WEBVTT - DARPA Robotics Challenge Results 0:00:00.160 --> 0:00:07.080 Brought to you by Toyota. Let's go places. Welcome to 0:00:07.280 --> 0:00:14.040 Forward Thinking. Hey there, and welcome to Forward Thinking, the 0:00:14.200 --> 0:00:16.439 podcast that looks at the future and says, try to 0:00:16.480 --> 0:00:19.280 be a robot king and settled for a robot boy. 0:00:19.440 --> 0:00:22.400 I'm Jonathan Strickland, I'm Lauren bolck Obam, and our other 0:00:22.440 --> 0:00:25.520 co host, Joe McCormick is not with us today. He's 0:00:25.560 --> 0:00:28.560 perfectly fine. He's on an excellent vacation and we'll be 0:00:28.600 --> 0:00:31.920 back with us soon, but perhaps even on a on 0:00:31.960 --> 0:00:35.400 a on a bogus journey. Thinking of the whole bill 0:00:35.440 --> 0:00:40.400 and ted that I caught it. So today we're talking 0:00:40.440 --> 0:00:44.280 about robots. Yes, we are sorry. That was so awkward. 0:00:45.760 --> 0:00:48.840 I inject awkwardness wherever I go. Oh me too. It's 0:00:48.880 --> 0:00:51.560 one of the things that I really pride myself on. Um. 0:00:51.680 --> 0:00:55.040 One of the things that robots pride themselves on is 0:00:55.520 --> 0:00:59.680 being in affiliation with dart Yeah, or at least DARPA 0:00:59.800 --> 0:01:04.840 is prides themselves on their affiliation with robots one or another. Yes, 0:01:05.520 --> 0:01:08.360 So we've done a bunch of episodes about DARPA and 0:01:08.520 --> 0:01:12.560 their connections to robots the past. Um. I mean, we 0:01:12.640 --> 0:01:15.640 mentioned them all the time, but just this May, we 0:01:15.680 --> 0:01:18.000 did a whole episode about how the organization works, end 0:01:18.120 --> 0:01:21.119 of the projects that they're sponsoring right now, and uh 0:01:21.280 --> 0:01:24.080 that that one was called What's Up with DARPA if 0:01:24.120 --> 0:01:26.600 you would like to check it out. And back in November, 0:01:27.800 --> 0:01:30.800 we did an episode about one of their other robot challenges, 0:01:30.880 --> 0:01:35.040 the Grand Challenge, which is an autonomous car obstacle course 0:01:35.080 --> 0:01:37.960 sort of thing, and that one's called robot you Can 0:01:38.080 --> 0:01:42.840 Drive My Car? Yeah, so, uh, and we'll talk more 0:01:42.920 --> 0:01:45.640 a little bit about the Grand Challenge towards the end 0:01:45.640 --> 0:01:50.160 to kind of tie in what the more recent DARPA 0:01:50.280 --> 0:01:52.800 Challenge it was all about, because as of the recording 0:01:52.800 --> 0:01:55.760 of this podcast, we're recording it on June nine, it's 0:01:56.000 --> 0:02:01.480 just after the most recent DARPA Challenge finals concluded. Yes, 0:02:01.680 --> 0:02:05.480 the I mean DARPA, of course, being the Defense Advanced 0:02:05.560 --> 0:02:09.520 Research Projects Agency. I am never going to get used 0:02:09.560 --> 0:02:12.680 to saying that out loud. It's so horrible. That's why. Yes, 0:02:13.000 --> 0:02:18.840 DARPA's Robotics Challenge, or the robo Olympics, as my friend 0:02:18.919 --> 0:02:22.640 Laslow has called it, that's a fitting term. It is 0:02:22.680 --> 0:02:25.519 because because they have to do so much, they do 0:02:25.600 --> 0:02:29.960 they well, so I guess would be an octathlon. Octathlon 0:02:30.600 --> 0:02:35.359 tasks for for walking robots. Yeah, that are beautiful and 0:02:35.440 --> 0:02:39.120 fearsome and fall down so much. Yes, there they are 0:02:39.160 --> 0:02:43.800 glorious and fearsome and vulnerable. It's like a Pixar character. 0:02:45.200 --> 0:02:47.200 They are. They are so So what the challenge is 0:02:47.240 --> 0:02:51.359 the Robotics Challenges is it's a competition for teams from 0:02:51.400 --> 0:02:55.519 around the world to build these savvy, adaptable robots that 0:02:55.560 --> 0:02:59.320 are capable of helping with disaster relief related tasks. It 0:02:59.360 --> 0:03:03.760 was announced and has been since then going through various stages. 0:03:03.840 --> 0:03:07.519 First a virtual challenge to guide a simulated robot through 0:03:07.560 --> 0:03:11.920 three tasks in a virtual environment, and then physical trials 0:03:12.000 --> 0:03:15.280 and now the finals. There were prizes for the finals 0:03:15.480 --> 0:03:18.560 two million for the winner, one million for the first 0:03:18.680 --> 0:03:24.480 runner up, and five hundred thousand for the next runners. Yeah. Yeah, 0:03:24.520 --> 0:03:27.000 so so we're talking some serious money and this is 0:03:27.040 --> 0:03:30.640 typical of DARPA with their challenges, and you could you know, 0:03:30.919 --> 0:03:32.320 that does sound like it's a ton of money, and 0:03:32.360 --> 0:03:34.640 it is, I mean, not to put not to dismiss 0:03:34.639 --> 0:03:36.240 it is a lot of money, but some of these 0:03:36.240 --> 0:03:39.920 teams are investing lots into building these robos. Oh yeah, 0:03:40.000 --> 0:03:42.560 way more than that. Much money. Yeah, So really, the 0:03:42.560 --> 0:03:45.760 the challenge is exactly what it sounds like. It is 0:03:45.800 --> 0:03:51.080 a challenge to engineers to develop machines capable of overcoming 0:03:51.720 --> 0:03:55.600 or performing some sort of task in uh, usually some 0:03:56.320 --> 0:04:00.880 trying circumstances. Yes, right, So, because the whole thing was 0:04:00.920 --> 0:04:05.920 spurred by the Fukushima disaster back in afterwards, a lot 0:04:05.920 --> 0:04:08.440 of officials started realizing that, you know, there are these 0:04:08.480 --> 0:04:13.280 situations in disaster relief which put human lives in danger, 0:04:13.360 --> 0:04:15.720 not just of the victims of the disaster, of course, 0:04:15.800 --> 0:04:19.760 but the but the human responders. Right sure, and you know, 0:04:20.480 --> 0:04:23.880 we live in this incredible future and can make hardy 0:04:24.040 --> 0:04:26.880 robots that can go into places or if we don't 0:04:26.960 --> 0:04:29.839 quite live in that incredible future yet, DARPA was like, hey, 0:04:29.920 --> 0:04:32.320 maybe we should build that incredible future. It sounds like 0:04:32.320 --> 0:04:34.719 a nice place to be. So when did they announce 0:04:34.880 --> 0:04:39.640 this specifically, that was April first, which seems like a 0:04:39.680 --> 0:04:42.440 really bad day to announce things if you ask me. Yeah, 0:04:42.720 --> 0:04:46.919 just imagine if at the conclusion this past weekend, when 0:04:47.400 --> 0:04:50.000 the winning team steps forward and DARPA's like, here's your 0:04:50.000 --> 0:04:54.480 two million psych April fools. Three years later, that would 0:04:54.480 --> 0:04:57.599 be that would be a great April Fools. That's pretty 0:04:57.680 --> 0:05:00.479 epic April Fool's joke. One that didn't not sure that 0:05:00.600 --> 0:05:03.680 Korea has a pro fools and so spoiler alert the 0:05:03.720 --> 0:05:06.480 Korean team one. So I don't know that it would 0:05:06.480 --> 0:05:10.280 have gone over so well. But yeah, so so the 0:05:10.279 --> 0:05:12.960 the This is exactly what you were saying, Lauren. It 0:05:13.000 --> 0:05:17.520 was an attempt to say, here are some situations that 0:05:17.720 --> 0:05:19.880 we might need to have a robot be able to 0:05:19.920 --> 0:05:24.919 respond to. Here are the various scenarios that the robot 0:05:24.960 --> 0:05:27.559 would encounter. Your job is to go out and build 0:05:27.560 --> 0:05:31.560 a robot that can complete these tasks under this scenario, 0:05:32.080 --> 0:05:34.320 or at the very least, to build software for a 0:05:34.400 --> 0:05:36.960 pre existing robot. Right, yes, so you didn't have to 0:05:37.000 --> 0:05:38.920 go out and build a brand new robot from scratch. 0:05:38.960 --> 0:05:43.120 You could design the software, the brains, the programming that 0:05:43.160 --> 0:05:45.520 would allow the robot to complete the tasks. So as 0:05:45.520 --> 0:05:48.440 long as the robots form factor already allowed it to 0:05:48.520 --> 0:05:52.479 do each of the tasks that were assigned, then you know, 0:05:52.560 --> 0:05:55.200 you didn't have to go out and build brand new hardware. Yeah. Yeah, 0:05:55.320 --> 0:05:56.960 nothing from from scratch if you didn't want to. And 0:05:56.960 --> 0:05:59.080 in fact, a lot of the teams have used Boston 0:05:59.160 --> 0:06:02.680 Dynamics at Liss Robot. Boston Dynamics, of course, being the 0:06:03.600 --> 0:06:09.200 uh eccentric company uh that that builds uh robo dogs, 0:06:09.240 --> 0:06:13.080 Big Dog and they and they kick adorable robotic dogs that. 0:06:13.560 --> 0:06:16.400 Oh I just thought about that again and it's still upsets. 0:06:16.520 --> 0:06:20.279 The video left a lasting impression on me. I know, 0:06:20.720 --> 0:06:23.880 I know the robot can't feel anything, right, I don't 0:06:24.080 --> 0:06:28.000 know that. I don't know that, but it's still is 0:06:28.040 --> 0:06:31.120 hard to watch um for me at any rate. So 0:06:31.200 --> 0:06:34.240 let's talk about Let's talk about the stages. You mentioned 0:06:34.279 --> 0:06:36.880 that the first one was a virtual challenge. What was 0:06:36.920 --> 0:06:40.080 that all about? Yeah, so this virtual challenge took place 0:06:40.120 --> 0:06:45.120 back in June, and twenty six teams built software to 0:06:45.160 --> 0:06:50.400 control a virtual Atlas robot through three disaster related tasks 0:06:50.680 --> 0:06:53.919 getting into a vehicle, driving it, and getting out that 0:06:54.040 --> 0:06:56.679 that's a single one, Yeah, which, by the way, sounds 0:06:56.720 --> 0:06:59.560 really basic, but when you think about it, it's natural 0:06:59.600 --> 0:07:02.040 for us, but not natural for a robot. I've also 0:07:02.240 --> 0:07:04.960 I can't do that all the time without like bumping 0:07:05.000 --> 0:07:08.360 my knees and falling down, or I stand up before 0:07:08.400 --> 0:07:11.880 my head is clear of the car, like once a week. Man, 0:07:11.960 --> 0:07:14.800 if you ever wonder why I'm a little bit fuzzy sometimes? 0:07:14.920 --> 0:07:17.080 Do you ever wonder why I'm bleeding from the scalp 0:07:17.520 --> 0:07:20.760 because I don't have hair, So it's just there. That's 0:07:20.920 --> 0:07:22.640 that's why, all right. So so that was the first 0:07:22.680 --> 0:07:25.960 task at then walking through an area of uneven ground 0:07:26.080 --> 0:07:28.840 that had mud and debris to contend with a right 0:07:28.920 --> 0:07:31.280 that the ground didn't have the mudd and debris to 0:07:31.360 --> 0:07:34.600 contend with the robot, yes, um. And then the third 0:07:34.760 --> 0:07:37.800 was attaching a hose to a spigott and turning the 0:07:37.880 --> 0:07:40.800 valve alright, So these are things that it might have 0:07:40.920 --> 0:07:43.800 to do in a response situation, for example, putting out 0:07:43.800 --> 0:07:47.160 a fire in an area that had suffered earthquake damage 0:07:47.280 --> 0:07:50.840 or something. Yeah. To make it a little bit more fun, 0:07:51.040 --> 0:07:54.640 the teams also had to deal with simulated communication lags 0:07:54.680 --> 0:07:58.000 and limits, like like limits to the amount of data 0:07:58.040 --> 0:07:59.920 that they could transfer back and forth to the robot 0:08:00.040 --> 0:08:02.600 and uh a lag time of of maybe like five 0:08:02.800 --> 0:08:05.640 dred milliseconds or something like, which again makes sense because 0:08:05.800 --> 0:08:10.120 in a disaster environment some of the infrastructure has probably 0:08:10.240 --> 0:08:13.600 suffered damage as well, so your ability to communicate could 0:08:13.600 --> 0:08:17.120 be limited. Um. In the end, they were judged on 0:08:17.280 --> 0:08:21.280 how well the simulated robots completed the simulated tasks and 0:08:21.520 --> 0:08:26.160 how much control the operators commanded. And from that UH 0:08:26.480 --> 0:08:30.640 one team team I h m C. That's the Institute 0:08:30.640 --> 0:08:34.080 for Human and Machine Cognition out of PENNSI Colla, Florida 0:08:34.840 --> 0:08:38.320 one and today, along with eight other teams, qualified for 0:08:38.440 --> 0:08:43.400 the trials in December. All right, so that moves us 0:08:43.480 --> 0:08:47.000 on to those trials. Yes, a couple of the pairs 0:08:47.040 --> 0:08:50.120 of teams that made it through merged. In the end, 0:08:50.200 --> 0:08:52.880 six teams went on to compete in the trials. That 0:08:53.080 --> 0:08:58.800 was at Homestead Miami Speedway in Florida on December one, 0:09:00.160 --> 0:09:02.960 and the robots were set eight tasks. They had to 0:09:03.920 --> 0:09:06.440 man a vehicle and I wish that there was a 0:09:06.440 --> 0:09:10.640 better word for that than robot a vehicle, Yeah, that thing. Um. 0:09:10.720 --> 0:09:12.800 They had to navigate uneven terrain. They had to climb 0:09:12.840 --> 0:09:15.720 a ladder, remove debris from a door, and then open 0:09:15.800 --> 0:09:20.120 the door, breakthrough a wall like kool aid Man. They 0:09:20.160 --> 0:09:23.920 did not, however, have to yell oh yeah, I really 0:09:23.920 --> 0:09:27.720 hope that they all did though too, okay, and handle 0:09:27.800 --> 0:09:31.920 some valves and again attached a host with spigott. So 0:09:32.840 --> 0:09:36.760 the winning team was called Shaft sc H A F T, 0:09:37.240 --> 0:09:40.000 which I love. Uh they're they're they're out of Japan 0:09:40.080 --> 0:09:42.880 and they had just been bought by Google prior to 0:09:42.920 --> 0:09:46.600 the trials. Now, wait a minute, I'm sure you're gonna 0:09:46.640 --> 0:09:48.520 get to this, but I don't remember seeing that team 0:09:48.600 --> 0:09:52.640 name when I was looking over the finals. Story about 0:09:52.640 --> 0:09:55.920 that just a moment, Yes, yes, So Shaft really just 0:09:55.920 --> 0:10:00.320 looked robo butt. In these trials, of thirty two possible points, 0:10:00.320 --> 0:10:03.520 they earned twenty seven, which was an entire seven more 0:10:03.600 --> 0:10:06.520 points than even their closest runner up, which was our 0:10:06.520 --> 0:10:10.560 friends I H n C Robotics. Third place, at nine 0:10:10.559 --> 0:10:13.800 points behind Shaft was a team called the Tartan Rescue 0:10:14.040 --> 0:10:17.480 out of Carnegie Melon. Now I've heard about that one. 0:10:18.120 --> 0:10:24.960 So what happened with the Google acquisition of this Japanese company? Uh? Well, 0:10:25.000 --> 0:10:29.520 in June, Google announced that Shaft would be dropping out 0:10:29.520 --> 0:10:32.120 of the finals in order to pursue work on a 0:10:32.160 --> 0:10:36.360 commercial Google project. So, in other words, they said, you 0:10:36.400 --> 0:10:39.920 know this, this research work is fantastic, it's great, but 0:10:40.080 --> 0:10:42.439 we need to dedicate these people to building something that's 0:10:42.480 --> 0:10:46.760 going to become a real world product and not a 0:10:46.760 --> 0:10:50.400 proof of concept kind of tasting out things in a 0:10:50.480 --> 0:10:53.440 scenario environment, and I suspect it also had something to 0:10:53.440 --> 0:10:57.839 do with Google's prior decisions to stay out of military 0:10:57.960 --> 0:11:02.040 related projects, which they have not infrequently said, you know, 0:11:02.120 --> 0:11:04.920 like thanks guys, but no thanks, We're doing good not 0:11:05.200 --> 0:11:07.840 funding military. We've seen we've seen it go the other 0:11:07.880 --> 0:11:10.600 way where people from projects that were part of the 0:11:10.640 --> 0:11:14.800 military ended up at Google later. But that's different. Yes, absolutely, 0:11:14.800 --> 0:11:18.880 so they dropped out in June, and the finals took 0:11:18.920 --> 0:11:21.720 place this past weekend as of when we're recording this 0:11:21.760 --> 0:11:25.559 podcast on June five and six. Yeah, over in California 0:11:26.080 --> 0:11:28.960 that they had a dartbed had a contest as well 0:11:29.080 --> 0:11:33.400 for high school students to create a video explaining what 0:11:33.640 --> 0:11:38.199 they how they felt robots fit into the future of culture, society, 0:11:38.520 --> 0:11:40.760 how they were going to integrate, and how they would 0:11:40.800 --> 0:11:43.200 be an important part of our lives. And the winners 0:11:43.360 --> 0:11:47.520 got to go and witness the finals. So that's kind 0:11:47.520 --> 0:11:50.320 of interesting. There was a big audience there there there 0:11:50.360 --> 0:11:52.560 have been at the past couple I don't I'm not 0:11:52.559 --> 0:11:54.360 sure if there was an audience for the virtual trials, 0:11:54.440 --> 0:12:00.160 but definitely for the preliminary the physical trials. Yeah. Yeah, 0:12:00.200 --> 0:12:02.360 what's interesting also is that if you watch the videos 0:12:02.400 --> 0:12:05.240 from this, I mean that crowd is not shy, they're psyched. 0:12:05.320 --> 0:12:07.719 It's so beautiful. It's like a sporting event. Yeah, it 0:12:07.800 --> 0:12:11.400 really is. And spoiler alert, a lot of these robots 0:12:12.320 --> 0:12:15.520 fell down a lot, and hearing the crowd react to 0:12:15.520 --> 0:12:19.679 the robots falling is heartbreaking. Is they're they're also invested in. 0:12:19.800 --> 0:12:22.760 They're not like laughing at the robots, which honestly I 0:12:22.800 --> 0:12:24.840 tend to do when I'm just sitting on my computer. 0:12:25.520 --> 0:12:28.120 Especially you see, like the animated gifts and like the 0:12:28.120 --> 0:12:30.520 anime gifts make it look hilarious. Like there's a robot 0:12:30.600 --> 0:12:33.120 that it takes a walk, it takes one step forward, 0:12:33.160 --> 0:12:38.120 immediately collapses and and the gift makes it hilarious. But 0:12:38.160 --> 0:12:40.959 you know when you kind of way, yeah, just like 0:12:41.240 --> 0:12:43.400 it's kind of like like, I mean, it's it's that 0:12:43.559 --> 0:12:47.360 ultimate in being taken down a peg right where you're right, 0:12:47.520 --> 0:12:50.959 we're ready to compete, one step falls apart. Like it's 0:12:51.000 --> 0:12:54.200 it's like almost like a national Lampoon vacation kind of moment. 0:12:54.880 --> 0:12:57.400 You figured the Griswolds where the team behind Yeah, yeah, 0:12:57.440 --> 0:12:59.319 but but the but the audience who was there? What 0:12:59.480 --> 0:13:03.160 would own? Yeah, every every time a robot fell down, 0:13:05.880 --> 0:13:12.240 like because everyone wanted everything to go Obviously, the the 0:13:12.240 --> 0:13:16.680 performance here meant pushing the field of robotics forwards. So 0:13:17.000 --> 0:13:19.760 it was more than just cheering on your favorite It 0:13:19.840 --> 0:13:23.640 was about cheering on the the advancement of robotics as 0:13:23.679 --> 0:13:27.720 a discipline. Yeah. And and these tasks were not easy 0:13:27.880 --> 0:13:30.199 tasks that were set to the robots. They were they 0:13:30.200 --> 0:13:34.360 were challenging. Yeah. They Now when we start saying them, 0:13:34.400 --> 0:13:36.800 they're gonna sound easy because you're going to be thinking 0:13:36.800 --> 0:13:39.160 about it in the terms of a human being completing 0:13:39.200 --> 0:13:42.000 these tasks. And they're very simple. But keep in mind 0:13:42.040 --> 0:13:44.360 that all these things are tasks that robots have to 0:13:44.360 --> 0:13:47.240 be engineered to do. And only that, but the robot 0:13:47.280 --> 0:13:51.400 has to be engineered to do all of these tasks root. Yeah, 0:13:51.480 --> 0:13:53.560 and you think about most robots that you would see 0:13:53.640 --> 0:13:55.080 in your day to day life, Like if you have 0:13:55.120 --> 0:13:58.360 a rumba, that rumba is designed to clean the floor. 0:13:58.760 --> 0:14:02.000 It's not designed to clean the floor plus do the dishes, 0:14:02.160 --> 0:14:06.480 plus or watch your kids, or walk your dog or whatever. 0:14:06.760 --> 0:14:09.080 It can't do those things and you wouldn't expect it to. 0:14:09.559 --> 0:14:12.400 Yet these are robots that have to complete these eight 0:14:12.520 --> 0:14:16.520 different tasks and have one robot to do it. Oh 0:14:16.600 --> 0:14:19.480 yeah yeah, and with minimal supervision from the from the team, 0:14:19.640 --> 0:14:22.440 right yeah, because again your communication is limited. And the 0:14:22.480 --> 0:14:25.840 idea was build a robot that can autonomously do as 0:14:25.920 --> 0:14:29.440 much of this as possible, not not expecting any robot 0:14:29.520 --> 0:14:33.160 to be like the Terminator and not need any further 0:14:33.200 --> 0:14:36.280 direction like go that way and save the people, like 0:14:36.480 --> 0:14:40.480 there's nothing like that, but limited, you know, the more 0:14:40.520 --> 0:14:44.640 limited than the human interaction, the better. So Task number 0:14:44.640 --> 0:14:49.840 one drive. So so here's how this worked. They had 0:14:49.840 --> 0:14:53.080 to drive a Polaris Ranger XP nine hundred, which is 0:14:53.160 --> 0:14:56.680 essentially like a little not quite an altering vehicle, but 0:14:56.800 --> 0:14:59.920 similar STV kind of thing. Yeah, not even in su 0:15:00.040 --> 0:15:02.440 be more like a little almost like think of like 0:15:02.480 --> 0:15:05.600 a souped up golf cart, so a little bit more 0:15:05.600 --> 0:15:08.520 advanced than the golf cart. Um, and the teams had 0:15:08.560 --> 0:15:11.400 five minutes to alter the vehicle without the use of tools, 0:15:11.480 --> 0:15:14.080 so that their robots could operate it. So if the 0:15:14.160 --> 0:15:17.240 robot was at a form factor that did not easily 0:15:17.280 --> 0:15:19.600 fit into this, they could alter the vehicle, but they 0:15:19.600 --> 0:15:22.280 couldn't use tools to do it. So this made me 0:15:22.320 --> 0:15:26.920 think of like cutthroat kitchen. I'm picturing robotics teams just 0:15:27.000 --> 0:15:30.400 like smashing their hands into panics to reform them or something. 0:15:30.720 --> 0:15:32.640 You can alter this vehicle, but you can only use 0:15:32.720 --> 0:15:36.680 gummy worms. Yeah, it is a little bit of a 0:15:36.960 --> 0:15:40.160 of a fun twist on that. So the way the 0:15:40.200 --> 0:15:43.000 challenge would start is the robots would already be behind 0:15:43.040 --> 0:15:45.320 the wheel. They did not have to get into the vehicle. 0:15:45.840 --> 0:15:48.200 They could be placed in the vehicle. The vehicle was 0:15:48.240 --> 0:15:51.640 already running and in high gear. They said that they 0:15:51.840 --> 0:15:54.440 chose high gear because it would move the most smoothly 0:15:54.440 --> 0:15:57.880 out of the gears. But the teams were welcome to 0:15:58.000 --> 0:16:01.080 design a robot that could shift gears if need be, 0:16:01.680 --> 0:16:05.120 but they didn't have to. Uh. So then the robot 0:16:05.160 --> 0:16:07.840 had to drive the vehicle from the starting position to 0:16:08.200 --> 0:16:11.920 a different position through an obstacle course, not really an 0:16:11.920 --> 0:16:16.080 obstacle course, but a driving course. Uh. If the robots 0:16:16.600 --> 0:16:19.880 was to uh collide with one of the barriers and 0:16:19.880 --> 0:16:22.680 move it, then it would not be eligible for a 0:16:22.760 --> 0:16:26.400 point for the task. And we should say these eight 0:16:26.400 --> 0:16:30.840 tasks represent eight points. So teams were judged on two criteria, 0:16:31.080 --> 0:16:33.360 the number of points that they were able to accumulate 0:16:33.400 --> 0:16:36.120 and the time it took the robot to complete the 0:16:36.640 --> 0:16:39.160 series of tasks. So if you were able to do 0:16:39.240 --> 0:16:41.200 all eight and you had the lowest time, you win. 0:16:42.120 --> 0:16:46.040 Uh So if you if you ran ran to an obstacle, 0:16:46.200 --> 0:16:48.680 you've got no point. You could also choose for your 0:16:48.760 --> 0:16:52.560 robot to walk from the starting point to the next task, 0:16:52.680 --> 0:16:55.440 but then you also time penalty share. Yeah, time penalty, 0:16:55.480 --> 0:16:57.800 and you don't get a point because the robots not 0:16:58.120 --> 0:17:02.360 operating the vehicle. Um. So really the robot bare minimum 0:17:02.440 --> 0:17:04.320 had to be able to operate the accelerator and the 0:17:04.359 --> 0:17:06.919 steering wheel, although you would hope it could also operate 0:17:06.960 --> 0:17:10.720 the brake um because otherwise the robot would just be 0:17:10.760 --> 0:17:13.480 easing off the accelerator so that it would essentially coast 0:17:13.520 --> 0:17:17.800 into the final position. And then it had to uh 0:17:18.040 --> 0:17:22.440 to get completely past a cut off point that said, 0:17:22.480 --> 0:17:24.920 you know here, once the vehicle has passed this point, 0:17:24.960 --> 0:17:28.399 you have completed the task without going so far as 0:17:28.440 --> 0:17:32.000 to smash into the next obstacle. All right, So that's 0:17:32.040 --> 0:17:36.560 that was the first task. Second task was called egress, 0:17:37.080 --> 0:17:41.680 which I love. It's that's terrific vocabulary. Yeah, it's it's 0:17:41.800 --> 0:17:43.920 it's a little nicer than get out of the DIRN car. 0:17:45.560 --> 0:17:50.560 So that that's the southern version, right. So egress is 0:17:50.640 --> 0:17:53.359 essentially what I just said. The robot had to get 0:17:53.400 --> 0:17:56.119 itself out of the vehicle. It could exit out of 0:17:56.160 --> 0:17:59.160 either side, so it was not required to exit from 0:17:59.160 --> 0:18:01.680 one side versus the other. It had to be able 0:18:01.720 --> 0:18:04.879 to stand up or otherwise get into its you know, 0:18:05.000 --> 0:18:09.040 mobile format, because you didn't have to have a bipedal robot. 0:18:09.200 --> 0:18:11.600 Most of the designs were, but you didn't have to 0:18:11.640 --> 0:18:14.560 design one that way. It's just that when you're talking 0:18:14.560 --> 0:18:18.320 about operating stuff that humans operate bipedal, since that's how 0:18:18.359 --> 0:18:21.919 we are, that tends to beat. Yeah. So then it 0:18:22.000 --> 0:18:26.359 had to move itself to the next uh task position. 0:18:26.480 --> 0:18:29.879 So the whole judging, the whole thing is get is 0:18:29.960 --> 0:18:32.520 allowing itself to get out and walk over to the 0:18:32.560 --> 0:18:35.600 next point, and that would be another You would get 0:18:35.600 --> 0:18:37.960 a point for the egress part of the task if 0:18:37.960 --> 0:18:40.280 you were able to do that, or rather if your 0:18:40.359 --> 0:18:46.000 robot were able to do that. After that was door. Okay, 0:18:46.040 --> 0:18:49.320 so here's one of those things that sounds incredibly simple. 0:18:49.440 --> 0:18:52.120 The robot had to open a door and walk through 0:18:52.160 --> 0:18:57.000 the doorway. That's it that's the challenge. So so drive 0:18:57.040 --> 0:19:00.840 a car is on equal playing field with open and 0:19:00.880 --> 0:19:05.240 walk through it through a door. Yeah. However, spoiler alert, 0:19:05.359 --> 0:19:07.879 this was one of the challenges that was the most 0:19:08.000 --> 0:19:12.439 difficult for the robots. Uh So. It was a push door, 0:19:13.000 --> 0:19:15.119 and it was a it was a central, a lever 0:19:15.480 --> 0:19:17.239 handled door. It kind of like the one we have 0:19:17.280 --> 0:19:20.080 to the studio where you have to either push down 0:19:20.200 --> 0:19:22.399 or lift up on the levers and then push the 0:19:22.440 --> 0:19:26.199 door to simultaneously push. There was no threshold, so the 0:19:26.240 --> 0:19:29.760 robot didn't have to step over anything. That's very kind. Still, 0:19:29.920 --> 0:19:32.399 a lot of robots fell over in this point. And 0:19:32.440 --> 0:19:34.280 part of the reason why the robots were having so 0:19:34.359 --> 0:19:37.560 much trouble because that the doors with when you include 0:19:37.600 --> 0:19:40.560 the door jam, was only thirty three and a half inches, 0:19:40.600 --> 0:19:43.240 and some of these robots were wider than that. So 0:19:43.280 --> 0:19:46.399 they had to turn themselves, they had to pivot in, 0:19:47.359 --> 0:19:50.200 or they had to fold their limbs inward and then 0:19:50.240 --> 0:19:53.560 just kind of, you know, wiggle on through. I've got 0:19:53.560 --> 0:19:56.320 all these great images of robots attempting to get through 0:19:56.320 --> 0:19:59.400 a doorway. So yeah, that's the thing is that, in fact, 0:19:59.440 --> 0:20:02.080 it prompted one guy in the audience to say, when 0:20:02.080 --> 0:20:05.800 the robot uprising inevitably happens, just close your door and 0:20:05.840 --> 0:20:09.600 you'll probably be safe. If you have a door and 0:20:09.640 --> 0:20:11.720 you're at the top of a set of stairs, you're 0:20:11.760 --> 0:20:17.040 doubly safe. Um. So, next was Valve, which is where 0:20:17.040 --> 0:20:20.000 a robot had to buy a game on Steam. Okay, yeah, 0:20:20.440 --> 0:20:24.520 preferably something like uh, well there's the new Fallout, so 0:20:24.560 --> 0:20:28.399 pre ordering Fallout. Oh yeah yeah, actually no, no, it's 0:20:28.400 --> 0:20:30.760 it was actually physical Valve. It was not not the 0:20:31.680 --> 0:20:34.320 not the game company Valve. It was a terrible joke 0:20:34.440 --> 0:20:37.639 that I wrote in our notes. Actually in there, I 0:20:37.680 --> 0:20:39.320 was willing to go with it. You know, I think 0:20:39.400 --> 0:20:43.359 that I think that navigating complex internet software is really 0:20:43.440 --> 0:20:46.520 part of your future of robots. Yeah, you know where 0:20:46.520 --> 0:20:48.240 your robot could just sit at home and buy all 0:20:48.280 --> 0:20:50.399 those games for you. Yeah, exactly. I mean you're not 0:20:50.440 --> 0:20:52.360 gonna play him anyway, You're just buying them because they're 0:20:52.359 --> 0:20:54.720 on sale. Right, Really hate putting my credit card information 0:20:54.720 --> 0:20:56.600 into Yeah, this is going to be valuable. You just 0:20:56.600 --> 0:20:58.360 do it once with the robot and then you're done, 0:20:58.520 --> 0:21:03.439 maybe less with maybe less with disaster situations. So in 0:21:03.440 --> 0:21:06.800 this case, in this case, they were operating an actual valve. 0:21:07.560 --> 0:21:09.560 It was a circular handle. They had to turn in 0:21:09.560 --> 0:21:13.199 a counter clockwise direction at least three sixty degrees that 0:21:13.200 --> 0:21:17.080 would be considering opening the valve. So this was another 0:21:17.119 --> 0:21:19.200 one that was a little tough. Was you know, design 0:21:19.280 --> 0:21:22.120 a robot that can grip a circular valve and then 0:21:22.240 --> 0:21:25.639 turn it in this way. Also, the teams only knew 0:21:25.840 --> 0:21:29.399 that the valves size would be somewhere between four and 0:21:29.520 --> 0:21:33.359 sixteen inches in diameter, so they couldn't a gap. Yeah, 0:21:33.440 --> 0:21:35.480 they couldn't just plan in advance, like all right, well, 0:21:35.520 --> 0:21:38.960 we'll just design the robots so that it's hands are 0:21:39.000 --> 0:21:43.280 you know, are precisely molded to this particular valve, right, Like, 0:21:43.359 --> 0:21:45.800 let's just assume it's twelve inches. It'll be fine. That's 0:21:45.840 --> 0:21:48.600 not necessarily the case. The next step was probably my 0:21:48.720 --> 0:21:51.880 favorite out of all of them. Oh this is this 0:21:51.960 --> 0:21:55.359 is the kool aid Man challenge. Yeah. Wall. This was wall, 0:21:55.600 --> 0:21:57.639 but it wasn't just breaking through a wall, which is 0:21:57.640 --> 0:21:59.480 the way it was always described to me when I 0:21:59.520 --> 0:22:02.679 heard about, well it's really cutting through a wall, and 0:22:02.680 --> 0:22:04.399 and that's and I and I said breaking through in 0:22:04.440 --> 0:22:07.840 the in the previous trial challenge. But but it's really 0:22:07.880 --> 0:22:11.520 cutting through a wall using a drill actually, and the 0:22:11.560 --> 0:22:14.960 wall was dry walls half inch thick drywall, and there 0:22:15.080 --> 0:22:18.720 was a shape that you your robot had to cut 0:22:18.760 --> 0:22:22.000 the shape out of the wall, so I think it 0:22:22.040 --> 0:22:23.520 was like a giant circle, at least the one I 0:22:23.560 --> 0:22:25.680 saw it was a giant circle. Where the idea was 0:22:25.720 --> 0:22:28.000 that the robot had to go pick up a drill. 0:22:28.560 --> 0:22:30.240 The drill was an off position, so I had to 0:22:30.440 --> 0:22:33.720 squeeze the trigger to have it go on. Turn it on, yeah, 0:22:33.800 --> 0:22:38.439 and then insert the drill uh inside the line of 0:22:38.440 --> 0:22:42.520 the shape, trace around that line on the inside, and 0:22:42.640 --> 0:22:46.159 remove the rubble. The idea being that there might be 0:22:46.320 --> 0:22:48.159 a time where a robot would have to have to 0:22:48.200 --> 0:22:51.919 respond to an emergency get access to controls, but the 0:22:52.080 --> 0:22:54.840