FacebookTwitterYoutubeInstagramGoogle Plus

Roboticist Chad Jenkins’s career started with the Atari 2600 video game, and after tinkering with other games, he began a new career creating robots that can sense, plan, and act in ways that are useful to humans.

Episode filmed live at the 2014 World Science Festival in New York CIty. The full Cool Jobs program from that year can be viewed online.

View Additional Video Information

Morgan Jenkins:

Hi. Before I introduce my dad, let me introduce myself. I’m Morgan Jenkins and I have grown up around robots. Why? Because my dad has a cool job. We are lucky that my dad gets to bring home some of his work for us to see. But when I go to my dad’s office, that is when I get to see the big, cool robots like the PR2. But we have to be careful because the PR2 costs as much as some houses. One time, we helped the PR2 build block towers. I’ve also seen the PR2 deliver sodas from one place to another, which I think everyone would want at their house.

Chad Jenkins:

Hi Morgan.

Morgan Jenkins:

Hi dad. I’ll let you take it from here.

Chad Jenkins:

Thank you very much. So, hi, my name is Chad Jenkins. I’m an Associate Professor of Computer Science, where we get to work with some of the coolest robots on the planet and beyond. These robots can roll, walk, fly, run, grab things, follow people, deliver, but still can’t do most of what we want them to do. And our job is to write more and more sophisticated computer programs that allow robots to do more for people, to do the things we want them to do. But this isn’t just a cool jobs talk, this is a recruitment talk. We actually need your help to make robots a future, robotics a reality for the future. And so we need you to learn how to program, just like us, and so we’re going to try and get you to program through this talk.

Chad Jenkins:

When I was a kid like Morgan, and like many of you out there, there were no robots. Robots were purely science fiction. Not only that, there were no computers or video games either until the day my parents changed my life, December 25th, 1981, when they brought home this, the Atari 2600 video game console … yeah … with the Space Invaders cartridge. Even back then, we hooked up to the TV set like you do now, but most TV sets back then were only black and white. We didn’t necessarily have color. I spent a lot of my time playing video games like this. I spent endless hours doing this. These games might seem simplistic or even lame by today’s standards, but it was totally cool for 1981, and just scratching the surface of what we could do today. And so I played games like this one too. So this is Kaboom. I played a lot of that to the detriment of my grades and other things. I just was fascinated, I was awed by these games.

Chad Jenkins:

So if you flash forward to today, so it was 30 years later when I actually have a real job, I can actually make those same games. So the games that my parents used to go Sears and pay $30 for, are the games that I can now make myself within a day or two and not only that, I can share them with people, I share them with Morgan. I waste the time of the people in my lab by sharing these games with them and I can do that all on my own. And the question that you should ask yourself, if, how did I get to this point? Well, I got this point through having a great education and that education is represented by the books that are on my bookshelf.

Chad Jenkins:

I essentially learned computer science, which is how I learned how to program and understand how computers work, math and physics, which lets me make games that move and look realistic just like it does in the real world or at least something that’s believable enough, a little bit about electronics, so I understood how computers worked at their lowest level, computer graphics so I could make interactive 3D worlds, computer vision so I can enable robots and computers to see things in the real world, computer vision didn’t show up, there we go, and robotics to make machines move in the actual, real physical world. So using this knowledge, what I was able to do is make my own video games and technology. So as a student, what you’re seeing is an early project that I did. I just made a virtual baseball game. So I could see the world, I had immersive head-mounted display that let me see the world, it was an image projected directly on top of my eyes. I had a bat I could swing and so it was a real immersive experience. It felt like I was actually swinging the bat.

Chad Jenkins:

We made a racing game where we could drive the car by essentially moving our hand in front of a camera. Believe it or not, that was state of the art for 1997. So now we have Wiis and Kinects, but that was a big deal back then. We took that system even further to be able to not just track the hand, but even track the body. So we use the tracking of the body to control a physically simulated humanoid robot. And then we took that system even further by enabling a person to control a robot, a real physical robot, directly using their body. And so what you’re seeing right here is Nathan controlling the NASA Robonaut, so an early version of the NASA Robonaut. The Robonaut Version 2 is actually on the International Space Station right now.

Chad Jenkins:

But you can try to move like the robot, if you want to. It’s actually makes a really interesting dance, not like the Dougie, but like the Nathan, which is kind of cool. But you could think of those little devices on his arms and sort of like Wemos before there were Wemos. We wanted the robot to not just copy your emotion, but actually be able to interact with you like a partner. So we basically had systems that can now track you and then could see and recognize a person and then we’d use that recognition to be able to have a robot follow a person. And we essentially use as well as states Hooke’s Law to be able to do this.

Chad Jenkins:

So that was really great when quadrotor helicopters started to become really, really, really… We could start to buy them off the shelf and we could use them for our regular research and so what you’re seeing here is Evan with the AR drone. And so what we’re able to do is there’s a frontward facing camera on the robot, and it can see an ARTag, which is called an augmented reality tag. And from that camera, we can essentially have the robot follow that person. And so we want to show you just a quick little programming demo of it because we want you to be able to do this for yourself. And with that, I will hand it over to Alice.

Alice:

Great. So can we have a volunteer from the audience? Okay. So what’s your name?

Simon:

My name is Simon.

Alice:

Simon. Thanks for being willing to help us today. Stand right here. So what you’re going to help us demonstrate is the simulation of a drone following an ARTag. So if you take the mouse and click on the ARTag and drag it around and drag it all over the screen. Great. So we see how the drone is following the ARTag and it follows at a set distance as if it’s connected with a virtual spring. So the program that makes this happen is going to be available to you. I’m going to show you. There it is. On the left side, that’s the code. And on the right side is the drone and the ARTag, And this is in JSFiddle. So go ahead, you can move it again.

Alice:

So these are the same settings as the first time I showed you. Now, what I’m going to do is show you that we can change the properties of a spring. So first we’re going to make the spring stiffer. So I’m going to make this from 0.05 to 0.5 and then click over here on run. So now let’s see how the stiffness has changed. Great. So now when we move the ARTag, the drone actually gets connected with a rigid spring, a really stiff spring that doesn’t stretch hardly at all. So again, this is something you can do at home. You can just open it up in your web browser. Thanks a lot, Simon.

Chad Jenkins:

Science is really about doing for yourself, right? You should never trust anything anybody says unless you can do it yourself. Now is a good time to figure out how to learn how to program because that can be very easily programmed in and we’re just going to show you a few quick examples of that. And so earlier last week, Morgan just sat down and said, “Here’s Hooke’s Law,” and she just programmed into Scratch. So many of you may be familiar with Scratch. That program is everything that you need to do to have essentially the Scratch cat follow your mouse cursor.

Chad Jenkins:

Also, the drone simulation that we had as Alice pointed out, is available on our website ProgramsFor.Me. And also I wanted to just finish up by saying that we want to reemphasize that you don’t need the ARTag, right? You can have the robot essentially follow you by recognizing where you are and we’re just using a regular old Microsoft Kinect camera and that camera is being used to follow [inaudible 00:09:12] around as you saw in that video and I think that’s a really amazing video. I think you should pay a lot of attention to that video. There we go.

Speaker 5:

PR2, can you stop here?

Chad Jenkins:

Thank you, [inaudible 00:09:34]. Just to reemphasize, science is about seeing for yourself, never trust a video. And so I think that just sort of highlights what we can do. So what we’re aiming for is by the time Morgan is my age, that we actually make robots a reality. Robots are no longer purely finance fiction. Robots are real and they’re here today and what we’re trying to find new ways to make robots more useful for people. And you are the future scientist engineers who will make the breakthroughs and develop the technology that we all use in the future.

Chad Jenkins:

Someday, robots, like the PR2, will be as common as computers, and we need your help to make that future a reality. What makes my job really cool is I get to help you make that reality and so what we need you to do is be able to learn how to program. All the examples that we have are free, available for you to use, learn from, do it better and show us how we can make robots a reality. And so for myself, Morgan, all the people in my group, we want to really invite you to come be one of us and help science move ahead and make robots a reality. Thank you very much.

Leave a Reply

Your email address will not be published. Required fields are marked *

ERROR: si-captcha.php plugin: GD image support not detected in PHP!

Contact your web host and ask them to enable GD image support for PHP.

ERROR: si-captcha.php plugin: imagepng function not detected in PHP!

Contact your web host and ask them to enable imagepng for PHP.

View More Comments
Load More

COOL JOBS: Robot Senser

Roboticist Chad Jenkins’s career started with the Atari 2600 video game, and after tinkering with other games, he began a new career creating robots that can sense, plan, and act in ways that are useful to humans.

Episode filmed live at the 2014 World Science Festival in New York CIty. The full Cool Jobs program from that year can be viewed online.

Transcription

Morgan Jenkins:

Hi. Before I introduce my dad, let me introduce myself. I’m Morgan Jenkins and I have grown up around robots. Why? Because my dad has a cool job. We are lucky that my dad gets to bring home some of his work for us to see. But when I go to my dad’s office, that is when I get to see the big, cool robots like the PR2. But we have to be careful because the PR2 costs as much as some houses. One time, we helped the PR2 build block towers. I’ve also seen the PR2 deliver sodas from one place to another, which I think everyone would want at their house.

Chad Jenkins:

Hi Morgan.

Morgan Jenkins:

Hi dad. I’ll let you take it from here.

Chad Jenkins:

Thank you very much. So, hi, my name is Chad Jenkins. I’m an Associate Professor of Computer Science, where we get to work with some of the coolest robots on the planet and beyond. These robots can roll, walk, fly, run, grab things, follow people, deliver, but still can’t do most of what we want them to do. And our job is to write more and more sophisticated computer programs that allow robots to do more for people, to do the things we want them to do. But this isn’t just a cool jobs talk, this is a recruitment talk. We actually need your help to make robots a future, robotics a reality for the future. And so we need you to learn how to program, just like us, and so we’re going to try and get you to program through this talk.

Chad Jenkins:

When I was a kid like Morgan, and like many of you out there, there were no robots. Robots were purely science fiction. Not only that, there were no computers or video games either until the day my parents changed my life, December 25th, 1981, when they brought home this, the Atari 2600 video game console … yeah … with the Space Invaders cartridge. Even back then, we hooked up to the TV set like you do now, but most TV sets back then were only black and white. We didn’t necessarily have color. I spent a lot of my time playing video games like this. I spent endless hours doing this. These games might seem simplistic or even lame by today’s standards, but it was totally cool for 1981, and just scratching the surface of what we could do today. And so I played games like this one too. So this is Kaboom. I played a lot of that to the detriment of my grades and other things. I just was fascinated, I was awed by these games.

Chad Jenkins:

So if you flash forward to today, so it was 30 years later when I actually have a real job, I can actually make those same games. So the games that my parents used to go Sears and pay $30 for, are the games that I can now make myself within a day or two and not only that, I can share them with people, I share them with Morgan. I waste the time of the people in my lab by sharing these games with them and I can do that all on my own. And the question that you should ask yourself, if, how did I get to this point? Well, I got this point through having a great education and that education is represented by the books that are on my bookshelf.

Chad Jenkins:

I essentially learned computer science, which is how I learned how to program and understand how computers work, math and physics, which lets me make games that move and look realistic just like it does in the real world or at least something that’s believable enough, a little bit about electronics, so I understood how computers worked at their lowest level, computer graphics so I could make interactive 3D worlds, computer vision so I can enable robots and computers to see things in the real world, computer vision didn’t show up, there we go, and robotics to make machines move in the actual, real physical world. So using this knowledge, what I was able to do is make my own video games and technology. So as a student, what you’re seeing is an early project that I did. I just made a virtual baseball game. So I could see the world, I had immersive head-mounted display that let me see the world, it was an image projected directly on top of my eyes. I had a bat I could swing and so it was a real immersive experience. It felt like I was actually swinging the bat.

Chad Jenkins:

We made a racing game where we could drive the car by essentially moving our hand in front of a camera. Believe it or not, that was state of the art for 1997. So now we have Wiis and Kinects, but that was a big deal back then. We took that system even further to be able to not just track the hand, but even track the body. So we use the tracking of the body to control a physically simulated humanoid robot. And then we took that system even further by enabling a person to control a robot, a real physical robot, directly using their body. And so what you’re seeing right here is Nathan controlling the NASA Robonaut, so an early version of the NASA Robonaut. The Robonaut Version 2 is actually on the International Space Station right now.

Chad Jenkins:

But you can try to move like the robot, if you want to. It’s actually makes a really interesting dance, not like the Dougie, but like the Nathan, which is kind of cool. But you could think of those little devices on his arms and sort of like Wemos before there were Wemos. We wanted the robot to not just copy your emotion, but actually be able to interact with you like a partner. So we basically had systems that can now track you and then could see and recognize a person and then we’d use that recognition to be able to have a robot follow a person. And we essentially use as well as states Hooke’s Law to be able to do this.

Chad Jenkins:

So that was really great when quadrotor helicopters started to become really, really, really… We could start to buy them off the shelf and we could use them for our regular research and so what you’re seeing here is Evan with the AR drone. And so what we’re able to do is there’s a frontward facing camera on the robot, and it can see an ARTag, which is called an augmented reality tag. And from that camera, we can essentially have the robot follow that person. And so we want to show you just a quick little programming demo of it because we want you to be able to do this for yourself. And with that, I will hand it over to Alice.

Alice:

Great. So can we have a volunteer from the audience? Okay. So what’s your name?

Simon:

My name is Simon.

Alice:

Simon. Thanks for being willing to help us today. Stand right here. So what you’re going to help us demonstrate is the simulation of a drone following an ARTag. So if you take the mouse and click on the ARTag and drag it around and drag it all over the screen. Great. So we see how the drone is following the ARTag and it follows at a set distance as if it’s connected with a virtual spring. So the program that makes this happen is going to be available to you. I’m going to show you. There it is. On the left side, that’s the code. And on the right side is the drone and the ARTag, And this is in JSFiddle. So go ahead, you can move it again.

Alice:

So these are the same settings as the first time I showed you. Now, what I’m going to do is show you that we can change the properties of a spring. So first we’re going to make the spring stiffer. So I’m going to make this from 0.05 to 0.5 and then click over here on run. So now let’s see how the stiffness has changed. Great. So now when we move the ARTag, the drone actually gets connected with a rigid spring, a really stiff spring that doesn’t stretch hardly at all. So again, this is something you can do at home. You can just open it up in your web browser. Thanks a lot, Simon.

Chad Jenkins:

Science is really about doing for yourself, right? You should never trust anything anybody says unless you can do it yourself. Now is a good time to figure out how to learn how to program because that can be very easily programmed in and we’re just going to show you a few quick examples of that. And so earlier last week, Morgan just sat down and said, “Here’s Hooke’s Law,” and she just programmed into Scratch. So many of you may be familiar with Scratch. That program is everything that you need to do to have essentially the Scratch cat follow your mouse cursor.

Chad Jenkins:

Also, the drone simulation that we had as Alice pointed out, is available on our website ProgramsFor.Me. And also I wanted to just finish up by saying that we want to reemphasize that you don’t need the ARTag, right? You can have the robot essentially follow you by recognizing where you are and we’re just using a regular old Microsoft Kinect camera and that camera is being used to follow [inaudible 00:09:12] around as you saw in that video and I think that’s a really amazing video. I think you should pay a lot of attention to that video. There we go.

Speaker 5:

PR2, can you stop here?

Chad Jenkins:

Thank you, [inaudible 00:09:34]. Just to reemphasize, science is about seeing for yourself, never trust a video. And so I think that just sort of highlights what we can do. So what we’re aiming for is by the time Morgan is my age, that we actually make robots a reality. Robots are no longer purely finance fiction. Robots are real and they’re here today and what we’re trying to find new ways to make robots more useful for people. And you are the future scientist engineers who will make the breakthroughs and develop the technology that we all use in the future.

Chad Jenkins:

Someday, robots, like the PR2, will be as common as computers, and we need your help to make that future a reality. What makes my job really cool is I get to help you make that reality and so what we need you to do is be able to learn how to program. All the examples that we have are free, available for you to use, learn from, do it better and show us how we can make robots a reality. And so for myself, Morgan, all the people in my group, we want to really invite you to come be one of us and help science move ahead and make robots a reality. Thank you very much.