0:00:17.706,0:00:19.267
Thanks for having me.

0:00:19.267,0:00:23.231
We have too many really exciting[br]robotics works that I want to show you

0:00:23.231,0:00:25.036
but we only have 18 minutes,

0:00:25.036,0:00:28.391
so I really had a hard time[br]trying to cut down the slides.

0:00:28.391,0:00:30.576
But let's see how it goes,[br]we have 18 minutes

0:00:30.576,0:00:34.507
and an apology in advance,[br]I'm probably going to speak really fast.

0:00:34.507,0:00:37.951
So, the first robot I'll talk about[br]is called STriDER.

0:00:37.951,0:00:41.467
It stands for Self-excited[br]Tripedal Dynamic Experimental Robot.

0:00:41.467,0:00:43.126
It's a robot that has three legs,

0:00:43.126,0:00:45.856
which is inspired by nature.

0:00:45.856,0:00:48.031
But have you seen anything in nature,

0:00:48.031,0:00:49.871
an animal that has three legs?

0:00:49.871,0:00:51.009
Probably not.

0:00:51.009,0:00:53.554
So, why do I call this[br]a biologically inspired robot?

0:00:53.554,0:00:54.755
How would it work?

0:00:54.755,0:00:57.060
But before that,[br]let's look at pop culture.

0:00:57.060,0:01:00.770
So, you know H.G. Wells'[br]"War of the Worlds," novel and movie.

0:01:00.770,0:01:02.098
And what you see over here

0:01:02.098,0:01:04.157
is a very popular video game,

0:01:04.157,0:01:07.183
and in this fiction they describe[br]these alien creatures

0:01:07.183,0:01:09.993
and robots that have three legs[br]that terrorize Earth.

0:01:09.993,0:01:13.842
But my robot, STriDER,[br]does not move like this.

0:01:13.842,0:01:15.252
So, how does it work?

0:01:15.252,0:01:18.000
So, this is an actual[br]dynamic simulation animation.

0:01:18.000,0:01:20.333
I'm just going to show you[br]how the robot works.

0:01:20.333,0:01:22.139
So when I go to robotics conferences,

0:01:22.139,0:01:24.167
I show this video to some of my colleagues

0:01:24.167,0:01:26.919
and everybody goes, wow, this is cool.

0:01:26.919,0:01:29.496
So when I click this,[br]it's going to show an animation,

0:01:29.496,0:01:32.144
so everybody say "Ooh" and "Aah".

0:01:33.445,0:01:35.052
Ooh.

0:01:36.575,0:01:38.819
Aah. Isn't that cool?

0:01:40.165,0:01:42.308
It flips its body 180 degrees

0:01:42.308,0:01:45.428
and it swings its leg between[br]the two legs and catches the fall.

0:01:45.428,0:01:46.793
So, that's how it walks.

0:01:46.793,0:01:49.996
If you think about it, it looks[br]very complicated, almost organic.

0:01:49.996,0:01:51.608
But why are we trying to do this?

0:01:51.608,0:01:53.572
How is this biologically inspired?

0:01:53.572,0:01:55.606
Let me talk about it a little bit.

0:01:55.606,0:01:58.560
So, when you look at us[br]human beings, bipedal walking,

0:01:58.560,0:02:01.049
what you're doing is[br]you're not really using a muscle

0:02:01.049,0:02:03.896
to lift your leg and walk like a robot.[br]Right?

0:02:03.896,0:02:07.303
What you're doing is you really swing[br]your leg and catch the fall,

0:02:07.303,0:02:09.964
stand up again,[br]swing your leg and catch the fall.

0:02:09.964,0:02:13.109
You're using your built-in dynamics,[br]the physics of your body,

0:02:13.109,0:02:14.887
just like a pendulum.

0:02:14.887,0:02:18.309
We call that the concept[br]of passive dynamic locomotion.

0:02:18.309,0:02:21.469
What you're doing is, when you stand up,

0:02:21.469,0:02:23.698
potential energy to kinetic energy,

0:02:23.698,0:02:25.468
potential energy to kinetic energy.

0:02:25.468,0:02:27.768
It's a constantly falling process.

0:02:27.768,0:02:30.800
So, even though there is nothing[br]in nature that looks like this,

0:02:30.800,0:02:32.537
really, we were inspired by biology

0:02:32.537,0:02:35.954
and applying the principles of walking[br]to this robot.

0:02:35.954,0:02:38.648
Thus it's a biologically inspired robot.

0:02:38.648,0:02:41.473
What you see over here,[br]this is what we want to do next.

0:02:41.473,0:02:44.864
We want to fold up the legs[br]and shoot it up for long-range motion.

0:02:44.864,0:02:47.588
And it deploys legs -[br]it looks almost like "Star Wars" -

0:02:47.588,0:02:50.469
when it lands, it absorbs[br]the shock and starts walking.

0:02:50.469,0:02:54.161
What you see over here, this yellow thing,[br]this is not a death ray. (Laughter)

0:02:54.161,0:02:56.529
This is just to show you[br]that if you have cameras

0:02:56.529,0:02:58.044
or different types of sensors -

0:02:58.044,0:03:00.114
because it is tall, it's 1.8 meters tall -

0:03:00.114,0:03:03.215
you can see over obstacles like bushes[br]and those kinds of things.

0:03:03.215,0:03:04.589
So we have two prototypes.

0:03:04.589,0:03:07.529
The first version, in the back,[br]that's STriDER I.

0:03:07.529,0:03:10.193
One of the problems[br]that we had with STriDER I -

0:03:10.193,0:03:12.768
The one in front, the smaller,[br]is STriDER II.

0:03:12.768,0:03:14.804
The problem that we had[br]with STriDER I is

0:03:14.804,0:03:16.544
it was just too heavy in the body.

0:03:16.544,0:03:19.162
We had so many motors,[br]you know, aligning the joints,

0:03:19.162,0:03:20.514
and those kinds of things.

0:03:20.514,0:03:23.486
So, we decided to synthesize[br]a mechanical mechanism

0:03:23.486,0:03:26.498
so we could get rid of all the motors,[br]and with a single motor

0:03:26.498,0:03:28.271
we can coordinate all the motions.

0:03:28.271,0:03:32.427
It's a mechanical solution to a problem,[br]instead of using mechatronics.

0:03:32.540,0:03:35.550
So, with this now the top body[br]is light enough.

0:03:35.550,0:03:39.135
So, it's walking in our lab;[br]this was the very first successful step.

0:03:39.135,0:03:41.599
It's still not perfected -[br]its coffee falls down -

0:03:41.599,0:03:43.739
so we still have a lot of work to do.

0:03:44.083,0:03:46.716
The second robot I want to talk about[br]is called IMPASS.

0:03:46.716,0:03:47.605
It stands for

0:03:47.605,0:03:51.035
Intelligent Mobility Platform[br]with Actuated Spoke System.

0:03:51.035,0:03:53.882
So, it's a wheel-leg hybrid robot.

0:03:53.882,0:03:56.020
So, think of a rimless wheel

0:03:56.020,0:03:57.630
or a spoke wheel,

0:03:57.630,0:04:01.003
but the spokes individually[br]move in and out of the hub;

0:04:01.003,0:04:02.877
so, it's a wheel-leg hybrid.

0:04:02.877,0:04:05.413
We are literally re-inventing[br]the wheel here.

0:04:05.413,0:04:07.503
Let me demonstrate how it works.

0:04:07.503,0:04:09.845
So, in this video we're using an approach

0:04:09.845,0:04:11.974
called the reactive approach.

0:04:11.974,0:04:14.788
Just simply using the tactile sensors[br]on the feet,

0:04:14.788,0:04:17.821
it's trying to walk over[br]a changing terrain,

0:04:17.821,0:04:20.726
a soft terrain[br]where it pushes down and changes.

0:04:20.726,0:04:22.710
And just by the tactile information,

0:04:22.710,0:04:25.742
it successfully crosses over[br]these type of terrain.

0:04:25.742,0:04:29.100
But, when it encounters[br]a very extreme terrain,

0:04:29.100,0:04:32.814
in this case, this obstacle[br]is more than three times

0:04:32.814,0:04:34.951
the height of the robot,

0:04:34.951,0:04:36.884
Then it switches to a deliberate mode,

0:04:36.884,0:04:38.989
where it uses a laser range finder,

0:04:38.989,0:04:41.961
and camera systems,[br]to identify the obstacle and the size,

0:04:41.961,0:04:44.962
and it plans, carefully plans[br]the motion of the spokes

0:04:44.962,0:04:47.094
and coordinates it[br]so that it can show this

0:04:47.094,0:04:49.004
kind of very very impressive mobility.

0:04:49.004,0:04:51.597
You probably haven't seen[br]anything like this out there.

0:04:51.597,0:04:53.582
This is a very high mobility robot

0:04:53.582,0:04:55.921
that we developed called IMPASS.

0:04:56.468,0:05:00.422
When you drive your car,[br]when you steer it,

0:05:00.422,0:05:02.468
you use a method called[br]Ackermann steering,[br]

0:05:02.468,0:05:04.508
the front wheels rotate like this.

0:05:05.339,0:05:09.738
But most of the small wheeled robots[br]use a method called differential steering

0:05:09.738,0:05:12.539
where the left and right wheel[br]turn in opposite directions.

0:05:12.858,0:05:16.013
For IMPASS, we can do many,[br]many different types of motion.

0:05:16.013,0:05:19.583
For example, in this case, even though[br]the left and right wheel is connected

0:05:19.583,0:05:22.369
with a single axle rotating[br]at the same angle of velocity,

0:05:22.369,0:05:24.462
we just simply change[br]the length of the spoke.

0:05:24.462,0:05:27.812
It affects the diameter and then[br]can turn to the left and to the right.

0:05:27.812,0:05:29.184
These are just some examples

0:05:29.184,0:05:31.429
of the neat things[br]that we can do with IMPASS.

0:05:31.429,0:05:33.414
This robot is called CLIMBeR:

0:05:33.414,0:05:36.619
Cable-suspended Limbed Intelligent[br]Matching Behavior Robot.

0:05:36.619,0:05:39.577
So, I've been talking to a lot[br]of NASA JPL scientists -

0:05:39.577,0:05:41.626
at JPL they are famous[br]for the Mars rovers -

0:05:41.626,0:05:44.001
and the scientists,[br]geologists always tell me

0:05:44.001,0:05:46.122
that the real interesting science,

0:05:46.122,0:05:48.759
the science-rich sites,[br]are always at the cliffs.

0:05:48.759,0:05:51.271
But the current rovers cannot get there.

0:05:51.271,0:05:53.904
So, inspired by that[br]we wanted to build a robot

0:05:53.904,0:05:57.037
that can climb a structured[br]cliff environment.

0:05:57.037,0:05:58.716
So, this is CLIMBeR.

0:05:58.716,0:06:01.511
So, what it does, it has three legs.[br]It's difficult to see,

0:06:01.511,0:06:03.584
but it has a winch[br]and a cable at the top -

0:06:03.584,0:06:06.417
and it tries to figure out[br]the best place to put its foot.

0:06:06.417,0:06:08.283
And then once it figures that out

0:06:08.283,0:06:10.805
in real time, it calculates[br]the force distribution:

0:06:10.805,0:06:13.285
how much force it needs[br]to exert to the surface

0:06:13.285,0:06:15.228
so it doesn't tip and doesn't slip.

0:06:15.228,0:06:17.489
Once it stabilizes that, it lifts a foot,

0:06:17.489,0:06:21.016
and then with the winch[br]it can climb up these kinds of thing.

0:06:21.333,0:06:24.405
Also for search and rescue[br]applications as well.

0:06:24.876,0:06:28.465
This robot is called MARS:[br]Multi-Appendage Robotic System.

0:06:28.465,0:06:30.815
Five years ago I actually[br]worked at NASA JPL

0:06:30.815,0:06:33.053
during the summer as a faculty fellow.

0:06:33.053,0:06:36.466
And they already had[br]a six legged robot called LEMUR.

0:06:36.466,0:06:39.003
So, this is actually based on that.

0:06:39.297,0:06:40.820
So, it's a hexapod robot.

0:06:40.820,0:06:42.760
We developed our adaptive gait planner.

0:06:42.760,0:06:45.330
We actually have a very interesting[br]payload on there.

0:06:45.330,0:06:47.044
The students like to have fun.

0:06:47.044,0:06:49.280
It shows very interesting mobility,

0:06:49.280,0:06:53.456
and here you can see that it's walking[br]over a structured terrain.

0:06:53.456,0:06:56.731
It's little bit difficult to see,[br]in the videos over here,

0:06:56.731,0:07:00.143
it's trying to walk[br]on the coastal terrain, sandy area,

0:07:00.143,0:07:04.887
but depending on the moisture content[br]or the grain size of the sand

0:07:04.887,0:07:07.640
the foot's soil sinkage model changes.

0:07:07.710,0:07:09.427
So, it tries to adapt its gait

0:07:09.427,0:07:12.158
to successfully cross over[br]these kind of things.

0:07:12.158,0:07:14.627
It also does some fun stuff,[br]as you can imagine.

0:07:14.627,0:07:16.953
We get so many visitors visiting our lab.

0:07:16.953,0:07:19.801
So, when the visitors come,[br]MARS walks up to the computer,

0:07:19.801,0:07:21.985
starts typing "Hello, my name is MARS.

0:07:21.985,0:07:23.266
Welcome to RoMeLa,

0:07:23.266,0:07:26.361
the Robotics Mechanisms Laboratory[br]at Virginia Tech."

0:07:28.202,0:07:30.448
This robot is an amoeba robot.

0:07:30.448,0:07:33.292
Now, we don't have enough time[br]to go into technical details,

0:07:33.292,0:07:35.934
I'll just show you some[br]of the experiments.

0:07:35.935,0:07:38.512
So, this is some of the early[br]feasibility experiments.

0:07:38.512,0:07:41.857
We store potential energy[br]to the elastic skin to make it move.

0:07:41.857,0:07:45.500
Or use active tension cords[br]to make it move forward and backward.

0:07:45.500,0:07:50.166
We've also been working with scientists[br]and engineers from UPenn

0:07:50.166,0:07:53.765
to come up with a chemically[br]actuated version of this Amoeba robot.

0:07:53.775,0:07:56.200
We do something to something,

0:07:56.200,0:08:00.548
and just like magic, it moves. The blob.

0:08:02.086,0:08:03.997
It's called ChIMERA.

0:08:04.106,0:08:06.130
This robot is a very recent project.

0:08:06.130,0:08:07.691
It's called RAPHaEL.

0:08:07.691,0:08:10.239
Robotic Air Powered Hand[br]with Elastic Ligaments.

0:08:10.239,0:08:14.020
There are a lot of really neat, very good[br]robotic hands out there in the market.

0:08:14.020,0:08:17.422
The problem is they're just too expensive,[br]tens of thousands of dollars.

0:08:17.422,0:08:20.459
So, for prosthesis applications[br]it's probably not too practical,

0:08:20.459,0:08:22.209
because it's not affordable.

0:08:22.209,0:08:25.367
We wanted to go tackle this problem[br]in a very different direction.

0:08:25.367,0:08:28.533
Instead of using electrical motors,[br]electromechanical actuators,

0:08:28.533,0:08:30.280
we're using compressed air.

0:08:30.280,0:08:32.973
We developed these[br]novel actuators for joints.

0:08:32.973,0:08:35.368
It is compliant.[br]You can actually change the force,

0:08:35.368,0:08:37.490
simply just changing the air pressure.

0:08:37.490,0:08:39.759
And it can actually crush[br]an empty soda can.

0:08:39.759,0:08:43.059
It can pick up very delicate objects[br]like a raw egg,

0:08:43.059,0:08:45.211
or in this case, a lightbulb.

0:08:45.211,0:08:48.909
The best part, it took only $200 dollars[br]to make the first prototype.

0:08:49.946,0:08:53.054
This robot is actually[br]a family of snake robots

0:08:53.054,0:08:54.421
that we call HyDRAS,

0:08:54.421,0:08:57.112
Hyper Degrees-of-freedom[br]Robotic Articulated Serpentine.

0:08:57.112,0:09:00.331
The one that you see over here -[br]you can see it outdoors in the lobby

0:09:00.331,0:09:03.367
we actually have a demo,[br]please stop by during the break time.

0:09:03.367,0:09:05.494
This is a robot that can climb structures.

0:09:05.494,0:09:07.488
This is a HyDRAS's arm.

0:09:07.488,0:09:09.493
It's a 12 degrees of freedom robotic arm.

0:09:09.493,0:09:11.724
But the cool part is the user interface.

0:09:11.724,0:09:14.554
The cable over there,[br]that's an optical fiber.

0:09:14.554,0:09:16.969
And this student,[br]probably the first time using it,

0:09:16.969,0:09:19.166
but she can articulate[br]it many different ways.

0:09:19.166,0:09:21.564
So, for example in Iraq,[br]you know, the war zone,

0:09:21.564,0:09:23.038
there is roadside bombs.

0:09:23.038,0:09:26.774
Currently you send these remotely[br]controlled vehicles that are armed.

0:09:26.774,0:09:29.081
It takes really a lot of time[br]and it's expensive

0:09:29.081,0:09:32.278
to train the operator[br]to operate this complex arm.

0:09:32.512,0:09:34.247
In this case it's very intuitive;

0:09:34.247,0:09:36.465
this student, probably[br]his first time using it,

0:09:36.465,0:09:38.478
doing very complex manipulation tasks,

0:09:38.478,0:09:42.005
picking up objects and doing manipulation,[br]just like that.

0:09:42.810,0:09:44.100
Very intuitive.

0:09:46.066,0:09:48.634
Now, this robot is currently[br]our star robot.

0:09:48.634,0:09:51.835
We actually have a fan club[br]for the robot, DARwIn:

0:09:51.835,0:09:54.624
Dynamic Anthropomorphic Robot[br]with Intelligence.

0:09:54.624,0:09:58.040
As you know, we are very interested[br]in human walking,

0:09:58.040,0:10:00.543
so we decided to build[br]a small humanoid robot.

0:10:00.543,0:10:02.349
This was in 2004; at that time,

0:10:02.349,0:10:04.326
this was something really revolutionary.

0:10:04.326,0:10:06.153
This was more of a feasibility study:

0:10:06.153,0:10:07.819
What kind of motors should we use?

0:10:07.819,0:10:10.507
Is it even possible?[br]What kinds of controls should we do?

0:10:10.507,0:10:12.267
So, this does not have any sensors.

0:10:12.267,0:10:13.976
So, it's an open loop control.

0:10:13.976,0:10:16.742
For those who probably know,[br]if you don't have any sensors

0:10:16.742,0:10:19.699
and there are any disturbances,[br]you know what happens.

0:10:20.126,0:10:21.950
(Laughter)

0:10:21.950,0:10:24.590
So, based on that success,[br]the following year

0:10:24.590,0:10:26.780
we did the proper mechanical design

0:10:26.780,0:10:28.344
starting from kinematics.

0:10:28.344,0:10:30.962
And thus, DARwIn I was born in 2005.

0:10:30.962,0:10:33.603
It stands up, it walks - very impressive.

0:10:33.603,0:10:36.799
However, still, as you can see,[br]it has a cord, umbilical cord.

0:10:36.799,0:10:39.060
So, we're still using[br]an external power source

0:10:39.060,0:10:41.264
and external computation.

0:10:41.896,0:10:44.929
So, in 2006, now it's really[br]time to have fun.

0:10:44.929,0:10:46.487
Let's give it intelligence.

0:10:46.487,0:10:48.560
We give it all the computing power[br]it needs:

0:10:48.560,0:10:50.192
a 1.5 gigahertz Pentium M chip,

0:10:50.192,0:10:52.581
two FireWire cameras,[br]rate gyros, accelerometers,

0:10:52.581,0:10:55.342
four force sensors on the foot,[br]lithium polymer batteries.

0:10:55.342,0:10:58.957
And now DARwIn II[br]is completely autonomous.

0:10:58.957,0:11:00.761
It is not remote controlled.

0:11:00.761,0:11:03.722
There are no tethers. It looks around,[br]searches for the ball,

0:11:03.722,0:11:07.612
looks around, searches for the ball,[br]and it tries to play a game of soccer,

0:11:07.612,0:11:10.203
autonomously: artificial intelligence.

0:11:10.541,0:11:14.188
Let's see how it does.[br]This was our very first trial, and...

0:11:14.188,0:11:17.474
(Video): Spectators: Goal!

0:11:18.998,0:11:22.171
Dennis Hong: So, there is actually[br]a competition called RoboCup.

0:11:22.171,0:11:24.747
I don't know how many of you[br]have heard about RoboCup.

0:11:24.747,0:11:29.087
It's an international autonomous[br]robot soccer competition.

0:11:29.087,0:11:31.955
And the goal of RoboCup,[br]the actual goal is,

0:11:31.955,0:11:33.883
by the year 2050

0:11:33.883,0:11:37.935
we want to have full size,[br]autonomous humanoid robots

0:11:37.935,0:11:40.902
play soccer against[br]the human World Cup champions

0:11:40.902,0:11:42.256
and win.

0:11:42.939,0:11:45.523
It's a true actual goal.[br]It's a very ambitious goal,

0:11:45.523,0:11:47.728
but we truly believe that we can do it.

0:11:47.728,0:11:49.706
So, this is last year in China.

0:11:49.706,0:11:52.688
We were the very first team[br]in the United States that qualified

0:11:52.688,0:11:54.824
in the humanoid RoboCup competition.

0:11:54.824,0:11:56.945
This is this year in Austria.

0:11:56.945,0:11:59.659
You're going to see the action,[br]three against three,

0:11:59.659,0:12:01.635
completely autonomous.

0:12:01.635,0:12:03.204
There you go. Yes!

0:12:04.598,0:12:06.126
The robots track and they

0:12:06.126,0:12:08.308
team play amongst themselves.

0:12:08.918,0:12:11.320
It's very impressive.[br]It's really a research event

0:12:11.320,0:12:15.159
packaged in a more exciting[br]competition event.

0:12:16.893,0:12:19.060
What you see over here,[br]this is the beautiful

0:12:19.060,0:12:20.844
Louis Vuitton Cup trophy.

0:12:20.844,0:12:22.523
So, this is for the best humanoid,

0:12:22.523,0:12:25.179
and we would like to bring this[br]for the very first time,

0:12:25.179,0:12:27.419
to the United States next year,[br]so wish us luck.

0:12:27.419,0:12:28.631
(Applause)

0:12:28.631,0:12:29.842
Thank you.

0:12:32.124,0:12:34.045
DARwIn also has a lot of other talents.

0:12:34.045,0:12:37.876
Last year it actually conducted[br]the Roanoke Symphony Orchestra

0:12:37.876,0:12:40.300
for the holiday concert.

0:12:40.300,0:12:43.013
This is the next generation robot,[br]DARwIn IV,

0:12:43.013,0:12:46.351
but smarter, faster, stronger.

0:12:46.351,0:12:48.505
And it's trying to show off its ability:

0:12:48.505,0:12:50.940
"I'm macho, I'm strong.

0:12:51.757,0:12:54.146
I can also do some Jackie Chan-motion,

0:12:54.146,0:12:56.000
martial art movements."

0:12:56.000,0:12:57.908
(Laughter)

0:12:59.314,0:13:01.299
And it walks away.[br]So, this is DARwIn IV.

0:13:01.299,0:13:03.332
And again, you'll be able[br]to see it in the lobby.

0:13:03.332,0:13:05.668
We truly believe this is going to be[br]the very first

0:13:05.668,0:13:08.446
running humanoid robot[br]in the United States, so, stay tuned.

0:13:08.446,0:13:12.306
All right. So I showed you some[br]of our exciting robots at work.

0:13:12.306,0:13:14.456
So, what is the secret of our success?

0:13:14.456,0:13:16.275
Where do we come up with these ideas?

0:13:16.275,0:13:18.166
How do we develop these kinds of ideas?

0:13:18.166,0:13:20.500
We win awards after awards,[br]year after year.

0:13:20.500,0:13:23.556
We're actually running out of wall space[br]to put these plaques,

0:13:23.556,0:13:26.970
they're staring to accumulate on the floor[br]hopefully we didn't loose any.

0:13:26.970,0:13:29.376
These are just the awards[br]that we won in 2007 fall

0:13:29.376,0:13:31.976
from robotics competitions[br]and those kinds of things.

0:13:31.976,0:13:33.950
So, really, we have five secrets.

0:13:33.950,0:13:36.594
First is: Where do we get inspiration?

0:13:36.594,0:13:38.633
Where do we get this spark of imagination?

0:13:38.633,0:13:40.555
This is a true story, my personal story.

0:13:40.555,0:13:42.652
At night when I go to bed, 3 - 4 a.m.

0:13:42.652,0:13:46.165
I lie down, close my eyes,[br]and I see these lines and circles

0:13:46.165,0:13:47.975
and different shapes floating around.

0:13:47.975,0:13:50.839
And they assemble, and they form[br]these kinds of mechanisms.

0:13:50.839,0:13:52.558
And then I think, "Ah this is cool."

0:13:52.558,0:13:54.747
So, right next to my bed[br]I keep a notebook,

0:13:54.747,0:13:57.888
a journal, with a special pen[br]that has a light on it, LED light,

0:13:57.888,0:14:00.821
because I don't want to turn on[br]the light and wake up my wife.

0:14:00.821,0:14:04.161
So, I see this, scribble everything down,[br]draw things, and I go to bed.

0:14:04.161,0:14:05.710
Every day in the morning,

0:14:05.710,0:14:08.106
the first thing I do[br]before my first cup of coffee,

0:14:08.106,0:14:10.293
before I brush my teeth,[br]I open my notebook.

0:14:10.293,0:14:11.860
Many times it's empty,

0:14:11.860,0:14:14.699
sometimes I have something there -[br]sometimes it's junk

0:14:14.699,0:14:17.264
but most of the time[br]I can't even read my handwriting.

0:14:17.264,0:14:19.718
And so, 4 in the morning,[br]what do you expect, right?

0:14:19.718,0:14:21.611
So, I need to decipher what I wrote.

0:14:21.611,0:14:24.815
But sometimes I see[br]this ingenious idea in there,

0:14:24.815,0:14:26.585
and I have this eureka moment.

0:14:26.585,0:14:29.099
I directly run to my home office,[br]sit at my computer,

0:14:29.099,0:14:31.017
I type in the ideas, I sketch things out

0:14:31.017,0:14:33.017
and I keep a database of ideas.

0:14:33.706,0:14:36.182
So, when we have these[br]calls for proposals,

0:14:36.182,0:14:40.320
I try to find a match between[br]my potential ideas and the problem.

0:14:40.320,0:14:42.625
If there is a match[br]we write a research proposal,

0:14:42.625,0:14:46.184
get the research funding in, and that's[br]how we start our research programs.

0:14:46.184,0:14:48.970
But just a spark of imagination[br]is not good enough.

0:14:48.970,0:14:51.037
How do we develop these kinds of ideas?

0:14:51.037,0:14:53.820
At our lab RoMeLa, the Robotics[br]and Mechanisms Laboratory,

0:14:53.820,0:14:56.454
we have these fantastic[br]brainstorming sessions.

0:14:56.454,0:14:59.002
So, we gather around,[br]we discuss about problems

0:14:59.002,0:15:02.217
and solutions to the problems[br]and talk about it.

0:15:02.217,0:15:05.441
But before we start[br]we set this golden rule.

0:15:05.441,0:15:06.856
The rule is:

0:15:06.856,0:15:09.906
Nobody criticizes anybody's ideas.

0:15:09.906,0:15:12.182
Nobody criticizes any opinion.

0:15:12.182,0:15:14.906
This is important, because many times[br]students, they fear

0:15:14.906,0:15:17.656
or they feel uncomfortable[br]how others might think

0:15:17.656,0:15:19.765
about their opinions and thoughts.

0:15:19.765,0:15:21.696
So, once you do this, it is amazing

0:15:21.696,0:15:23.173
how the students open up.

0:15:23.173,0:15:26.303
They have these wacky, cool,[br]crazy, brilliant ideas,

0:15:26.303,0:15:29.778
and the whole room is just electrified[br]with creative energy.

0:15:29.778,0:15:32.326
And this is how we develop our ideas.

0:15:32.871,0:15:34.419
Well, we're running out of time.

0:15:34.419,0:15:36.275
One more thing I want to talk about is,

0:15:36.275,0:15:39.419
you know, just a spark of idea[br]and development is not good enough.

0:15:39.419,0:15:41.058
There was a great TED moment,

0:15:41.058,0:15:43.987
I think it was Sir Ken Robinson, was it?

0:15:43.987,0:15:45.974
He gave a talk about how education

0:15:45.974,0:15:48.303
and school kills creativity.

0:15:48.303,0:15:50.594
Well, actually, there are[br]two sides to the story.

0:15:52.020,0:15:54.635
So, there is only so much one can do

0:15:54.635,0:15:56.521
with just ingenious ideas

0:15:56.521,0:15:59.666
and creativity and good[br]engineering intuition.

0:15:59.666,0:16:01.531
If you want to go beyond a tinkering,

0:16:01.531,0:16:03.649
if you want to go beyond[br]a hobby of robotics

0:16:03.649,0:16:07.000
and really tackle the grand challenges[br]of robotics

0:16:07.000,0:16:09.569
through rigorous research[br]we need more than that.

0:16:09.569,0:16:11.429
This is where school comes in.

0:16:11.526,0:16:13.817
Batman, fighting against bad guys,

0:16:13.817,0:16:16.340
he has his utility belt,[br]he has his grappling hook,

0:16:16.340,0:16:18.347
he has all different kinds of gadgets.

0:16:18.347,0:16:20.809
For us roboticists,[br]engineers and scientists,

0:16:20.809,0:16:24.672
these tools, these are the courses[br]and classes you take in class.

0:16:24.672,0:16:26.834
Math, differential equations.

0:16:26.834,0:16:29.744
I have linear algebra, science, physics,

0:16:29.744,0:16:32.589
even nowadays, chemistry[br]and biology, as you've seen.

0:16:32.589,0:16:34.904
These are all the tools that we need.

0:16:34.904,0:16:36.848
So, the more tools you have, for Batman,

0:16:36.848,0:16:38.795
more effective at fighting the bad guys,

0:16:38.795,0:16:41.478
for us, more tools to attack[br]these kinds of big problems.

0:16:42.510,0:16:44.629
So, education is very important.

0:16:45.373,0:16:48.121
Also, it's not about that,[br]only about that.

0:16:48.121,0:16:50.255
You also have to work really, really hard.

0:16:50.255,0:16:51.745
So, I always tell my students,

0:16:51.745,0:16:53.830
"Work smart, then work hard."

0:16:53.830,0:16:56.483
This picture in the back[br]this is 3 in the morning.

0:16:56.483,0:16:59.090
I guarantee if you come[br]to your lab at 3 - 4 am

0:16:59.090,0:17:00.687
we have students working there,

0:17:00.687,0:17:03.860
not because I tell them to,[br]but because we are having too much fun.

0:17:03.860,0:17:05.460
Which leads to the last topic:

0:17:05.460,0:17:07.366
Do not forget to have fun.

0:17:07.366,0:17:10.606
That's really the secret of our success,[br]we're having too much fun.

0:17:10.606,0:17:14.135
I truly believe that highest productivity[br]comes when you're having fun,

0:17:14.135,0:17:15.541
and that's what we're doing.

0:17:15.541,0:17:17.122
Again, we're running out of time.

0:17:17.122,0:17:20.511
Hopefully I'll have another chance[br]to talk to you about and introduce

0:17:20.511,0:17:24.196
some other exciting robotics projects[br]that we didn't have time to talk about.

0:17:24.196,0:17:26.272
We have a fully autonomous vehicle

0:17:26.272,0:17:28.203
that can drive into urban environments.

0:17:28.203,0:17:31.078
We won a half a million dollars[br]in the DARPA Urban Challenge.

0:17:31.078,0:17:32.769
We also have the world's very first

0:17:32.769,0:17:34.675
vehicle that can be driven by the blind.

0:17:34.675,0:17:37.242
We call it the Blind Driver Challenge,[br]very exciting.

0:17:37.242,0:17:40.867
And many, many other robotics projects[br]I want to talk about.

0:17:40.867,0:17:43.532
There you go.[br]Go out there, read a great book.

0:17:43.532,0:17:46.658
Get inspired, invent, work really hard.

0:17:46.885,0:17:48.544
Stay in school.

0:17:48.544,0:17:51.772
Come up with cool ideas,[br]I'll be happy to learn more about [them].

0:17:51.772,0:17:54.106
Shoot me an email, let's talk about it.

0:17:54.106,0:17:56.073
There you go. Thank you so much.

0:17:56.073,0:17:58.443
(Applause)