, Hey, 921 00:52:56,840 --> 00:52:59,160 Speaker 1: I'm sorry your job's gone because there's a robot here. 922 00:52:59,160 --> 00:53:01,680 Speaker 1: But guess what, we have an opening and engineering. So 923 00:53:01,719 --> 00:53:04,480 Speaker 1: if you just go and pursue a four year degree 924 00:53:04,520 --> 00:53:07,120 Speaker 1: and then some post graduate work, you'll be right back 925 00:53:07,160 --> 00:53:10,719 Speaker 1: to work. That's that's obviously not uh something that's going 926 00:53:10,760 --> 00:53:14,040 Speaker 1: to be easy, especially in the short term. But the 927 00:53:14,080 --> 00:53:16,879 Speaker 1: long term hope is that more and more of these 928 00:53:17,000 --> 00:53:20,600 Speaker 1: jobs that are are dangerous for people, are less desirable 929 00:53:20,640 --> 00:53:24,399 Speaker 1: for people, will be taken up by robots, and then 930 00:53:24,560 --> 00:53:28,200 Speaker 1: the will there will be the creation of better jobs 931 00:53:28,239 --> 00:53:29,920 Speaker 1: that are higher up on the food chain. And I 932 00:53:29,920 --> 00:53:32,680 Speaker 1: think that makes sense to me. It's just the once 933 00:53:32,719 --> 00:53:37,200 Speaker 1: you enter the sociability, yeah, because without sociability, there's no 934 00:53:37,320 --> 00:53:40,439 Speaker 1: reason to create a humanoid robot. Everything else can look 935 00:53:40,520 --> 00:53:44,239 Speaker 1: like a robot. Yeah. Um, so it's it's when you 936 00:53:44,360 --> 00:53:46,880 Speaker 1: enter sociability that you lose me. Not only does it 937 00:53:47,120 --> 00:53:49,040 Speaker 1: can it look like a robot, but we can still 938 00:53:49,120 --> 00:53:51,239 Speaker 1: socialize with it, even if it doesn't look like a 939 00:53:51,320 --> 00:53:54,360 Speaker 1: human people there. You know, there's the story that Rumba 940 00:53:54,400 --> 00:53:57,920 Speaker 1: owners named the Yeah yeah, so you we we end 941 00:53:58,000 --> 00:54:02,279 Speaker 1: up having these kind of emotional attachments and investments in 942 00:54:02,880 --> 00:54:05,439 Speaker 1: things that don't look not only do they not like human, 943 00:54:05,560 --> 00:54:08,520 Speaker 1: they don't look like any other animal that we would 944 00:54:08,600 --> 00:54:13,080 Speaker 1: interact with on a like owner or and pet or whatever. 945 00:54:13,120 --> 00:54:16,319 Speaker 1: I mean, they they're they're just a robot. So I 946 00:54:16,360 --> 00:54:18,040 Speaker 1: think at the end of the day, Josh, I think 947 00:54:18,080 --> 00:54:20,160 Speaker 1: we're on the same page. We think humanoid robots are 948 00:54:20,200 --> 00:54:23,520 Speaker 1: an interesting idea, but not necessarily the end goal. There's 949 00:54:23,640 --> 00:54:27,000 Speaker 1: there's not a whole lot of of incentive to go 950 00:54:27,120 --> 00:54:29,799 Speaker 1: after it for its own purposes. We can see the 951 00:54:29,800 --> 00:54:32,239 Speaker 1: benefits of going after it in the sense of the 952 00:54:32,239 --> 00:54:35,160 Speaker 1: developments that are made in that pursuit help us in 953 00:54:35,200 --> 00:54:41,399 Speaker 1: other ways. But I don't need a human robot, Butler, Yeah, 954 00:54:42,280 --> 00:54:45,799 Speaker 1: I just know I don't. Well, I'm curious to hear 955 00:54:45,880 --> 00:54:49,040 Speaker 1: what my listeners have to say about this. You can 956 00:54:49,080 --> 00:54:51,800 Speaker 1: get in touch with me my email addresses, text stuff 957 00:54:51,960 --> 00:54:54,480 Speaker 1: at hell stuff works dot com, or drop me a 958 00:54:54,520 --> 00:54:59,560 Speaker 1: line on Twitter or Facebook or tumbler. Tech Stuff HSW 959 00:54:59,800 --> 00:55:02,399 Speaker 1: is the handle for all three of those. Josh, thank 960 00:55:02,480 --> 00:55:05,120 Speaker 1: you so much for being on the show. Thank you 961 00:55:05,160 --> 00:55:07,120 Speaker 1: for having me. I'm let do this begin now. If 962 00:55:07,160 --> 00:55:10,720 Speaker 1: you have not heard stuff, you should know, you definitely 963 00:55:10,760 --> 00:55:12,560 Speaker 1: need to go and check that out because it is 964 00:55:12,600 --> 00:55:16,440 Speaker 1: a phenomenal podcast. Thank you. Josh is one of the 965 00:55:16,480 --> 00:55:19,160 Speaker 1: two hosts, the other being Chuck Bryant, who I hope 966 00:55:19,160 --> 00:55:21,719 Speaker 1: to have on tech stuff in the near future, so 967 00:55:21,880 --> 00:55:23,600 Speaker 1: keep your ears up for that. And Josh, I hope 968 00:55:23,640 --> 00:55:26,560 Speaker 1: I can grab you back in here for another episode 969 00:55:26,600 --> 00:55:30,400 Speaker 1: in each time. Man awesome. Well, thank you again, and folks, 970 00:55:30,520 --> 00:55:35,319 Speaker 1: we'll talk to you again really soon for more on 971 00:55:35,400 --> 00:55:37,719 Speaker 1: this and thousands of other topics. Because it has to 972 00:55:37,880 --> 00:55:48,280 Speaker 1: works dot Com