4 lessons from robots about being human
-
0:01 - 0:03I know this is going to sound strange,
-
0:03 - 0:08but I think robots can inspire us
to be better humans. -
0:09 - 0:12See, I grew up in Bethlehem, Pennsylvania,
-
0:12 - 0:14the home of Bethlehem Steel.
-
0:15 - 0:17My father was an engineer,
-
0:17 - 0:21and when I was growing up,
he would teach me how things worked. -
0:21 - 0:24We would build projects together,
-
0:24 - 0:26like model rockets and slot cars.
-
0:27 - 0:30Here's the go-kart that we built together.
-
0:30 - 0:32That's me behind the wheel,
-
0:32 - 0:34with my sister and my best
friend at the time. -
0:36 - 0:38And one day,
-
0:38 - 0:41he came home, when I was
about 10 years old, -
0:41 - 0:44and at the dinner table, he announced
-
0:44 - 0:47that for our next project,
we were going to build ... -
0:47 - 0:48a robot.
-
0:50 - 0:51A robot.
-
0:51 - 0:53Now, I was thrilled about this,
-
0:53 - 0:57because at school,
there was a bully named Kevin, -
0:57 - 0:59and he was picking on me,
-
0:59 - 1:01because I was the only
Jewish kid in class. -
1:02 - 1:04So I couldn't wait to get
started to work on this, -
1:04 - 1:07so I could introduce Kevin to my robot.
-
1:07 - 1:08(Laughter)
-
1:08 - 1:12(Robot noises)
-
1:18 - 1:19(Laughter)
-
1:19 - 1:23But that wasn't the kind of robot
my dad had in mind. -
1:23 - 1:24(Laughter)
-
1:24 - 1:28See, he owned a chromium-plating company,
-
1:28 - 1:33and they had to move heavy steel parts
between tanks of chemicals. -
1:33 - 1:37And so he needed
an industrial robot like this, -
1:37 - 1:39that could basically do the heavy lifting.
-
1:40 - 1:43But my dad didn't get
the kind of robot he wanted, either. -
1:44 - 1:46He and I worked on it for several years,
-
1:46 - 1:51but it was the 1970s, and the technology
that was available to amateurs -
1:51 - 1:52just wasn't there yet.
-
1:54 - 1:57So Dad continued to do
this kind of work by hand. -
1:58 - 1:59And a few years later,
-
2:00 - 2:01he was diagnosed with cancer.
-
2:04 - 2:05You see,
-
2:05 - 2:08what the robot we were trying
to build was telling him -
2:08 - 2:10was not about doing the heavy lifting.
-
2:10 - 2:11It was a warning
-
2:11 - 2:14about his exposure to the toxic chemicals.
-
2:15 - 2:17He didn't recognize that at the time,
-
2:18 - 2:19and he contracted leukemia.
-
2:20 - 2:22And he died at the age of 45.
-
2:23 - 2:25I was devastated by this.
-
2:26 - 2:28And I never forgot the robot
that he and I tried to build. -
2:30 - 2:34When I was at college, I decided
to study engineering, like him. -
2:35 - 2:40And I went to Carnegie Mellon,
and I earned my PhD in robotics. -
2:40 - 2:42I've been studying robots ever since.
-
2:43 - 2:47So what I'd like to tell you about
are four robot projects, -
2:47 - 2:50and how they've inspired me
to be a better human. -
2:54 - 3:00By 1993, I was a young professor at USC,
-
3:00 - 3:03and I was just building up
my own robotics lab, -
3:03 - 3:06and this was the year
the World Wide Web came out. -
3:06 - 3:09And I remember my students
were the ones who told me about it, -
3:09 - 3:12and we would -- we were just amazed.
-
3:12 - 3:15We started playing with this,
and that afternoon, -
3:15 - 3:20we realized that we could use
this new, universal interface -
3:20 - 3:24to allow anyone in the world
to operate the robot in our lab. -
3:25 - 3:29So, rather than have it fight
or do industrial work, -
3:30 - 3:33we decided to build a planter,
-
3:33 - 3:35put the robot into the center of it,
-
3:35 - 3:37and we called it the Telegarden.
-
3:38 - 3:42And we had put a camera
in the gripper of the hand of the robot, -
3:42 - 3:45and we wrote some
special scripts and software, -
3:45 - 3:47so that anyone in the world could come in,
-
3:47 - 3:49and by clicking on the screen,
-
3:49 - 3:53they could move the robot around
and visit the garden. -
3:53 - 3:57But we also set up some other software
-
3:57 - 4:01that lets you participate
and help us water the garden, remotely. -
4:02 - 4:04And if you watered it a few times,
-
4:04 - 4:06we'd give you your own seed to plant.
-
4:07 - 4:11Now, this was an engineering project,
-
4:11 - 4:15and we published some papers
on the system design of it, -
4:15 - 4:17but we also thought of it
as an art installation. -
4:19 - 4:21It was invited, after the first year,
-
4:21 - 4:24by the Ars Electronica Museum in Austria,
-
4:24 - 4:27to have it installed in their lobby.
-
4:28 - 4:32And I'm happy to say, it remained
online there, 24 hours a day, -
4:32 - 4:33for almost nine years.
-
4:34 - 4:38That robot was operated by more people
-
4:38 - 4:40than any other robot in history.
-
4:41 - 4:43Now, one day,
-
4:43 - 4:46I got a call out of the blue
from a student, -
4:47 - 4:51who asked a very simple
but profound question. -
4:52 - 4:55He said, "Is the robot real?"
-
4:57 - 4:59Now, everyone else had assumed it was,
-
4:59 - 5:01and we knew it was,
because we were working with it. -
5:01 - 5:03But I knew what he meant,
-
5:03 - 5:04because it would be possible
-
5:04 - 5:07to take a bunch of pictures
of flowers in a garden -
5:07 - 5:11and then, basically, index them
in a computer system, -
5:11 - 5:13such that it would appear
that there was a real robot, -
5:13 - 5:15when there wasn't.
-
5:15 - 5:17And the more I thought about it,
-
5:17 - 5:20I couldn't think of a good answer
for how he could tell the difference. -
5:21 - 5:23This was right about the time
that I was offered a position -
5:23 - 5:25here at Berkeley.
-
5:25 - 5:26And when I got here,
-
5:26 - 5:29I looked up Hubert Dreyfus,
-
5:29 - 5:32who's a world-renowned
professor of philosophy, -
5:33 - 5:35And I talked with him
about this and he said, -
5:35 - 5:39"This is one of the oldest
and most central problems in philosophy. -
5:39 - 5:43It goes back to the Skeptics
and up through Descartes. -
5:44 - 5:47It's the issue of epistemology,
-
5:47 - 5:50the study of how do we know
that something is true." -
5:51 - 5:53So he and I started working together,
-
5:53 - 5:56and we coined a new term:
"telepistemology," -
5:57 - 5:59the study of knowledge at a distance.
-
5:59 - 6:04We invited leading artists,
engineers and philosophers -
6:04 - 6:05to write essays about this,
-
6:05 - 6:09and the results are collected
in this book from MIT Press. -
6:10 - 6:12So thanks to this student,
-
6:12 - 6:15who questioned what everyone else
had assumed to be true, -
6:15 - 6:19this project taught me
an important lesson about life, -
6:19 - 6:22which is to always question assumptions.
-
6:24 - 6:26Now, the second project
I'll tell you about -
6:26 - 6:28grew out of the Telegarden.
-
6:28 - 6:31As it was operating, my students
and I were very interested -
6:31 - 6:33in how people were interacting
with each other, -
6:33 - 6:35and what they were doing with the garden.
-
6:35 - 6:36So we started thinking:
-
6:36 - 6:38what if the robot could leave the garden
-
6:38 - 6:41and go out into some other
interesting environment? -
6:41 - 6:44Like, for example,
what if it could go to a dinner party -
6:44 - 6:46at the White House?
-
6:46 - 6:47(Laughter)
-
6:48 - 6:52So, because we were interested
more in the system design -
6:52 - 6:55and the user interface
than in the hardware, -
6:55 - 6:56we decided that,
-
6:56 - 7:01rather than have a robot replace
the human to go to the party, -
7:01 - 7:03we'd have a human replace the robot.
-
7:04 - 7:05We called it the Tele-Actor.
-
7:06 - 7:08We got a human,
-
7:08 - 7:11someone who's very
outgoing and gregarious, -
7:11 - 7:15and she was outfitted with a helmet
with various equipment, -
7:15 - 7:17cameras and microphones,
-
7:17 - 7:20and then a backpack with wireless
Internet connection. -
7:21 - 7:23And the idea was that she could go
-
7:23 - 7:26into a remote and interesting environment,
-
7:26 - 7:28and then over the Internet,
-
7:28 - 7:30people could experience
what she was experiencing. -
7:31 - 7:34So they could see what she was seeing,
-
7:34 - 7:37but then, more importantly,
they could participate, -
7:37 - 7:42by interacting with each other
and coming up with ideas -
7:42 - 7:46about what she should do next
and where she should go, -
7:46 - 7:48and then conveying those
to the Tele-Actor. -
7:49 - 7:51So we got a chance to take the Tele-Actor
-
7:52 - 7:54to the Webby Awards in San Francisco.
-
7:55 - 7:58And that year, Sam Donaldson was the host.
-
8:00 - 8:03Just before the curtain went
up, I had about 30 seconds -
8:03 - 8:07to explain to Mr. Donaldson
what we were going to do. -
8:08 - 8:12And I said, "The Tele-Actor
is going to be joining you onstage. -
8:12 - 8:14This is a new experimental project,
-
8:14 - 8:17and people are watching her
on their screens, -
8:17 - 8:20there's cameras involved
and there's microphones -
8:20 - 8:22and she's got an earbud in her ear,
-
8:22 - 8:24and people over the network
are giving her advice -
8:24 - 8:25about what to do next."
-
8:25 - 8:27And he said, "Wait a second.
-
8:28 - 8:29That's what I do."
-
8:29 - 8:34(Laughter)
-
8:34 - 8:36So he loved the concept,
-
8:36 - 8:40and when the Tele-Actor walked onstage,
she walked right up to him, -
8:40 - 8:43and she gave him a big kiss
right on the lips. -
8:43 - 8:45(Laughter)
-
8:45 - 8:48We were totally surprised --
we had no idea that would happen. -
8:48 - 8:50And he was great, he just gave her
a big hug in return, -
8:50 - 8:52and it worked out great.
-
8:52 - 8:54But that night, as we were packing up,
-
8:54 - 8:59I asked the Tele-Actor,
how did the Tele-Directors decide -
8:59 - 9:02that they would give
a kiss to Sam Donaldson? -
9:03 - 9:05And she said they hadn't.
-
9:05 - 9:08She said, when she was
just about to walk onstage, -
9:08 - 9:11the Tele-Directors still were trying
to agree on what to do, -
9:11 - 9:14and so she just walked onstage
and did what felt most natural. -
9:14 - 9:19(Laughter)
-
9:19 - 9:22So, the success
of the Tele-Actor that night -
9:22 - 9:26was due to the fact
that she was a wonderful actor. -
9:26 - 9:28She knew when to trust her instincts.
-
9:28 - 9:32And so that project taught me
another lesson about life, -
9:32 - 9:36which is that, when in doubt, improvise.
-
9:36 - 9:38(Laughter)
-
9:39 - 9:44Now, the third project
grew out of my experience -
9:44 - 9:45when my father was in the hospital.
-
9:47 - 9:51He was undergoing a treatment --
chemotherapy treatments -- -
9:51 - 9:55and there's a related treatment
called brachytherapy, -
9:55 - 9:59where tiny, radioactive seeds
are placed into the body -
9:59 - 10:01to treat cancerous tumors.
-
10:02 - 10:04And the way it's done,
as you can see here, -
10:04 - 10:08is that surgeons
insert needles into the body -
10:08 - 10:10to deliver the seeds.
-
10:10 - 10:14And all these needles
are inserted in parallel. -
10:14 - 10:20So it's very common that some
of the needles penetrate sensitive organs. -
10:21 - 10:28And as a result, the needles damage
these organs, cause damage, -
10:28 - 10:30which leads to trauma and side effects.
-
10:31 - 10:32So my students and I wondered:
-
10:32 - 10:37what if we could modify the system,
-
10:37 - 10:39so that the needles
could come in at different angles? -
10:40 - 10:42So we simulated this;
-
10:42 - 10:46we developed some optimization
algorithms and we simulated this. -
10:46 - 10:47And we were able to show
-
10:47 - 10:49that we are able to avoid
the delicate organs, -
10:49 - 10:55and yet still achieve the coverage
of the tumors with the radiation. -
10:55 - 10:59So now, we're working with doctors at UCSF
-
10:59 - 11:01and engineers at Johns Hopkins,
-
11:01 - 11:05and we're building a robot
that has a number of -- -
11:05 - 11:08it's a specialized design
with different joints -
11:08 - 11:12that can allow the needles to come in
at an infinite variety of angles. -
11:12 - 11:16And as you can see here,
they can avoid delicate organs -
11:16 - 11:19and still reach the targets
they're aiming for. -
11:20 - 11:25So, by questioning this assumption
that all the needles have to be parallel, -
11:25 - 11:28this project also taught me
an important lesson: -
11:28 - 11:33When in doubt, when your path
is blocked, pivot. -
11:34 - 11:38And the last project
also has to do with medical robotics. -
11:38 - 11:42And this is something
that's grown out of a system -
11:42 - 11:45called the da Vinci surgical robot.
-
11:46 - 11:48And this is a commercially
available device. -
11:48 - 11:51It's being used in over 2,000
hospitals around the world. -
11:52 - 11:56The idea is it allows the surgeon
to operate comfortably -
11:56 - 11:58in his own coordinate frame.
-
12:01 - 12:07Many of the subtasks in surgery are very
routine and tedious, like suturing, -
12:07 - 12:09and currently, all of these are performed
-
12:09 - 12:13under the specific and immediate
control of the surgeon. -
12:13 - 12:16So the surgeon becomes fatigued over time.
-
12:16 - 12:18And we've been wondering,
-
12:18 - 12:22what if we could program the robot
to perform some of these subtasks, -
12:22 - 12:23and thereby free the surgeon
-
12:23 - 12:27to focus on the more complicated
parts of the surgery, -
12:27 - 12:29and also cut down on the time
that the surgery would take -
12:29 - 12:32if we could get the robot
to do them a little bit faster? -
12:33 - 12:36Now, it's hard to program a robot
to do delicate things like this. -
12:37 - 12:41But it turns out my colleague
Pieter Abbeel, who's here at Berkeley, -
12:41 - 12:47has developed a new set of techniques
for teaching robots from example. -
12:47 - 12:50So he's gotten robots to fly helicopters,
-
12:50 - 12:53do incredibly interesting,
beautiful acrobatics, -
12:53 - 12:55by watching human experts fly them.
-
12:56 - 12:58So we got one of these robots.
-
12:58 - 13:01We started working with Pieter
and his students. -
13:01 - 13:05And we asked a surgeon
to perform a task -- -
13:07 - 13:08with the robot.
-
13:08 - 13:11So what we're doing is asking
the surgeon to perform the task, -
13:11 - 13:13and we record the motions of the robot.
-
13:13 - 13:14So here's an example.
-
13:14 - 13:18I'll use tracing out
a figure eight as an example. -
13:18 - 13:22So here's what it looks like
when the robot -- -
13:22 - 13:25this is what the robot's path
looks like, those three examples. -
13:25 - 13:29Now, those are much better
than what a novice like me could do, -
13:29 - 13:32but they're still jerky and imprecise.
-
13:32 - 13:35So we record all these examples, the data,
-
13:35 - 13:38and then go through a sequence of steps.
-
13:38 - 13:41First, we use a technique
called dynamic time warping -
13:41 - 13:43from speech recognition.
-
13:43 - 13:46And this allows us to temporally
align all of the examples. -
13:47 - 13:52And then we apply Kalman filtering,
a technique from control theory, -
13:52 - 13:55that allows us to statistically
analyze all the noise -
13:55 - 13:59and extract the desired
trajectory that underlies them. -
14:01 - 14:04Now we take those human demonstrations --
-
14:04 - 14:06they're all noisy and imperfect --
-
14:06 - 14:08and we extract from them
an inferred task trajectory -
14:08 - 14:11and control sequence for the robot.
-
14:11 - 14:13We then execute that on the robot,
-
14:14 - 14:16we observe what happens,
-
14:16 - 14:17then we adjust the controls,
-
14:17 - 14:20using a sequence of techniques
called iterative learning. -
14:21 - 14:25Then what we do is we increase
the velocity a little bit. -
14:25 - 14:28We observe the results,
adjust the controls again, -
14:29 - 14:31and observe what happens.
-
14:31 - 14:33And we go through this several rounds.
-
14:33 - 14:35And here's the result.
-
14:35 - 14:37That's the inferred task trajectory,
-
14:37 - 14:40and here's the robot
moving at the speed of the human. -
14:40 - 14:42Here's four times the speed of the human.
-
14:42 - 14:44Here's seven times.
-
14:45 - 14:50And here's the robot operating
at 10 times the speed of the human. -
14:51 - 14:54So we're able to get a robot
to perform a delicate task -
14:54 - 14:57like a surgical subtask,
-
14:57 - 14:59at 10 times the speed of a human.
-
15:00 - 15:02So this project also,
-
15:02 - 15:05because of its involved
practicing and learning, -
15:05 - 15:07doing something over and over again,
-
15:07 - 15:09this project also has a lesson, which is:
-
15:09 - 15:12if you want to do something well,
-
15:13 - 15:18there's no substitute
for practice, practice, practice. -
15:21 - 15:25So these are four of the lessons
that I've learned from robots -
15:25 - 15:26over the years.
-
15:27 - 15:33And the field of robotics
has gotten much better over time. -
15:34 - 15:37Nowadays, high school students
can build robots, -
15:37 - 15:40like the industrial robot
my dad and I tried to build. -
15:41 - 15:43But, it's very -- now ...
-
15:44 - 15:47And now, I have a daughter,
-
15:48 - 15:49named Odessa.
-
15:50 - 15:51She's eight years old.
-
15:52 - 15:53And she likes robots, too.
-
15:54 - 15:55Maybe it runs in the family.
-
15:55 - 15:57(Laughter)
-
15:57 - 15:59I wish she could meet my dad.
-
16:00 - 16:03And now I get to teach her
how things work, -
16:03 - 16:05and we get to build projects together.
-
16:05 - 16:09And I wonder what kind of lessons
she'll learn from them. -
16:10 - 16:14Robots are the most human of our machines.
-
16:15 - 16:18They can't solve all
of the world's problems, -
16:18 - 16:21but I think they have something
important to teach us. -
16:22 - 16:24I invite all of you
-
16:24 - 16:28to think about the innovations
that you're interested in, -
16:29 - 16:31the machines that you wish for.
-
16:32 - 16:34And think about
what they might be telling you. -
16:35 - 16:39Because I have a hunch that many
of our technological innovations, -
16:39 - 16:41the devices we dream about,
-
16:42 - 16:45can inspire us to be better humans.
-
16:46 - 16:47Thank you.
-
16:47 - 16:49(Applause)
- Title:
- 4 lessons from robots about being human
- Speaker:
- Ken Goldberg
- Description:
-
The more that robots ingrain themselves into our everyday lives, the more we're forced to examine ourselves as people. At TEDxBerkeley, Ken Goldberg shares four very human lessons that he's learned from working with robots. (Filmed at TEDxBerkeley.)
- Video Language:
- English
- Team:
- closed TED
- Project:
- TEDTalks
- Duration:
- 17:09
Krystian Aparta commented on English subtitles for 4 lessons from robots about being human | ||
Krystian Aparta edited English subtitles for 4 lessons from robots about being human | ||
Krystian Aparta edited English subtitles for 4 lessons from robots about being human | ||
Krystian Aparta edited English subtitles for 4 lessons from robots about being human | ||
Morton Bast edited English subtitles for 4 lessons from robots about being human | ||
Morton Bast edited English subtitles for 4 lessons from robots about being human | ||
Thu-Huong Ha approved English subtitles for 4 lessons from robots about being human | ||
Thu-Huong Ha accepted English subtitles for 4 lessons from robots about being human |
Krystian Aparta
The English transcript was updated on 5/9/2016.