1 00:00:00,480 --> 00:00:03,760 Speaker 1: One of my greatest fears is doing something ridiculous in 2 00:00:03,800 --> 00:00:05,480 Speaker 1: my house late at night, because you know how I 3 00:00:05,519 --> 00:00:08,520 Speaker 1: like to shuffle around and I hurt myself and no 4 00:00:08,560 --> 00:00:11,799 Speaker 1: one hears me call for help. You know, No, that 5 00:00:11,920 --> 00:00:15,600 Speaker 1: is scary, right it is. But what if instead of 6 00:00:15,680 --> 00:00:18,360 Speaker 1: laying on the ground needing life alert, there was a 7 00:00:18,520 --> 00:00:22,119 Speaker 1: robot that could catch me before I even feel I 8 00:00:22,160 --> 00:00:23,239 Speaker 1: love that idea. 9 00:00:23,760 --> 00:00:27,240 Speaker 2: So today we're gonna be talking elder care engineering and 10 00:00:27,280 --> 00:00:31,680 Speaker 2: the soft, squishy future of robotic support. I'm TT and 11 00:00:31,720 --> 00:00:39,560 Speaker 2: I'm Zakiah and this is Dope Labs. Welcome to Dope Labs, 12 00:00:39,640 --> 00:00:42,960 Speaker 2: a weekly podcast that mixes hardcore science with pop culture 13 00:00:43,040 --> 00:00:50,760 Speaker 2: and a healthy dose of friendship. In today's lab, we're 14 00:00:50,800 --> 00:00:53,880 Speaker 2: talking about aging in America and the technology that could 15 00:00:53,880 --> 00:00:58,200 Speaker 2: help us stay safer for longer. Our guest is Roberto Bowley, 16 00:00:58,280 --> 00:01:03,080 Speaker 2: a mechanical engineering PhDc student MIT who's designing a robot 17 00:01:03,120 --> 00:01:06,679 Speaker 2: that can literally catch you when you fall. It's called Ebar. 18 00:01:07,120 --> 00:01:10,399 Speaker 2: But before we meet the robot, let's set the stage. 19 00:01:10,800 --> 00:01:15,240 Speaker 1: What do we know? So between twenty ten and twenty twenty, 20 00:01:15,520 --> 00:01:18,920 Speaker 1: the US Census told us that the over sixty five 21 00:01:19,000 --> 00:01:22,160 Speaker 1: population saw the largest and fastest growth spurt that has 22 00:01:22,160 --> 00:01:25,480 Speaker 1: seen since to like late eighteen hundreds, and according to 23 00:01:25,520 --> 00:01:28,840 Speaker 1: the Urban Institute, by twenty forty, we're expecting one in 24 00:01:28,880 --> 00:01:31,679 Speaker 1: five Americans to be over sixty five. And what do 25 00:01:31,720 --> 00:01:32,760 Speaker 1: we want to know? 26 00:01:33,200 --> 00:01:35,280 Speaker 2: Well, I want to know what kind of tech could 27 00:01:35,440 --> 00:01:38,880 Speaker 2: actually help? Like, how do you build a robot that 28 00:01:38,959 --> 00:01:42,200 Speaker 2: doesn't feel scary, you know, not like the ones that 29 00:01:42,440 --> 00:01:44,160 Speaker 2: from I robot that are going to turn on you? 30 00:01:44,240 --> 00:01:48,000 Speaker 1: And yeah, what were they thinking? Or that's too invasive? 31 00:01:48,080 --> 00:01:48,760 Speaker 1: You know what I mean? 32 00:01:49,440 --> 00:01:52,440 Speaker 2: Yeah, what does it take to go from a great 33 00:01:52,480 --> 00:01:57,160 Speaker 2: idea to a real life idea that's manifesting in front 34 00:01:57,200 --> 00:02:01,640 Speaker 2: of you, that is safety certified and in someone's living room. 35 00:02:01,920 --> 00:02:04,280 Speaker 1: I think we're ready to jump right into the dissection. 36 00:02:08,639 --> 00:02:11,360 Speaker 3: My name is Roberto Bolly. I'm a graduate student at 37 00:02:11,400 --> 00:02:13,280 Speaker 3: MIT studying mechanical engineering. 38 00:02:14,120 --> 00:02:17,160 Speaker 1: Where do you think some of our biggest disconnects are 39 00:02:17,200 --> 00:02:20,120 Speaker 1: between people's hopes for what that kind of aging looks 40 00:02:20,200 --> 00:02:24,360 Speaker 1: like and what our current caregiving support infrastructure delivers today. 41 00:02:24,760 --> 00:02:26,720 Speaker 3: So we actually we did a lot of interviews with 42 00:02:26,760 --> 00:02:29,280 Speaker 3: elderly people where do they need support? What kind of 43 00:02:29,320 --> 00:02:32,440 Speaker 3: support are they looking for? And we found like virtually 44 00:02:32,520 --> 00:02:35,760 Speaker 3: everybody we interviewed once to Asian place at home, Like 45 00:02:35,800 --> 00:02:38,200 Speaker 3: that's like, I feel like the goal. It's like, you 46 00:02:38,240 --> 00:02:41,200 Speaker 3: get older, you live at home, you have hobbies like 47 00:02:41,240 --> 00:02:44,000 Speaker 3: gardening or moving around the home, and you know, you 48 00:02:44,120 --> 00:02:49,400 Speaker 3: just gracefully age in place. The reality is that something 49 00:02:49,520 --> 00:02:52,440 Speaker 3: like thirty or forty percent of elderly people fall each year. 50 00:02:52,840 --> 00:02:57,080 Speaker 3: Oh and oftentimes when they fall it's like a debilitating injury. Like, 51 00:02:57,120 --> 00:02:59,560 Speaker 3: if you're young, you fall, it's not to make a deal. 52 00:02:59,600 --> 00:03:01,440 Speaker 3: You might get a bruise or something. But if you're 53 00:03:01,480 --> 00:03:03,440 Speaker 3: old and you fall, you can sometimes break a hip. 54 00:03:04,440 --> 00:03:07,520 Speaker 3: And so unfortunately, what we see is a lot of 55 00:03:07,560 --> 00:03:11,000 Speaker 3: people get shuttled into nursing care or long term care, 56 00:03:11,800 --> 00:03:13,560 Speaker 3: and they often don't like it. They want to go 57 00:03:13,639 --> 00:03:17,560 Speaker 3: back to their homes. Sometimes they get suboptimal care because 58 00:03:17,600 --> 00:03:19,399 Speaker 3: there's also a big shortage of caregivers. 59 00:03:19,919 --> 00:03:23,320 Speaker 2: Can you clarify what age is elderly? 60 00:03:24,080 --> 00:03:24,680 Speaker 1: Ah? 61 00:03:25,600 --> 00:03:27,880 Speaker 3: I think in our lab we've been looking at people 62 00:03:27,919 --> 00:03:31,600 Speaker 3: over sixty five, but there's no really good definition. Because 63 00:03:31,600 --> 00:03:34,080 Speaker 3: I met someone who is seventy five and who bikes 64 00:03:34,160 --> 00:03:37,520 Speaker 3: like eight miles a day is in probably better shape 65 00:03:37,560 --> 00:03:41,560 Speaker 3: than me, but more than like an age we're looking 66 00:03:41,600 --> 00:03:44,800 Speaker 3: at like a subgroup. So we say people who have 67 00:03:44,920 --> 00:03:47,960 Speaker 3: like medium muscle strength, so they're able to hold onto 68 00:03:47,960 --> 00:03:51,000 Speaker 3: handlebars or do activities of daily living, but they may 69 00:03:51,040 --> 00:03:52,960 Speaker 3: lose their balance or they have a tendency to fall, 70 00:03:53,400 --> 00:03:56,560 Speaker 3: and sometimes for hard transfers like getting out of a bathtub, 71 00:03:56,600 --> 00:03:58,760 Speaker 3: they require assistance, like they need to grab onto a 72 00:03:58,760 --> 00:03:59,600 Speaker 3: handlebar or something. 73 00:04:00,280 --> 00:04:02,880 Speaker 1: When we consider the increasing demand for care of an 74 00:04:02,880 --> 00:04:06,560 Speaker 1: aging population, you and your team are proposing robotics as 75 00:04:06,560 --> 00:04:09,840 Speaker 1: a solution or at least an enhancement. And from what 76 00:04:09,880 --> 00:04:14,240 Speaker 1: you've said, people want robotics, which I'm surprised by. I 77 00:04:14,280 --> 00:04:16,960 Speaker 1: think I would have intuitively thought that older people would 78 00:04:17,000 --> 00:04:18,279 Speaker 1: be anti robotic. 79 00:04:18,600 --> 00:04:20,839 Speaker 2: I would have thought that too, But then I mean, 80 00:04:21,400 --> 00:04:25,880 Speaker 2: here comes Ebar, this really amazing invention of yours that's 81 00:04:26,000 --> 00:04:28,200 Speaker 2: meant to help older people in the ways that they 82 00:04:28,240 --> 00:04:28,920 Speaker 2: want to be helped. 83 00:04:29,440 --> 00:04:32,799 Speaker 3: Yeah, for sure. So Ebar came about because we're looking 84 00:04:32,839 --> 00:04:35,640 Speaker 3: around through the literature and through what devices are available, 85 00:04:36,000 --> 00:04:39,320 Speaker 3: and we found that for robots that actually catch a fall, 86 00:04:39,640 --> 00:04:41,159 Speaker 3: pretty much all of them you have to wear a 87 00:04:41,200 --> 00:04:44,520 Speaker 3: harness or like some sort of wearable device. But like 88 00:04:44,600 --> 00:04:48,360 Speaker 3: elderly people hate to do that. The feedback we got 89 00:04:48,400 --> 00:04:52,679 Speaker 3: was that it makes them feel old and it's sometimes cumbersome. Yeah. Yeah, 90 00:04:53,120 --> 00:04:55,120 Speaker 3: So we're trying to develop a robot that can catch 91 00:04:55,120 --> 00:04:57,719 Speaker 3: a fall without any like having to wear any sort 92 00:04:57,720 --> 00:05:00,760 Speaker 3: of device. And then another thing we found is that 93 00:05:00,800 --> 00:05:03,080 Speaker 3: a lot of elder care robut it's only a few 94 00:05:03,120 --> 00:05:07,240 Speaker 3: that have looked at physical assistance. But typically you have 95 00:05:07,320 --> 00:05:09,599 Speaker 3: to stand within what's called the base of support of 96 00:05:09,640 --> 00:05:12,160 Speaker 3: the robot. So if you imagine all the points of 97 00:05:12,160 --> 00:05:14,760 Speaker 3: the robot that touch the floor, if you like connect 98 00:05:14,839 --> 00:05:18,200 Speaker 3: them with lines, as long as you stand within that area, 99 00:05:18,320 --> 00:05:20,960 Speaker 3: the robot will never tip because you're within the base 100 00:05:21,000 --> 00:05:23,960 Speaker 3: of support. But if you're outside, for some robots, they 101 00:05:23,960 --> 00:05:26,960 Speaker 3: can tip over. So we're trying to design a robot 102 00:05:27,000 --> 00:05:29,440 Speaker 3: that stable even if you're outside of that base of support, 103 00:05:29,480 --> 00:05:31,560 Speaker 3: because then it can go like over bathtuble lips, it 104 00:05:31,600 --> 00:05:34,240 Speaker 3: can go like onto a bed, it can go over 105 00:05:34,320 --> 00:05:37,320 Speaker 3: like gaps and obstacles. So we put these two together 106 00:05:37,400 --> 00:05:40,520 Speaker 3: and we developed what my professor calls like a mobile 107 00:05:40,600 --> 00:05:44,440 Speaker 3: forklift or robotic candlebars. 108 00:05:44,720 --> 00:05:48,039 Speaker 2: I think that that is so fascinating and such a 109 00:05:48,120 --> 00:05:51,080 Speaker 2: leap forward in the technology for the folks that you 110 00:05:51,120 --> 00:05:53,400 Speaker 2: know they're going to be listening. They can't see us. 111 00:05:53,480 --> 00:05:55,760 Speaker 2: Hopefully they'll do their googles to be able to see ebar. 112 00:05:55,839 --> 00:05:59,640 Speaker 2: Can you just describe what ebar looks like from top 113 00:05:59,680 --> 00:06:02,679 Speaker 2: to box so that somebody can visualize it in their mind. 114 00:06:03,240 --> 00:06:06,159 Speaker 3: Sure, yeah, I'll try to do my best. It's this 115 00:06:06,279 --> 00:06:09,680 Speaker 3: robot that can drive around. It can catch people with 116 00:06:09,720 --> 00:06:12,280 Speaker 3: airbags when they fall. It can like physically lift them 117 00:06:12,360 --> 00:06:14,560 Speaker 3: up with this sort of U shaped fork at the front, 118 00:06:14,560 --> 00:06:16,479 Speaker 3: and then it has handlebars for them to grab onto. 119 00:06:16,640 --> 00:06:19,320 Speaker 3: It's kind of just this big U that's padded with 120 00:06:19,400 --> 00:06:21,760 Speaker 3: handlebars on the front and on the back. That's the 121 00:06:21,760 --> 00:06:24,000 Speaker 3: part of the robot that you grab onto. You can 122 00:06:24,040 --> 00:06:25,920 Speaker 3: rest your forearms on it, or you can just grab 123 00:06:25,960 --> 00:06:28,120 Speaker 3: onto the handlebars on the side. And it has the 124 00:06:28,160 --> 00:06:32,080 Speaker 3: airbags underneath which can grab onto your waist. So that 125 00:06:32,200 --> 00:06:35,480 Speaker 3: U shaped fork is attached to a big linkage, and 126 00:06:35,560 --> 00:06:38,719 Speaker 3: then that whole thing is attached to an omnidirectional drive base. 127 00:06:39,400 --> 00:06:41,360 Speaker 3: And so the drive base, you know, like if you're 128 00:06:41,360 --> 00:06:44,040 Speaker 3: trying to parallel parker car, you can't just like slide 129 00:06:44,040 --> 00:06:45,800 Speaker 3: into a spot. You kind of have to move back 130 00:06:45,839 --> 00:06:46,200 Speaker 3: and forth. 131 00:06:46,279 --> 00:06:49,800 Speaker 2: Right, Oh, Yeah. 132 00:06:50,040 --> 00:06:53,120 Speaker 3: So this robot has four wheels. Each wheel can independently 133 00:06:53,200 --> 00:06:55,640 Speaker 3: rotate and translate, and so you can actually just go 134 00:06:55,720 --> 00:06:58,200 Speaker 3: and then move sideways instantly, so it can move in 135 00:06:58,279 --> 00:06:58,880 Speaker 3: any direction. 136 00:06:59,200 --> 00:07:00,920 Speaker 1: That's great, That is amazing. 137 00:07:01,800 --> 00:07:04,080 Speaker 3: I didn't put this in the paper, but I believe 138 00:07:04,120 --> 00:07:07,360 Speaker 3: it's probably the world's fastest elder care robot. So we 139 00:07:08,680 --> 00:07:11,320 Speaker 3: limit the power for safety, but it has a max 140 00:07:11,360 --> 00:07:14,800 Speaker 3: speed of around twelve feet per second. It's very powerful, 141 00:07:17,240 --> 00:07:17,800 Speaker 3: it's moved. 142 00:07:17,840 --> 00:07:19,480 Speaker 2: I need one of those for my home. 143 00:07:20,840 --> 00:07:22,960 Speaker 3: We limit it to like one to two feet per second. 144 00:07:22,960 --> 00:07:24,800 Speaker 3: You know, they don't want to cause any injuries. 145 00:07:25,000 --> 00:07:29,840 Speaker 1: Yeah. I think that's a great description of the design 146 00:07:30,080 --> 00:07:32,920 Speaker 1: of how ebar looks. And I watched some of the 147 00:07:32,920 --> 00:07:35,960 Speaker 1: footage that you all share it's on YouTube, and it 148 00:07:36,000 --> 00:07:37,480 Speaker 1: looked like you had I don't know if it was 149 00:07:37,560 --> 00:07:41,800 Speaker 1: PlayStation or Xbox style, like a joystick on there, a controller. 150 00:07:41,920 --> 00:07:44,280 Speaker 1: Was that part of early testing? You know, what kind 151 00:07:44,320 --> 00:07:46,880 Speaker 1: of control system does e bar have? 152 00:07:47,640 --> 00:07:50,120 Speaker 3: Yeah? So right now, in the original paper, it's just 153 00:07:50,240 --> 00:07:52,800 Speaker 3: manually controlled with a joystick, like similar to what you 154 00:07:52,840 --> 00:07:55,600 Speaker 3: see with mobility scooters, where there's a joystick and people 155 00:07:55,680 --> 00:07:58,400 Speaker 3: just sort of move it around. Currently, right now in 156 00:07:58,440 --> 00:08:01,440 Speaker 3: the lab, we're working on automating some of the functionality. 157 00:08:01,960 --> 00:08:04,800 Speaker 3: So we have a project where we're trying to use 158 00:08:04,800 --> 00:08:07,600 Speaker 3: the drive base to track a person automatically so it 159 00:08:07,600 --> 00:08:11,280 Speaker 3: can follow them around. And so you know, it's a 160 00:08:11,280 --> 00:08:13,720 Speaker 3: lot of work to do that sort of automation, so 161 00:08:13,800 --> 00:08:16,040 Speaker 3: we kind of just went for manual control first, but 162 00:08:16,080 --> 00:08:17,280 Speaker 3: we're definitely looking into it. 163 00:08:17,400 --> 00:08:18,280 Speaker 1: That's really cool. 164 00:08:18,440 --> 00:08:22,120 Speaker 2: My background is also engineering, and so I also have 165 00:08:22,240 --> 00:08:24,960 Speaker 2: a degree in mechanical engineering, and so I know that 166 00:08:25,160 --> 00:08:29,880 Speaker 2: part of this is about footprint, because if you're thinking 167 00:08:29,880 --> 00:08:33,360 Speaker 2: about the function of this robotis to help folks with 168 00:08:33,520 --> 00:08:35,880 Speaker 2: getting around and to keep them safe, we know that 169 00:08:35,920 --> 00:08:38,960 Speaker 2: it has to be able to take up as least 170 00:08:38,960 --> 00:08:41,760 Speaker 2: amount of space as possible. Can you talk about the 171 00:08:41,880 --> 00:08:45,640 Speaker 2: role that the robots footprint played in your design and 172 00:08:45,679 --> 00:08:48,880 Speaker 2: how did you make sure that it could navigate in 173 00:08:49,000 --> 00:08:52,720 Speaker 2: tight spaces inside of a home without tipping over or 174 00:08:52,880 --> 00:08:56,240 Speaker 2: interfering with other things in the house or the user. 175 00:08:56,800 --> 00:08:59,840 Speaker 3: Yeah, for sure, for sure. So our goal was to 176 00:08:59,840 --> 00:09:03,240 Speaker 3: make the robe but as small as possible. The problem 177 00:09:03,320 --> 00:09:06,480 Speaker 3: is that you know, if it were just like six 178 00:09:06,520 --> 00:09:10,600 Speaker 3: inches wide, it would tip over immediately. So what we 179 00:09:10,640 --> 00:09:13,800 Speaker 3: did is. We set up a sort of an optimization problem, 180 00:09:14,080 --> 00:09:18,000 Speaker 3: and from a high level we said, okay, like how 181 00:09:18,040 --> 00:09:20,840 Speaker 3: small can we make the drive base and how heavy 182 00:09:20,840 --> 00:09:23,040 Speaker 3: can we make it so that it doesn't fall through 183 00:09:23,040 --> 00:09:25,960 Speaker 3: the floor. Because you know, if you think about a person, 184 00:09:26,000 --> 00:09:28,640 Speaker 3: a person occupies about one square foot of space if 185 00:09:28,640 --> 00:09:31,240 Speaker 3: they're standing up straight. He said, okay, you know the 186 00:09:31,280 --> 00:09:34,319 Speaker 3: average person. A floor can support a person that weighs 187 00:09:34,320 --> 00:09:36,480 Speaker 3: maybe two hundred three hundred pounds, no problem, So we'll 188 00:09:36,520 --> 00:09:39,520 Speaker 3: try to limit the robot weight to that. Then we 189 00:09:39,559 --> 00:09:42,480 Speaker 3: looked at like what are the maximum forces people can 190 00:09:42,520 --> 00:09:46,080 Speaker 3: apply laterally and horizontally. So it turns out the US 191 00:09:46,080 --> 00:09:48,040 Speaker 3: military has done a lot of studies like this in 192 00:09:48,080 --> 00:09:50,240 Speaker 3: the eighties and they found that, like I think it's 193 00:09:50,240 --> 00:09:53,280 Speaker 3: like one hundred and twenty Newton's horizontal force, they have 194 00:09:53,440 --> 00:09:56,400 Speaker 3: like force from any orientation. So we can quantify this 195 00:09:56,559 --> 00:09:58,800 Speaker 3: really well, like when you're standing up, how much can 196 00:09:58,800 --> 00:09:59,760 Speaker 3: you push on the robot? 197 00:10:00,240 --> 00:10:00,400 Speaker 1: Right? 198 00:10:00,520 --> 00:10:02,800 Speaker 3: So we put all that together and we have a 199 00:10:02,840 --> 00:10:06,400 Speaker 3: cost function. With the cost function says, okay, how can 200 00:10:06,440 --> 00:10:08,920 Speaker 3: I shrink the robot as much as possible while still 201 00:10:08,960 --> 00:10:12,960 Speaker 3: satisfying the load bearing constraints? And so putting those all together, 202 00:10:13,280 --> 00:10:15,800 Speaker 3: the actual wheels of the drive base occupy around a 203 00:10:15,840 --> 00:10:18,040 Speaker 3: ten inch square and then we have two sort of 204 00:10:18,040 --> 00:10:22,080 Speaker 3: outriggers like almost antennae, so we can get a little 205 00:10:22,120 --> 00:10:25,360 Speaker 3: bit more stability. And so the footprint of the robot, 206 00:10:26,520 --> 00:10:29,959 Speaker 3: I think it's around the base itself is around fifteen 207 00:10:30,000 --> 00:10:33,440 Speaker 3: inches by fifteen inches, not including the outriggers. Wow, with 208 00:10:33,520 --> 00:10:35,319 Speaker 3: the outriggers, it's a little bit bigger. I think they're 209 00:10:35,320 --> 00:10:38,720 Speaker 3: around twenty inches wide. But your average doorways are somewhere 210 00:10:38,800 --> 00:10:41,000 Speaker 3: between twenty eight to thirty six inches, so we still 211 00:10:41,040 --> 00:10:43,120 Speaker 3: got plenty of space around the door. 212 00:10:43,679 --> 00:10:44,439 Speaker 1: That's amazing. 213 00:10:44,559 --> 00:10:47,240 Speaker 2: And you know, I know that this is designed for 214 00:10:47,600 --> 00:10:49,720 Speaker 2: elderly folks that need help around the house, but I 215 00:10:49,760 --> 00:10:53,000 Speaker 2: can already imagine this helping a lot of people who 216 00:10:53,120 --> 00:10:57,440 Speaker 2: are differently abled from the disabled community. And did you 217 00:10:57,600 --> 00:10:59,880 Speaker 2: consider that as you were designing? Is that something that 218 00:11:00,040 --> 00:11:03,240 Speaker 2: also came into your mind as another use for ebar? 219 00:11:04,800 --> 00:11:07,480 Speaker 3: Sort of, So we did think about using it for 220 00:11:07,520 --> 00:11:11,800 Speaker 3: Parkinson's patients because they sometimes just have a struggle maintaining 221 00:11:11,800 --> 00:11:14,240 Speaker 3: their balance, But I think absolutely it could be applied 222 00:11:14,240 --> 00:11:17,880 Speaker 3: towards different populations all be honest, we specifically designed it 223 00:11:17,920 --> 00:11:21,600 Speaker 3: for elderly persons, but I think you know, there are 224 00:11:21,640 --> 00:11:24,400 Speaker 3: certainly other people who could benefit from the robot. 225 00:11:24,880 --> 00:11:28,000 Speaker 1: Absolutely. I think that's such a good point that TT's 226 00:11:28,040 --> 00:11:31,200 Speaker 1: talked about before in engineering and design. We've talked about 227 00:11:31,200 --> 00:11:35,320 Speaker 1: it in just inclusivity across the board in anything that 228 00:11:35,360 --> 00:11:37,360 Speaker 1: you create. You know, the more you think about who 229 00:11:37,440 --> 00:11:39,640 Speaker 1: this can help, the more people benefit from it, even 230 00:11:39,679 --> 00:11:42,720 Speaker 1: people you didn't consider. I want to know about how 231 00:11:42,800 --> 00:11:47,440 Speaker 1: you're these different types of assistance that ebar provides, because 232 00:11:47,880 --> 00:11:50,160 Speaker 1: it's not just that you have to fall in. Because 233 00:11:50,200 --> 00:11:51,520 Speaker 1: of the shape of it and because of how you 234 00:11:51,640 --> 00:11:54,640 Speaker 1: designed it, it seems like it can do more than 235 00:11:54,840 --> 00:11:57,400 Speaker 1: just like wait until you're at the ground and needing 236 00:11:57,440 --> 00:11:59,720 Speaker 1: to be lifted, right, like ebar can come in ahead 237 00:11:59,760 --> 00:12:01,839 Speaker 1: of time. Yeah, I'd love to hear you talk a 238 00:12:01,840 --> 00:12:05,040 Speaker 1: little bit more about the different falls you anticipate it, 239 00:12:05,160 --> 00:12:07,520 Speaker 1: or the different types of knees you anticipated, and how 240 00:12:07,559 --> 00:12:10,319 Speaker 1: you build all those things together into this system. 241 00:12:10,760 --> 00:12:13,560 Speaker 3: Yeah. For sure. Our goal was to catch a person 242 00:12:13,600 --> 00:12:17,480 Speaker 3: before they fell, because when they're on the ground, oftentimes 243 00:12:17,520 --> 00:12:20,520 Speaker 3: they may be unconscious, they may have passed out, and 244 00:12:20,559 --> 00:12:22,480 Speaker 3: it's kind of a bad situation to be and if 245 00:12:22,480 --> 00:12:24,960 Speaker 3: the person's already on the ground, right, So you're thinking 246 00:12:25,000 --> 00:12:26,360 Speaker 3: of how to do it, and we came up with 247 00:12:26,640 --> 00:12:29,319 Speaker 3: the idea of using airbags because they're soft, you can 248 00:12:29,360 --> 00:12:33,960 Speaker 3: have like a large contact area. And the question is, 249 00:12:34,000 --> 00:12:38,440 Speaker 3: like is it physically possible. So a previous student in 250 00:12:38,440 --> 00:12:42,320 Speaker 3: my lab has worked on like fall prediction and she 251 00:12:42,480 --> 00:12:44,839 Speaker 3: found that you can predict a fall up to two 252 00:12:44,880 --> 00:12:49,360 Speaker 3: hundred fifty milliseconds before the person actually starts to fall down. Wow, 253 00:12:49,920 --> 00:12:52,560 Speaker 3: And that's why using like a waste mounted sensor called 254 00:12:52,559 --> 00:12:55,160 Speaker 3: an im you. So we said, okay, two fifty milliseconds, 255 00:12:55,200 --> 00:12:57,880 Speaker 3: that's our target inflation time. Can we like fully inflate 256 00:12:57,880 --> 00:13:01,520 Speaker 3: the airbags and catch a person right before they so then, yeah, 257 00:13:01,520 --> 00:13:05,000 Speaker 3: we tried different shapes and sizes and configurations of airbags. 258 00:13:05,520 --> 00:13:08,679 Speaker 3: I tested a lot on myself, you see, like how 259 00:13:09,000 --> 00:13:11,640 Speaker 3: how much can I inflate them before it becomes painful? 260 00:13:11,880 --> 00:13:13,880 Speaker 3: And then we looked at studies of like skin bruising 261 00:13:13,880 --> 00:13:16,440 Speaker 3: because you know, we know that elderly people's skin are 262 00:13:16,520 --> 00:13:19,320 Speaker 3: kind of sensitive, so we didn't want to cause them 263 00:13:19,320 --> 00:13:21,960 Speaker 3: any danger or put them in risk of bruising their skin. 264 00:13:23,040 --> 00:13:25,960 Speaker 3: And we settled with a configuration of four airbacks. There's 265 00:13:25,960 --> 00:13:28,160 Speaker 3: two big ones on the side and then two smaller 266 00:13:28,200 --> 00:13:30,920 Speaker 3: ones on the front like columns, so when they inflate, 267 00:13:31,200 --> 00:13:33,560 Speaker 3: they sort of push the person back into the robot. 268 00:13:34,280 --> 00:13:37,200 Speaker 3: And then we developed a rapid like two stage inflation 269 00:13:37,280 --> 00:13:40,040 Speaker 3: system that can inflate them within two hundred and fifty milliseconds, 270 00:13:40,960 --> 00:13:44,040 Speaker 3: so if you're walking, you know, right now. Again, it's 271 00:13:44,080 --> 00:13:45,920 Speaker 3: all done manually, but we have done work in our 272 00:13:46,000 --> 00:13:49,000 Speaker 3: lab about like detecting falls, just haven't implemented it on 273 00:13:49,000 --> 00:13:51,360 Speaker 3: the robot yet. The idea is, if you begin to fall, 274 00:13:51,400 --> 00:13:54,520 Speaker 3: the airbags which just rapidly inflate and gravy and sort 275 00:13:54,520 --> 00:13:56,720 Speaker 3: of hold on to you, and so you're kind of 276 00:13:56,760 --> 00:13:58,560 Speaker 3: frozen in this position, but you have a chance to 277 00:13:58,600 --> 00:14:01,199 Speaker 3: regain your balance, or we can deflate the airbags and 278 00:14:01,240 --> 00:14:03,839 Speaker 3: you can continue normally, or we can just hold you, 279 00:14:03,840 --> 00:14:05,840 Speaker 3: you know, until someone can come to help. 280 00:14:20,960 --> 00:14:23,720 Speaker 2: And so the next part of the engineering is to 281 00:14:23,920 --> 00:14:26,720 Speaker 2: you know, test it out on the users. I'm wondering, 282 00:14:27,240 --> 00:14:30,080 Speaker 2: you know, one, I think it'll be interesting to hear 283 00:14:30,240 --> 00:14:33,240 Speaker 2: like how you get volunteers for this or who you 284 00:14:33,320 --> 00:14:36,480 Speaker 2: recruit to test these things out, and then also what 285 00:14:36,560 --> 00:14:39,960 Speaker 2: their feedback was and how that informs like how you 286 00:14:40,000 --> 00:14:42,080 Speaker 2: move forward and any changes that you might make. 287 00:14:42,400 --> 00:14:44,720 Speaker 3: The major thing we have to make sure before we 288 00:14:44,880 --> 00:14:48,360 Speaker 3: can roll actual elderly persons that it's completely safe because 289 00:14:48,400 --> 00:14:51,200 Speaker 3: we don't want to cause anyone any injury. So right 290 00:14:51,240 --> 00:14:55,520 Speaker 3: now we've been testing in healthy volunteers. By healthy volunteers, 291 00:14:55,560 --> 00:14:58,800 Speaker 3: I mean myself and a couple of my web mates. Okay, 292 00:14:58,880 --> 00:15:02,320 Speaker 3: but yeah, the idea is to refine the system to 293 00:15:02,720 --> 00:15:04,840 Speaker 3: make sure it's safe, to you know, sort of measure 294 00:15:04,880 --> 00:15:07,920 Speaker 3: the forces which we have been and so far everything's good. 295 00:15:08,240 --> 00:15:10,800 Speaker 3: Then we can apply for approval from our university and 296 00:15:10,840 --> 00:15:12,840 Speaker 3: then start enrolding elderly persons. 297 00:15:12,960 --> 00:15:17,040 Speaker 1: Okay, this sounds really cool because you've called EBAR a 298 00:15:17,080 --> 00:15:20,960 Speaker 1: step towards aging in place. And I am thinking back 299 00:15:21,000 --> 00:15:24,520 Speaker 1: to those commercials where people were like life alert and 300 00:15:24,520 --> 00:15:27,320 Speaker 1: they were waiting until they already fail. And like you said, 301 00:15:27,440 --> 00:15:30,240 Speaker 1: after you've once you hit the ground, anything could happen. 302 00:15:30,280 --> 00:15:33,160 Speaker 1: You could be unconscious. But like I think about what 303 00:15:33,200 --> 00:15:37,240 Speaker 1: this could mean. Something you mentioned is how maybe stressed 304 00:15:37,320 --> 00:15:40,600 Speaker 1: our healthcare system is for aging adults. Yes, we're talking 305 00:15:40,600 --> 00:15:43,120 Speaker 1: about this in the home, but could you imagine this 306 00:15:43,240 --> 00:15:46,600 Speaker 1: type of tech in other places like care facilities or 307 00:15:46,640 --> 00:15:50,640 Speaker 1: as part of public programs. How do you imagine this tech? 308 00:15:50,760 --> 00:15:53,120 Speaker 1: You know, I know we're looking much further ahead, but 309 00:15:53,120 --> 00:15:54,400 Speaker 1: how do you imagine it scaling? 310 00:15:54,640 --> 00:15:57,800 Speaker 3: I think for me personally, i'd say, like, I think 311 00:15:57,840 --> 00:16:00,920 Speaker 3: the gold standard is a human being. It's very difficult 312 00:16:00,960 --> 00:16:03,200 Speaker 3: for robot to replace a human, right. I think We've 313 00:16:03,200 --> 00:16:06,120 Speaker 3: seen this again and again. But the reality is that 314 00:16:06,400 --> 00:16:08,680 Speaker 3: if there is a care shortage, I think it's better 315 00:16:08,720 --> 00:16:12,200 Speaker 3: to like augment the shortage with robots than just to 316 00:16:12,280 --> 00:16:14,840 Speaker 3: not be able to do anything about it. So one 317 00:16:14,840 --> 00:16:17,400 Speaker 3: thing we were thinking is like in nursing homes, ebar 318 00:16:17,520 --> 00:16:20,320 Speaker 3: could sort of handle some of the easier tasks. If 319 00:16:20,320 --> 00:16:22,960 Speaker 3: a person just needs to walk, for example, to a sink, 320 00:16:23,040 --> 00:16:26,120 Speaker 3: then ebar could help them out. But very complex tasks 321 00:16:26,200 --> 00:16:28,720 Speaker 3: like lifting a person into a bathtub with a sling 322 00:16:29,200 --> 00:16:32,400 Speaker 3: like those can still be done by the caretakers, so 323 00:16:32,480 --> 00:16:34,280 Speaker 3: it can sort of free them up. That instead of 324 00:16:34,320 --> 00:16:36,440 Speaker 3: elderly persons having to wait a long time for care 325 00:16:36,880 --> 00:16:39,120 Speaker 3: that if for some tasks we could send the robot 326 00:16:39,200 --> 00:16:42,360 Speaker 3: and for some tasks we could send a human caretaker. 327 00:16:43,200 --> 00:16:45,840 Speaker 2: I love that because Menzakia talk about this all the 328 00:16:45,880 --> 00:16:49,320 Speaker 2: time where a lot of solutions to the world's problems 329 00:16:49,360 --> 00:16:54,240 Speaker 2: is not an or response like this or that. It's 330 00:16:54,240 --> 00:16:57,200 Speaker 2: an and so not to say, oh, Ebar is going 331 00:16:57,240 --> 00:17:01,240 Speaker 2: to replace all caregivers, there won't be a need for 332 00:17:01,240 --> 00:17:03,120 Speaker 2: a human. It's like, no, you can have the human 333 00:17:03,240 --> 00:17:05,520 Speaker 2: and you can have e bar, which to supplement and 334 00:17:05,520 --> 00:17:10,280 Speaker 2: it makes it an even better experience. I'm curious about, 335 00:17:10,440 --> 00:17:13,320 Speaker 2: you know, what are the next steps with ebar. Are 336 00:17:13,320 --> 00:17:19,480 Speaker 2: there any like upgrades or advancements that you want to 337 00:17:19,480 --> 00:17:23,160 Speaker 2: add to EBAR, or what's the vision or are there 338 00:17:23,200 --> 00:17:25,479 Speaker 2: things that you want to do outside of e bar 339 00:17:25,640 --> 00:17:27,679 Speaker 2: to also help supplement EBAR. 340 00:17:28,600 --> 00:17:32,600 Speaker 3: Yeah, that's a great question. Honestly, it's discussion my advisor 341 00:17:32,960 --> 00:17:38,960 Speaker 3: had with me almost immediately after I submitted the paper. Yeah. 342 00:17:39,240 --> 00:17:42,400 Speaker 3: I think certainly there's room for making the robots smaller 343 00:17:42,400 --> 00:17:45,320 Speaker 3: and more compact. I've talked with a lot of people, 344 00:17:45,359 --> 00:17:47,439 Speaker 3: even my parents are saying like, hey, you should add 345 00:17:47,840 --> 00:17:49,840 Speaker 3: something that can pick up a person's phone if it 346 00:17:49,880 --> 00:17:52,960 Speaker 3: falls down, like a sort of a coup holder on 347 00:17:53,000 --> 00:17:55,560 Speaker 3: the robot. I said, well, that's great. I'd love to 348 00:17:55,600 --> 00:17:57,520 Speaker 3: do that, but I don't know if I can really 349 00:17:57,560 --> 00:18:03,760 Speaker 3: put that in my thesis work. So one of the 350 00:18:03,760 --> 00:18:06,960 Speaker 3: other things our lab is looked into is handlebar optimization. 351 00:18:07,480 --> 00:18:08,800 Speaker 3: Like if you think about it, when you go into 352 00:18:08,880 --> 00:18:12,280 Speaker 3: restrooms or some public places, you see handlebars on the walls. 353 00:18:12,720 --> 00:18:14,679 Speaker 3: It turns out there's not really been a lot of 354 00:18:14,720 --> 00:18:18,080 Speaker 3: work that's been done on like is this the biomechanically 355 00:18:18,080 --> 00:18:22,200 Speaker 3: optimal location for handlebar? And because like you know, who knows, 356 00:18:22,240 --> 00:18:23,600 Speaker 3: it could be in front of you, it could be 357 00:18:23,720 --> 00:18:26,919 Speaker 3: like up here, it could be like down there. So 358 00:18:26,960 --> 00:18:28,800 Speaker 3: we were trying to look into, like can we make 359 00:18:28,840 --> 00:18:31,600 Speaker 3: a model of a person and then predict like where 360 00:18:31,680 --> 00:18:35,080 Speaker 3: is the optimal place for handlebar it maybe reduces the 361 00:18:35,160 --> 00:18:38,160 Speaker 3: muscle strength the most or provides the most support. So 362 00:18:38,400 --> 00:18:40,320 Speaker 3: that sort of stuff I think is interesting and I 363 00:18:40,320 --> 00:18:42,719 Speaker 3: think could compliment a robot like e bar because then 364 00:18:42,760 --> 00:18:45,440 Speaker 3: it helps us nowhere to position the U shaped fork 365 00:18:45,720 --> 00:18:48,520 Speaker 3: based on the posture of the person. So yeah, that's 366 00:18:48,680 --> 00:18:50,480 Speaker 3: I guess that sort of work that we've been looking 367 00:18:50,680 --> 00:18:52,560 Speaker 3: to and thinking about pursuing in the future. 368 00:18:52,720 --> 00:18:54,920 Speaker 1: Okay, I think this is so cool. 369 00:18:55,880 --> 00:18:56,280 Speaker 3: Things. 370 00:18:56,600 --> 00:19:01,000 Speaker 1: You know, this is totally outside my comfort zone of science. 371 00:19:01,359 --> 00:19:03,720 Speaker 1: TT understands this kind of stuff way better than me, 372 00:19:04,359 --> 00:19:06,680 Speaker 1: which is why she has such great questions, is there 373 00:19:06,680 --> 00:19:09,359 Speaker 1: anything else here seeing in the field of robotics and 374 00:19:09,400 --> 00:19:11,639 Speaker 1: elder care? Is there anything else you're excited about this 375 00:19:11,720 --> 00:19:14,840 Speaker 1: in the research pipeline, even if it's not in your lab, 376 00:19:14,920 --> 00:19:18,720 Speaker 1: like with other labs that do great work that you see, Ye, 377 00:19:18,720 --> 00:19:19,680 Speaker 1: that feels promising. 378 00:19:20,119 --> 00:19:24,320 Speaker 3: So we are collaborating with So just full disclosure. But 379 00:19:24,400 --> 00:19:27,960 Speaker 3: at Stanford, Alison O Kumurro, she did a lot of 380 00:19:28,040 --> 00:19:30,760 Speaker 3: work on these things called vine robots. They're sort of 381 00:19:30,800 --> 00:19:33,679 Speaker 3: like flexible tubes. They can inflate and they can go 382 00:19:33,880 --> 00:19:37,600 Speaker 3: under a person. And so we have this idea. It's like, 383 00:19:37,640 --> 00:19:40,520 Speaker 3: wait a second, you have an elderly person lying in 384 00:19:40,560 --> 00:19:43,320 Speaker 3: bed and you want to like put them in a sling, 385 00:19:43,440 --> 00:19:45,000 Speaker 3: Like right now, you've got to lift them up and 386 00:19:45,080 --> 00:19:47,560 Speaker 3: pull a slip. What if the sling just like inflated 387 00:19:47,720 --> 00:19:51,600 Speaker 3: under them, like and then you could just pick them 388 00:19:51,680 --> 00:19:54,680 Speaker 3: up that way. So that work I think we've been 389 00:19:54,680 --> 00:19:57,000 Speaker 3: doing with her. But she was the one who's been 390 00:19:57,040 --> 00:20:00,080 Speaker 3: working on vine robots. I think that's really cool. In 391 00:20:00,160 --> 00:20:03,200 Speaker 3: terms of other labs and other research, we see a 392 00:20:03,200 --> 00:20:06,280 Speaker 3: lot of work with humanoids. Humanoid robot seems to be 393 00:20:06,320 --> 00:20:08,480 Speaker 3: like the next big thing. There's a bunch of companies 394 00:20:08,480 --> 00:20:11,639 Speaker 3: pursuing humanoids, and so people have started looking into like 395 00:20:11,840 --> 00:20:14,639 Speaker 3: using a humanoid for sit to stand assistance, which I 396 00:20:14,640 --> 00:20:17,720 Speaker 3: think is pretty cool. My concern with it is just, 397 00:20:18,040 --> 00:20:20,520 Speaker 3: especially if the robot has two feet, it's not going 398 00:20:20,600 --> 00:20:22,919 Speaker 3: to be a stable as something that has like a heavy, 399 00:20:23,680 --> 00:20:26,399 Speaker 3: big drive base. You know, like if the robot and 400 00:20:26,440 --> 00:20:30,439 Speaker 3: the person fall down, then that's really bad. But I 401 00:20:30,440 --> 00:20:32,560 Speaker 3: think it's great work though. I think that that should 402 00:20:32,600 --> 00:20:35,280 Speaker 3: be explored. And I saw a couple of papers when 403 00:20:35,280 --> 00:20:37,600 Speaker 3: I was at akra Acra is a big robotics conference 404 00:20:37,600 --> 00:20:40,400 Speaker 3: that happens each year. It's sort of like v big 405 00:20:40,920 --> 00:20:43,800 Speaker 3: robotics conference, and so I saw a couple of papers 406 00:20:43,800 --> 00:20:46,520 Speaker 3: where people are looking at using humanoids to like provide 407 00:20:46,560 --> 00:20:48,480 Speaker 3: sit to stand assistance, and I thought that was really cool. 408 00:20:48,800 --> 00:20:52,200 Speaker 2: Yeah, I was thinking about this the other day because 409 00:20:52,800 --> 00:20:56,840 Speaker 2: I've also been noticing a lot of the humanoid innovation 410 00:20:57,200 --> 00:21:01,159 Speaker 2: and how it's like, you know, as engineers, we try 411 00:21:01,200 --> 00:21:05,840 Speaker 2: and create things that are not just flashy but useful, 412 00:21:05,920 --> 00:21:11,240 Speaker 2: and it doesn't really seem intuitive to me to say, 413 00:21:11,680 --> 00:21:14,639 Speaker 2: this human is not able to form this task, so 414 00:21:14,720 --> 00:21:16,800 Speaker 2: I'm going to replace it with another human but I 415 00:21:16,840 --> 00:21:20,120 Speaker 2: think people are just so enamored by humanoids. 416 00:21:20,440 --> 00:21:24,639 Speaker 1: I'm not. As a non engineering person, I feel like, 417 00:21:25,080 --> 00:21:27,359 Speaker 1: give me the e bar. If I knew I was 418 00:21:27,400 --> 00:21:29,560 Speaker 1: falling back into a face, I don't think I would 419 00:21:29,600 --> 00:21:33,840 Speaker 1: like this, you know, And so I think it's interesting, 420 00:21:33,880 --> 00:21:37,040 Speaker 1: Like I feel like that humanoid component is what makes 421 00:21:37,080 --> 00:21:39,000 Speaker 1: people feel like, oh, you're trying to replace me, or 422 00:21:39,040 --> 00:21:42,520 Speaker 1: oh that's my own bias that I think. If it's 423 00:21:42,560 --> 00:21:44,920 Speaker 1: hard already for a person to help you, why would 424 00:21:44,960 --> 00:21:46,840 Speaker 1: I put it in something else that's person shaped to 425 00:21:46,920 --> 00:21:48,479 Speaker 1: do the same work so it can be just as 426 00:21:48,480 --> 00:21:49,000 Speaker 1: hard for it. 427 00:21:49,520 --> 00:21:55,640 Speaker 2: Yeah, make that inflatable sling, Like, I love that idea. 428 00:21:55,720 --> 00:22:01,560 Speaker 1: I think it's great. 429 00:22:09,920 --> 00:22:12,919 Speaker 2: My last question is just about the process, because we 430 00:22:13,080 --> 00:22:16,760 Speaker 2: just did an episode on the research funding cuts and 431 00:22:16,760 --> 00:22:18,960 Speaker 2: stuff like that. I really would love for you to 432 00:22:19,080 --> 00:22:22,679 Speaker 2: highlight like what it takes one to get to this 433 00:22:22,800 --> 00:22:26,119 Speaker 2: point with EBAR and then to have EBAR kind of 434 00:22:26,160 --> 00:22:29,600 Speaker 2: like break into the healthcare system, if you know, because 435 00:22:29,600 --> 00:22:31,600 Speaker 2: I think that one thing that the Kia said is 436 00:22:31,640 --> 00:22:35,240 Speaker 2: that folks they don't think about research in the way 437 00:22:35,240 --> 00:22:37,720 Speaker 2: that they should. They think about innovation. So when the 438 00:22:37,760 --> 00:22:41,400 Speaker 2: product is there and in their hand, they're like, ah, research, 439 00:22:41,440 --> 00:22:44,080 Speaker 2: and it's like, no, that's innovation. There's a lot of 440 00:22:44,119 --> 00:22:46,359 Speaker 2: research that gets you to that point. So can you 441 00:22:46,480 --> 00:22:48,720 Speaker 2: talk about that process for yourself. I think it would 442 00:22:48,720 --> 00:22:50,960 Speaker 2: be great for people to here to understand what it 443 00:22:51,000 --> 00:22:52,280 Speaker 2: takes to do something like this. 444 00:22:52,840 --> 00:22:55,040 Speaker 3: I took product design. It was a class at MIT 445 00:22:55,160 --> 00:22:57,800 Speaker 3: a couple of years ago. They presented us with this process. 446 00:22:57,880 --> 00:22:59,960 Speaker 3: I think it's just called like a need driven develop 447 00:23:00,160 --> 00:23:03,439 Speaker 3: and process. But the idea is you start first with 448 00:23:03,880 --> 00:23:06,600 Speaker 3: the stakeholders. You go to the elderly person, you ask 449 00:23:06,680 --> 00:23:09,400 Speaker 3: them like what sort of tasks are you trying to do? 450 00:23:10,160 --> 00:23:12,280 Speaker 3: And then oftentimes what you find is people will tell 451 00:23:12,320 --> 00:23:16,040 Speaker 3: you things, but really there's like underlying needs they're called 452 00:23:16,119 --> 00:23:20,000 Speaker 3: latent needs that they're not really telling you. They can't 453 00:23:20,040 --> 00:23:23,520 Speaker 3: really put into words well, but it becomes obvious as 454 00:23:23,560 --> 00:23:27,320 Speaker 3: you look into more of the of what they're doing. Like, 455 00:23:27,400 --> 00:23:30,320 Speaker 3: for example, an elderly person might say like, oh, you know, 456 00:23:30,400 --> 00:23:32,920 Speaker 3: I really have trouble getting into and out of the bathtub, 457 00:23:33,359 --> 00:23:35,879 Speaker 3: but I want is just like like a cane or 458 00:23:35,920 --> 00:23:38,760 Speaker 3: something that'll help me get in and out. And you're like, well, 459 00:23:39,440 --> 00:23:41,919 Speaker 3: maybe the problem is that the tub is too high. 460 00:23:42,280 --> 00:23:44,639 Speaker 3: Maybe it's the problem that, like, you just need a 461 00:23:44,640 --> 00:23:46,800 Speaker 3: little bit of support, and so it may not be 462 00:23:46,880 --> 00:23:48,600 Speaker 3: a cane that you want. It may be like a 463 00:23:48,680 --> 00:23:51,840 Speaker 3: robot or a handlebar or some other device that can 464 00:23:51,880 --> 00:23:56,439 Speaker 3: also help you. So we start with this stakeholders and 465 00:23:56,480 --> 00:23:59,120 Speaker 3: looking at the latent needs and then in our case, 466 00:23:59,240 --> 00:24:01,960 Speaker 3: we develop this sign concept for robot and we went 467 00:24:02,000 --> 00:24:05,600 Speaker 3: to a physical therapist that's Spaulding Rehabilitatian Hospital. We did 468 00:24:05,600 --> 00:24:09,320 Speaker 3: a presentation and they said, oh, we like these aspects 469 00:24:09,320 --> 00:24:11,359 Speaker 3: of it, but we think these aspects wouldn't work with 470 00:24:11,400 --> 00:24:13,800 Speaker 3: the patients that we work with. So then we sort 471 00:24:13,800 --> 00:24:15,679 Speaker 3: of go back and forth a couple of times, rEFInd 472 00:24:15,720 --> 00:24:19,040 Speaker 3: the design, and then from there on it's the most 473 00:24:19,080 --> 00:24:21,040 Speaker 3: fun part for me. I get to build a prototype. 474 00:24:21,600 --> 00:24:24,760 Speaker 1: I think that's interesting because that's such a long process 475 00:24:24,960 --> 00:24:28,120 Speaker 1: and the only research you're highlighting is the new research 476 00:24:28,200 --> 00:24:31,320 Speaker 1: that you're doing. But you've already told us that even 477 00:24:31,359 --> 00:24:34,760 Speaker 1: in your prototype, to determine how much force a person 478 00:24:34,840 --> 00:24:37,440 Speaker 1: might use, you're going back to research from forty years 479 00:24:37,440 --> 00:24:41,480 Speaker 1: ago to the nineteen eighties, right, and so research that 480 00:24:41,520 --> 00:24:43,359 Speaker 1: some people may say, why does the army need to 481 00:24:43,400 --> 00:24:45,119 Speaker 1: do this, or why does the military need to figure 482 00:24:45,119 --> 00:24:48,399 Speaker 1: out how much force a person exerts laterally, because in 483 00:24:48,520 --> 00:24:52,840 Speaker 1: forty years, a graduate student is going to be figuring 484 00:24:52,880 --> 00:24:54,879 Speaker 1: out how to design a robot that can keep your 485 00:24:54,920 --> 00:24:58,280 Speaker 1: grandmother from falling when she reaches for something. And I 486 00:24:58,359 --> 00:25:02,560 Speaker 1: just think those are the connections between research and innovation 487 00:25:03,040 --> 00:25:06,760 Speaker 1: that we don't highlight enough. You're relying on research that 488 00:25:06,760 --> 00:25:10,520 Speaker 1: has already been done to help you iterate and innovate 489 00:25:10,800 --> 00:25:14,520 Speaker 1: really quickly to decide what the drive based size should be. 490 00:25:14,560 --> 00:25:17,399 Speaker 1: And I think it's just such a good demonstration of 491 00:25:17,520 --> 00:25:21,800 Speaker 1: research and innovation how closely those two rely on each other. 492 00:25:22,200 --> 00:25:25,560 Speaker 3: For sure, for sure, And there are so many times when, like, like, 493 00:25:25,600 --> 00:25:27,960 Speaker 3: one of the critical things that we've needed was you 494 00:25:28,040 --> 00:25:30,440 Speaker 3: needed to know the friction between a person's skin and 495 00:25:30,480 --> 00:25:33,920 Speaker 3: their clothes. There's a sony in twenty thirteen that characterizes 496 00:25:34,080 --> 00:25:36,600 Speaker 3: so thank you so much. You know, it's such an 497 00:25:36,600 --> 00:25:38,879 Speaker 3: obscure piece of knowledge. You think, like, when would you 498 00:25:38,920 --> 00:25:41,680 Speaker 3: ever need that? But it turns out we need to know, like, well, 499 00:25:41,760 --> 00:25:43,680 Speaker 3: the closes slip on the skin if we can press 500 00:25:43,720 --> 00:25:47,240 Speaker 3: them with airbags. So this random research study ended up 501 00:25:47,280 --> 00:25:50,560 Speaker 3: being extremely useful because we can quantify now the friction. 502 00:25:51,280 --> 00:25:54,880 Speaker 3: So yeah, there's a ton of these connections between prior research, 503 00:25:55,040 --> 00:25:57,440 Speaker 3: some of it not even remotely related to elder care. 504 00:25:58,040 --> 00:25:59,960 Speaker 3: But you know, it's like we're standing on the show 505 00:26:00,359 --> 00:26:03,920 Speaker 3: of giants. Yes, all this knowledge gets built up, and 506 00:26:03,960 --> 00:26:05,800 Speaker 3: you may not think it's useful in the moment, but 507 00:26:05,840 --> 00:26:08,160 Speaker 3: then twenty years down the road someone needs it. It's 508 00:26:08,200 --> 00:26:10,440 Speaker 3: like the exact thing that they need exactly. 509 00:26:10,680 --> 00:26:12,719 Speaker 2: And that's another thing that we always say is that 510 00:26:12,840 --> 00:26:16,639 Speaker 2: science never stops. And that is a really good illustration 511 00:26:16,760 --> 00:26:20,480 Speaker 2: of that, where you know, just because that part of 512 00:26:20,560 --> 00:26:27,159 Speaker 2: research ended or that paper was published, doesn't mean that 513 00:26:27,240 --> 00:26:29,080 Speaker 2: it'll never be used again. It doesn't mean that it 514 00:26:29,119 --> 00:26:32,159 Speaker 2: won't be useful. It doesn't mean that you can't build 515 00:26:32,240 --> 00:26:35,359 Speaker 2: off of that. And so like science never never stops, 516 00:26:35,400 --> 00:26:38,840 Speaker 2: someone will be citing your paper one hundred years from now, 517 00:26:38,880 --> 00:26:43,120 Speaker 2: I'm sure and saying, wow, look what we were able 518 00:26:43,119 --> 00:26:46,360 Speaker 2: to do based on what Roberto and his lab group 519 00:26:46,400 --> 00:26:48,640 Speaker 2: were able to do, and now we can innovate off 520 00:26:48,680 --> 00:26:51,119 Speaker 2: of that. The science never stops, and the work that 521 00:26:51,160 --> 00:26:54,800 Speaker 2: we do is really important, even if it feels obscure. 522 00:26:54,880 --> 00:26:58,879 Speaker 2: Sometimes I think about my graduate, my dissertation work, and 523 00:26:58,920 --> 00:27:01,760 Speaker 2: I'm like, oh, oh god, no one needs this. It 524 00:27:01,800 --> 00:27:04,040 Speaker 2: was in nano materials. And then I'll go and look 525 00:27:04,080 --> 00:27:06,360 Speaker 2: at some of my old papers. I'm like, wow, cited 526 00:27:06,440 --> 00:27:11,000 Speaker 2: eighty times. Okay, that's not bad, that's excellent. 527 00:27:12,680 --> 00:27:16,280 Speaker 3: Yeah. No, it's cool to see you. Everything fits together, 528 00:27:16,359 --> 00:27:18,119 Speaker 3: and honestly, I think we're going to see more and 529 00:27:18,160 --> 00:27:18,680 Speaker 3: more on that. 530 00:27:19,080 --> 00:27:22,800 Speaker 2: Congratulations on all of your success. We will be tapping 531 00:27:22,840 --> 00:27:26,320 Speaker 2: into mix to see how Ebar is evolving and your 532 00:27:26,359 --> 00:27:30,320 Speaker 2: success as your career continues to grow and change. You're 533 00:27:30,320 --> 00:27:32,720 Speaker 2: doing a great job and doing a lot of really 534 00:27:32,720 --> 00:27:36,040 Speaker 2: important work. So congratulations, Well, thank you so much. 535 00:27:36,160 --> 00:27:38,800 Speaker 3: I'm honestly, I'm just so grateful to have the opportunity, 536 00:27:38,960 --> 00:27:41,200 Speaker 3: you know, to be a graduate student and to study 537 00:27:41,240 --> 00:27:44,360 Speaker 3: all of this. I'm you know, I'm always very grateful 538 00:27:44,400 --> 00:27:44,720 Speaker 3: for that. 539 00:27:45,160 --> 00:27:46,560 Speaker 1: So amazing. 540 00:27:46,560 --> 00:27:47,760 Speaker 3: Thank you, guys. I appreciate it. 541 00:27:55,359 --> 00:27:58,200 Speaker 2: You can find us on X and Instagram at Dope 542 00:27:58,320 --> 00:27:59,920 Speaker 2: Labs podcast. 543 00:28:00,000 --> 00:28:02,520 Speaker 1: He is on X and Instagram at d R Underscore 544 00:28:02,600 --> 00:28:03,760 Speaker 1: t Sho. 545 00:28:03,640 --> 00:28:06,240 Speaker 2: And you can find Zakiya at z said So. 546 00:28:06,680 --> 00:28:08,919 Speaker 1: Dope Labs is a production of Lamanada Media. 547 00:28:09,160 --> 00:28:13,800 Speaker 2: Our senior supervising producer is Kristin Lapour. And Our Associate 548 00:28:13,840 --> 00:28:16,000 Speaker 2: producer is Issara Savez. 549 00:28:16,640 --> 00:28:20,320 Speaker 1: Dope Labs is sound design, edited and mixed by James Barber. 550 00:28:21,040 --> 00:28:25,200 Speaker 1: Lamanada Media's Vice President of Partnerships and Production is Jackie Danziger. 551 00:28:25,880 --> 00:28:30,040 Speaker 1: Executive producer from iHeart Podcast is Katrina Norvil. Marketing lead 552 00:28:30,240 --> 00:28:31,080 Speaker 1: is Alison Kanter. 553 00:28:31,840 --> 00:28:36,080 Speaker 2: Original music composed and produced by Taka Yasuzawa and Alex 554 00:28:36,160 --> 00:28:41,200 Speaker 2: sugi Ura, with additional music by Elijah Harvey. Dope Labs 555 00:28:41,240 --> 00:28:44,600 Speaker 2: is executive produced by us T T Show Dia and 556 00:28:44,920 --> 00:28:45,560 Speaker 2: Kia Wattley.