Return to Video

My seven species of robot -- and how we created them

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

more » « less
Video Language:
English
Team:
TED
Project:
TEDTalks
Duration:
15:57

English subtitles

Revisions Compare revisions