My seven species of robot -- and how we created them
-
0:00 - 0:03So, the first robot to talk about is called STriDER.
-
0:03 - 0:05It stands for Self-excited
-
0:05 - 0:07Tripedal Dynamic Experimental Robot.
-
0:07 - 0:09It's a robot that has three legs,
-
0:09 - 0:12which is inspired by nature.
-
0:12 - 0:14But have you seen anything in nature,
-
0:14 - 0:16an animal that has three legs?
-
0:16 - 0:18Probably not. So, why do I call this
-
0:18 - 0:20a biologically inspired robot? How would it work?
-
0:20 - 0:23But before that, let's look at pop culture.
-
0:23 - 0:26So, you know H.G. Wells' "War of the Worlds," novel and movie.
-
0:26 - 0:28And what you see over here is a very popular
-
0:28 - 0:30video game,
-
0:30 - 0:33and in this fiction they describe these alien creatures that
-
0:33 - 0:35are robots that have three legs that terrorize Earth.
-
0:35 - 0:39But my robot, STriDER, does not move like this.
-
0:39 - 0:42So, this is an actual dynamic simulation animation.
-
0:42 - 0:44I'm just going to show you how the robot works.
-
0:44 - 0:47It flips its body 180 degrees
-
0:47 - 0:50and it swings its leg between the two legs and catches the fall.
-
0:50 - 0:52So, that's how it walks. But when you look at us
-
0:52 - 0:54human being, bipedal walking,
-
0:54 - 0:56what you're doing is you're not really using a muscle
-
0:56 - 0:59to lift your leg and walk like a robot. Right?
-
0:59 - 1:02What you're doing is you really swing your leg and catch the fall,
-
1:02 - 1:05stand up again, swing your leg and catch the fall.
-
1:05 - 1:08You're using your built-in dynamics, the physics of your body,
-
1:08 - 1:10just like a pendulum.
-
1:10 - 1:14We call that the concept of passive dynamic locomotion.
-
1:14 - 1:16What you're doing is, when you stand up,
-
1:16 - 1:18potential energy to kinetic energy,
-
1:18 - 1:20potential energy to kinetic energy.
-
1:20 - 1:22It's a constantly falling process.
-
1:22 - 1:25So, even though there is nothing in nature that looks like this,
-
1:25 - 1:27really, we were inspired by biology
-
1:27 - 1:29and applying the principles of walking
-
1:29 - 1:32to this robot. Thus it's a biologically inspired robot.
-
1:32 - 1:34What you see over here, this is what we want to do next.
-
1:34 - 1:38We want to fold up the legs and shoot it up for long-range motion.
-
1:38 - 1:41And it deploys legs -- it looks almost like "Star Wars" --
-
1:41 - 1:44when it lands, it absorbs the shock and starts walking.
-
1:44 - 1:47What you see over here, this yellow thing, this is not a death ray. (Laughter)
-
1:47 - 1:49This is just to show you that if you have cameras
-
1:49 - 1:51or different types of sensors --
-
1:51 - 1:53because it is tall, it's 1.8 meters tall --
-
1:53 - 1:56you can see over obstacles like bushes and those kinds of things.
-
1:56 - 1:58So we have two prototypes.
-
1:58 - 2:01The first version, in the back, that's STriDER I.
-
2:01 - 2:03The one in front, the smaller, is STriDER II.
-
2:03 - 2:05The problem that we had with STriDER I is
-
2:05 - 2:08it was just too heavy in the body. We had so many motors,
-
2:08 - 2:10you know, aligning the joints, and those kinds of things.
-
2:10 - 2:14So, we decided to synthesize a mechanical mechanism
-
2:14 - 2:17so we could get rid of all the motors, and with a single motor
-
2:17 - 2:19we can coordinate all the motions.
-
2:19 - 2:22It's a mechanical solution to a problem, instead of using mechatronics.
-
2:22 - 2:25So, with this now the top body is light enough. So, it's walking in our lab;
-
2:25 - 2:28this was the very first successful step.
-
2:28 - 2:30It's still not perfected -- its coffee falls down --
-
2:30 - 2:33so we still have a lot of work to do.
-
2:33 - 2:36The second robot I want to talk about is called IMPASS.
-
2:36 - 2:40It stands for Intelligent Mobility Platform with Actuated Spoke System.
-
2:40 - 2:43So, it's a wheel-leg hybrid robot.
-
2:43 - 2:45So, think of a rimless wheel
-
2:45 - 2:47or a spoke wheel,
-
2:47 - 2:50but the spokes individually move in and out of the hub;
-
2:50 - 2:52so, it's a wheel-leg hybrid.
-
2:52 - 2:54We are literally re-inventing the wheel here.
-
2:54 - 2:57Let me demonstrate how it works.
-
2:57 - 2:59So, in this video we're using an approach
-
2:59 - 3:01called the reactive approach.
-
3:01 - 3:04Just simply using the tactile sensors on the feet,
-
3:04 - 3:06it's trying to walk over a changing terrain,
-
3:06 - 3:09a soft terrain where it pushes down and changes.
-
3:09 - 3:11And just by the tactile information,
-
3:11 - 3:14it successfully crosses over these type of terrain.
-
3:14 - 3:18But, when it encounters a very extreme terrain,
-
3:18 - 3:21in this case, this obstacle is more than three times
-
3:21 - 3:23the height of the robot,
-
3:23 - 3:25Then it switches to a deliberate mode,
-
3:25 - 3:27where it uses a laser range finder,
-
3:27 - 3:29and camera systems, to identify the obstacle and the size,
-
3:29 - 3:32and it plans, carefully plans the motion of the spokes
-
3:32 - 3:34and coordinates it so that it can show this
-
3:34 - 3:36kind of very very impressive mobility.
-
3:36 - 3:38You probably haven't seen anything like this out there.
-
3:38 - 3:41This is a very high mobility robot
-
3:41 - 3:44that we developed called IMPASS.
-
3:44 - 3:46Ah, isn't that cool?
-
3:46 - 3:49When you drive your car,
-
3:49 - 3:51when you steer your car, you use a method
-
3:51 - 3:53called Ackermann steering.
-
3:53 - 3:55The front wheels rotate like this.
-
3:55 - 3:58For most small wheeled robots,
-
3:58 - 4:00they use a method called differential steering
-
4:00 - 4:03where the left and right wheel turns the opposite direction.
-
4:03 - 4:06For IMPASS, we can do many, many different types of motion.
-
4:06 - 4:09For example, in this case, even though the left and right wheel is connected
-
4:09 - 4:11with a single axle rotating at the same angle of velocity.
-
4:11 - 4:14We just simply change the length of the spoke.
-
4:14 - 4:16It affects the diameter and then can turn to the left, turn to the right.
-
4:16 - 4:18So, these are just some examples of the neat things
-
4:18 - 4:21that we can do with IMPASS.
-
4:21 - 4:23This robot is called CLIMBeR:
-
4:23 - 4:26Cable-suspended Limbed Intelligent Matching Behavior Robot.
-
4:26 - 4:29So, I've been talking to a lot of NASA JPL scientists --
-
4:29 - 4:31at JPL they are famous for the Mars rovers --
-
4:31 - 4:33and the scientists, geologists always tell me
-
4:33 - 4:36that the real interesting science,
-
4:36 - 4:39the science-rich sites, are always at the cliffs.
-
4:39 - 4:41But the current rovers cannot get there.
-
4:41 - 4:43So, inspired by that we wanted to build a robot
-
4:43 - 4:46that can climb a structured cliff environment.
-
4:46 - 4:48So, this is CLIMBeR.
-
4:48 - 4:50So, what it does, it has three legs. It's probably difficult to see,
-
4:50 - 4:53but it has a winch and a cable at the top --
-
4:53 - 4:55and it tries to figure out the best place to put its foot.
-
4:55 - 4:57And then once it figures that out
-
4:57 - 5:00in real time, it calculates the force distribution:
-
5:00 - 5:03how much force it needs to exert to the surface
-
5:03 - 5:05so it doesn't tip and doesn't slip.
-
5:05 - 5:07Once it stabilizes that, it lifts a foot,
-
5:07 - 5:11and then with the winch it can climb up these kinds of thing.
-
5:11 - 5:13Also for search and rescue applications as well.
-
5:13 - 5:15Five years ago I actually worked at NASA JPL
-
5:15 - 5:17during the summer as a faculty fellow.
-
5:17 - 5:21And they already had a six legged robot called LEMUR.
-
5:21 - 5:24So, this is actually based on that. This robot is called MARS:
-
5:24 - 5:27Multi-Appendage Robotic System. So, it's a hexapod robot.
-
5:27 - 5:29We developed our adaptive gait planner.
-
5:29 - 5:31We actually have a very interesting payload on there.
-
5:31 - 5:33The students like to have fun. And here you can see that it's
-
5:33 - 5:36walking over unstructured terrain.
-
5:36 - 5:38It's trying to walk on the coarse terrain,
-
5:38 - 5:40sandy area,
-
5:40 - 5:45but depending on the moisture content or the grain size of the sand
-
5:45 - 5:47the foot's soil sinkage model changes.
-
5:47 - 5:51So, it tries to adapt its gait to successfully cross over these kind of things.
-
5:51 - 5:53And also, it does some fun stuff, as can imagine.
-
5:53 - 5:56We get so many visitors visiting our lab.
-
5:56 - 5:58So, when the visitors come, MARS walks up to the computer,
-
5:58 - 6:00starts typing "Hello, my name is MARS."
-
6:00 - 6:02Welcome to RoMeLa,
-
6:02 - 6:06the Robotics Mechanisms Laboratory at Virginia Tech.
-
6:06 - 6:08This robot is an amoeba robot.
-
6:08 - 6:11Now, we don't have enough time to go into technical details,
-
6:11 - 6:13I'll just show you some of the experiments.
-
6:13 - 6:15So, this is some of the early feasibility experiments.
-
6:15 - 6:19We store potential energy to the elastic skin to make it move.
-
6:19 - 6:21Or use an active tension cords to make it move
-
6:21 - 6:24forward and backward. It's called ChIMERA.
-
6:24 - 6:26We also have been working with some scientists
-
6:26 - 6:28and engineers from UPenn
-
6:28 - 6:30to come up with a chemically actuated version
-
6:30 - 6:32of this amoeba robot.
-
6:32 - 6:34We do something to something
-
6:34 - 6:40And just like magic, it moves. The blob.
-
6:40 - 6:42This robot is a very recent project. It's called RAPHaEL.
-
6:42 - 6:45Robotic Air Powered Hand with Elastic Ligaments.
-
6:45 - 6:49There are a lot of really neat, very good robotic hands out there in the market.
-
6:49 - 6:53The problem is they're just too expensive, tens of thousands of dollars.
-
6:53 - 6:55So, for prosthesis applications it's probably not too practical,
-
6:55 - 6:57because it's not affordable.
-
6:57 - 7:01We wanted to go tackle this problem in a very different direction.
-
7:01 - 7:04Instead of using electrical motors, electromechanical actuators,
-
7:04 - 7:06we're using compressed air.
-
7:06 - 7:08We developed these novel actuators for joints.
-
7:08 - 7:11It is compliant. You can actually change the force,
-
7:11 - 7:13simply just changing the air pressure.
-
7:13 - 7:15And it can actually crush an empty soda can.
-
7:15 - 7:18It can pick up very delicate objects like a raw egg,
-
7:18 - 7:21or in this case, a lightbulb.
-
7:21 - 7:25The best part, it took only $200 dollars to make the first prototype.
-
7:25 - 7:28This robot is actually a family of snake robots
-
7:28 - 7:30that we call HyDRAS,
-
7:30 - 7:32Hyper Degrees-of-freedom Robotic Articulated Serpentine.
-
7:32 - 7:35This is a robot that can climb structures.
-
7:35 - 7:37This is a HyDRAS's arm.
-
7:37 - 7:39It's a 12 degrees of freedom robotic arm.
-
7:39 - 7:41But the cool part is the user interface.
-
7:41 - 7:44The cable over there, that's an optical fiber.
-
7:44 - 7:46And this student, probably the first time using it,
-
7:46 - 7:48but she can articulate it many different ways.
-
7:48 - 7:51So, for example in Iraq, you know, the war zone,
-
7:51 - 7:53there is roadside bombs. Currently you send these
-
7:53 - 7:56remotely controlled vehicles that are armed.
-
7:56 - 7:58It takes really a lot of time and it's expensive
-
7:58 - 8:02to train the operator to operate this complex arm.
-
8:02 - 8:04In this case it's very intuitive;
-
8:04 - 8:08this student, probably his first time using it, doing very complex manipulation tasks,
-
8:08 - 8:10picking up objects and doing manipulation,
-
8:10 - 8:13just like that. Very intuitive.
-
8:15 - 8:17Now, this robot is currently our star robot.
-
8:17 - 8:20We actually have a fan club for the robot, DARwIn:
-
8:20 - 8:23Dynamic Anthropomorphic Robot with Intelligence.
-
8:23 - 8:25As you know, we are very interested in
-
8:25 - 8:27humanoid robot, human walking,
-
8:27 - 8:29so we decided to build a small humanoid robot.
-
8:29 - 8:31This was in 2004; at that time,
-
8:31 - 8:33this was something really, really revolutionary.
-
8:33 - 8:35This was more of a feasibility study:
-
8:35 - 8:37What kind of motors should we use?
-
8:37 - 8:39Is it even possible? What kinds of controls should we do?
-
8:39 - 8:41So, this does not have any sensors.
-
8:41 - 8:43So, it's an open loop control.
-
8:43 - 8:45For those who probably know, if you don't have any sensors
-
8:45 - 8:47and there are any disturbances, you know what happens.
-
8:50 - 8:51(Laughter)
-
8:51 - 8:53So, based on that success, the following year
-
8:53 - 8:56we did the proper mechanical design
-
8:56 - 8:58starting from kinematics.
-
8:58 - 9:00And thus, DARwIn I was born in 2005.
-
9:00 - 9:02It stands up, it walks -- very impressive.
-
9:02 - 9:04However, still, as you can see,
-
9:04 - 9:08it has a cord, umbilical cord. So, we're still using an external power source
-
9:08 - 9:10and external computation.
-
9:10 - 9:14So, in 2006, now it's really time to have fun.
-
9:14 - 9:17Let's give it intelligence. We give it all the computing power it needs:
-
9:17 - 9:19a 1.5 gigahertz Pentium M chip,
-
9:19 - 9:21two FireWire cameras, rate gyros, accelerometers,
-
9:21 - 9:24four force sensors on the foot, lithium polymer batteries.
-
9:24 - 9:28And now DARwIn II is completely autonomous.
-
9:28 - 9:30It is not remote controlled.
-
9:30 - 9:33There are no tethers. It looks around, searches for the ball,
-
9:33 - 9:36looks around, searches for the ball, and it tries to play a game of soccer,
-
9:36 - 9:39autonomously: artificial intelligence.
-
9:39 - 9:42Let's see how it does. This was our very first trial,
-
9:42 - 9:47and... Spectators (Video): Goal!
-
9:48 - 9:51Dennis Hong: So, there is actually a competition called RoboCup.
-
9:51 - 9:53I don't know how many of you have heard about RoboCup.
-
9:53 - 9:58It's an international autonomous robot soccer competition.
-
9:58 - 10:01And the goal of RoboCup, the actual goal is,
-
10:01 - 10:03by the year 2050
-
10:03 - 10:06we want to have full size, autonomous humanoid robots
-
10:06 - 10:10play soccer against the human World Cup champions
-
10:10 - 10:12and win.
-
10:12 - 10:14It's a true actual goal. It's a very ambitious goal,
-
10:14 - 10:16but we truly believe that we can do it.
-
10:16 - 10:19So, this is last year in China.
-
10:19 - 10:21We were the very first team in the United States that qualified
-
10:21 - 10:23in the humanoid RoboCup competition.
-
10:23 - 10:26This is this year in Austria.
-
10:26 - 10:28You're going to see the action, three against three,
-
10:28 - 10:30completely autonomous.
-
10:30 - 10:32There you go. Yes!
-
10:33 - 10:35The robots track and they
-
10:35 - 10:38team play amongst themselves.
-
10:38 - 10:40It's very impressive. It's really a research event
-
10:40 - 10:44packaged in a more exciting competition event.
-
10:44 - 10:46What you see over here, this is the beautiful
-
10:46 - 10:48Louis Vuitton Cup trophy.
-
10:48 - 10:50So, this is for the best humanoid,
-
10:50 - 10:52and we would like to bring this for the very first time, to the United States
-
10:52 - 10:54next year, so wish us luck.
-
10:54 - 10:56(Applause)
-
10:56 - 10:59Thank you.
-
10:59 - 11:01DARwIn also has a lot of other talents.
-
11:01 - 11:04Last year it actually conducted the Roanoke Symphony Orchestra
-
11:04 - 11:07for the holiday concert.
-
11:07 - 11:10This is the next generation robot, DARwIn IV,
-
11:10 - 11:13but smarter, faster, stronger.
-
11:13 - 11:15And it's trying to show off its ability:
-
11:15 - 11:18"I'm macho, I'm strong.
-
11:18 - 11:21I can also do some Jackie Chan-motion,
-
11:21 - 11:24martial art movements."
-
11:24 - 11:26(Laughter)
-
11:26 - 11:28And it walks away. So, this is DARwIn IV.
-
11:28 - 11:30And again, you'll be able to see it in the lobby.
-
11:30 - 11:32We truly believe this is going to be the very first running
-
11:32 - 11:35humanoid robot in the United States. So, stay tuned.
-
11:35 - 11:38All right. So I showed you some of our exciting robots at work.
-
11:38 - 11:41So, what is the secret of our success?
-
11:41 - 11:43Where do we come up with these ideas?
-
11:43 - 11:45How do we develop these kinds of ideas?
-
11:45 - 11:47We have a fully autonomous vehicle
-
11:47 - 11:49that can drive into urban environments. We won a half a million dollars
-
11:49 - 11:51in the DARPA Urban Challenge.
-
11:51 - 11:53We also have the world's very first
-
11:53 - 11:55vehicle that can be driven by the blind.
-
11:55 - 11:57We call it the Blind Driver Challenge, very exciting.
-
11:57 - 12:01And many, many other robotics projects I want to talk about.
-
12:01 - 12:03These are just the awards that we won in 2007 fall
-
12:03 - 12:06from robotics competitions and those kinds of things.
-
12:06 - 12:08So, really, we have five secrets.
-
12:08 - 12:10First is: Where do we get inspiration?
-
12:10 - 12:12Where do we get this spark of imagination?
-
12:12 - 12:15This is a true story, my personal story.
-
12:15 - 12:17At night when I go to bed, 3 - 4 a.m. in the morning,
-
12:17 - 12:20I lie down, close my eyes, and I see these lines and circles
-
12:20 - 12:22and different shapes floating around.
-
12:22 - 12:25And they assemble, and they form these kinds of mechanisms.
-
12:25 - 12:27And then I think, "Ah this is cool."
-
12:27 - 12:29So, right next to my bed I keep a notebook,
-
12:29 - 12:32a journal, with a special pen that has a light on it, LED light,
-
12:32 - 12:34because I don't want to turn on the light and wake up my wife.
-
12:34 - 12:36So, I see this, scribble everything down, draw things,
-
12:36 - 12:38and I go to bed.
-
12:38 - 12:40Every day in the morning,
-
12:40 - 12:42the first thing I do before my first cup of coffee,
-
12:42 - 12:44before I brush my teeth, I open my notebook.
-
12:44 - 12:46Many times it's empty,
-
12:46 - 12:48sometimes I have something there -- if something's there, sometimes it's junk --
-
12:48 - 12:51but most of the time I can't even read my handwriting.
-
12:51 - 12:54And so, 4 am in the morning, what do you expect, right?
-
12:54 - 12:56So, I need to decipher what I wrote.
-
12:56 - 12:59But sometimes I see this ingenious idea in there,
-
12:59 - 13:01and I have this eureka moment.
-
13:01 - 13:03I directly run to my home office, sit at my computer,
-
13:03 - 13:05I type in the ideas, I sketch things out
-
13:05 - 13:08and I keep a database of ideas.
-
13:08 - 13:10So, when we have these calls for proposals,
-
13:10 - 13:12I try to find a match between my
-
13:12 - 13:14potential ideas
-
13:14 - 13:16and the problem. If there is a match we write a research proposal,
-
13:16 - 13:20get the research funding in, and that's how we start our research programs.
-
13:20 - 13:23But just a spark of imagination is not good enough.
-
13:23 - 13:25How do we develop these kinds of ideas?
-
13:25 - 13:28At our lab RoMeLa, the Robotics and Mechanisms Laboratory,
-
13:28 - 13:31we have these fantastic brainstorming sessions.
-
13:31 - 13:33So, we gather around, we discuss about problems
-
13:33 - 13:35and social problems and talk about it.
-
13:35 - 13:38But before we start we set this golden rule.
-
13:38 - 13:40The rule is:
-
13:40 - 13:43Nobody criticizes anybody's ideas.
-
13:43 - 13:45Nobody criticizes any opinion.
-
13:45 - 13:47This is important, because many times students, they fear
-
13:47 - 13:50or they feel uncomfortable how others might think
-
13:50 - 13:52about their opinions and thoughts.
-
13:52 - 13:54So, once you do this, it is amazing
-
13:54 - 13:56how the students open up.
-
13:56 - 13:59They have these wacky, cool, crazy, brilliant ideas, and
-
13:59 - 14:02the whole room is just electrified with creative energy.
-
14:02 - 14:05And this is how we develop our ideas.
-
14:05 - 14:08Well, we're running out of time. One more thing I want to talk about is,
-
14:08 - 14:12you know, just a spark of idea and development is not good enough.
-
14:12 - 14:14There was a great TED moment,
-
14:14 - 14:17I think it was Sir Ken Robinson, was it?
-
14:17 - 14:19He gave a talk about how education
-
14:19 - 14:21and school kills creativity.
-
14:21 - 14:24Well, actually, there are two sides to the story.
-
14:24 - 14:27So, there is only so much one can do
-
14:27 - 14:29with just ingenious ideas
-
14:29 - 14:32and creativity and good engineering intuition.
-
14:32 - 14:34If you want to go beyond a tinkering,
-
14:34 - 14:36if you want to go beyond a hobby of robotics
-
14:36 - 14:39and really tackle the grand challenges of robotics
-
14:39 - 14:41through rigorous research
-
14:41 - 14:44we need more than that. This is where school comes in.
-
14:44 - 14:47Batman, fighting against bad guys,
-
14:47 - 14:49he has his utility belt, he has his grappling hook,
-
14:49 - 14:51he has all different kinds of gadgets.
-
14:51 - 14:53For us roboticists, engineers and scientists,
-
14:53 - 14:58these tools, these are the courses and classes you take in class.
-
14:58 - 15:00Math, differential equations.
-
15:00 - 15:02I have linear algebra, science, physics,
-
15:02 - 15:05even nowadays, chemistry and biology, as you've seen.
-
15:05 - 15:07These are all the tools that we need.
-
15:07 - 15:09So, the more tools you have, for Batman,
-
15:09 - 15:11more effective at fighting the bad guys,
-
15:11 - 15:15for us, more tools to attack these kinds of big problems.
-
15:15 - 15:18So, education is very important.
-
15:18 - 15:20Also, it's not about that,
-
15:20 - 15:22only about that. You also have to work really, really hard.
-
15:22 - 15:24So, I always tell my students,
-
15:24 - 15:26"Work smart, then work hard."
-
15:26 - 15:29This picture in the back this is 3 a.m. in the morning.
-
15:29 - 15:31I guarantee if you come to your lab at 3 - 4 am
-
15:31 - 15:33we have students working there,
-
15:33 - 15:36not because I tell them to, but because we are having too much fun.
-
15:36 - 15:38Which leads to the last topic:
-
15:38 - 15:40Do not forget to have fun.
-
15:40 - 15:43That's really the secret of our success, we're having too much fun.
-
15:43 - 15:46I truly believe that highest productivity comes when you're having fun,
-
15:46 - 15:48and that's what we're doing.
-
15:48 - 15:50There you go. Thank you so much.
-
15:50 - 15:55(Applause)
- Title:
- My seven species of robot -- and how we created them
- Speaker:
- Dennis Hong
- Description:
-
At TEDxNASA, Dennis Hong introduces seven award-winning, all-terrain robots -- like the humanoid, soccer-playing DARwIn and the cliff-gripping CLIMBeR -- all built by his team at RoMeLa, Virginia Tech. Watch to the end to hear the five creative secrets to his lab's incredible technical success.
- Video Language:
- English
- Team:
- closed TED
- Project:
- TEDTalks
- Duration:
- 15:57
Krystian Aparta commented on English subtitles for My seven species of robot -- and how we created them | ||
Krystian Aparta edited English subtitles for My seven species of robot -- and how we created them | ||
Krystian Aparta edited English subtitles for My seven species of robot -- and how we created them | ||
Brian Greene edited English subtitles for My seven species of robot -- and how we created them | ||
TED Translators admin edited English subtitles for My seven species of robot -- and how we created them | ||
TED edited English subtitles for My seven species of robot -- and how we created them | ||
TED added a translation |
Krystian Aparta
The English transcript was updated on 6/21/2017.