SciCafe: Swarms of Aerial Robots
SciCafe: When Black Holes Collide - Transcript
Vijay Kumar (Dean and Professor, School of Engineering, University of Pennsylvania):
Really great to be here. It's an honor to be here, and thank you all for coming, especially the newcomers.
What I thought I would do is talk a little bit about my work. When I say my work, I really refer to my students' work on aerial robot swarms. Is anyone here from the FAA? If you are, this was shot in South America.
No, but this is the city of Philadelphia, and what we do is try to create smart, intelligent robots like this. I want to tell you a little bit about the work we do and give you a flavor of some of the excitement, some of the challenges in this field.
I was told that this is a scientifically oriented audience, a geeky audience, so I want to get into a few details and tell you a little bit about why we think of these as robots as opposed to what other people call them, drones or unmanned aerial vehicles. Tell you how we think about autonomous control, how we think about autonomy. And a big problem that we face is this challenge of state estimation, which is figuring out where you are in the real world. And then think about how to get robots to cooperate, and then give you a sense for why we do what we're doing.
So unmanned aerial vehicles. We've been working on this for about 15 years now, and I want to show you this picture which illustrates the number of unmanned aerial vehicles and how it's grown over the years. This is a picture in 2010, and the smaller vehicles that I'm going to talk to you about, we started playing around with these in 2005. You can see the exponential growth in these vehicles. In the 1980s we did not have commercial GPS, and therefore it was really hard to develop autonomous flying robots.
So in 2010, people said, well, this is going to be a $10 billion industry and people projected all kinds of uses. But it was primarily military uses. It was about surveillance, about spying, force protection, warfare—all the kinds of things that many of us are not really interested in. Certainly, from a scientific standpoint, these don't present the challenges or the potential for impact; no pun on that word.
The FAA famously predicted that we'll have 15,000 civilian drones by 2020. So fast forward five years, and now they are all over the place. I don't have to explain to anyone what an unmanned aerial vehicle is or what a drone is. And going back to the number of 15,000, 15,000 drones were sold in a single month last year, per month. And people estimate that over a million drones were sold just in December in the Christmas season.
So it's a $15 billion industry already, and again, people make famous predictions that it's going to grow to $20 billion, $25 billion by 2020. And you know that that number is also going to be wrong.
But what's exciting now is that the applications have grown to areas that we never imagined. So agriculture, inspecting different aspects of our civilian infrastructure, border patrols, photography, construction and so on. So it's really grown to be a very exciting field.
Of course, different people call them different things. We prefer to use the word aerial robots, because robots we think of as being smart, able to make their own decisions and so on. The military calls them remotely piloted vehicles, because in fact, they're not drones. There are human beings that are controlling these vehicles every step of the way. So it's actually a misnomer to call them drones. But of course, the popular press and all of us call them drones. So to me, they're all now pretty much the same thing.
It seemed appropriate to show this picture in this museum. You think about the evolution of aerial robots, and we are just starting. And really, we want to be further along. In my lab, we look at what I call the five S's of aerial robotics.
So the first S is we want to make them small. And I'll give you some motivation for that. You can imagine if you want to navigate an environment of humans, you want to be small. You want to be able to maneuver. You want to go through doorways. You want to go across rubble in buildings. So we are looking for making them small.
We also want to make them safe. Clearly, we don't want something banging into humans causing harm, so therefore we're trying to make them as safe as possible.
Smart, this is an obvious thing. If you're building a robot you want it to be smart. We also want these robots to move quickly. I don't know how many of you watched the Nova episode just last week on robotics. All of those videos of robots that you saw were fast-forwarded. So we want to create robots that you actually have to slow them down to actually see what happens, just like NFL replays. So those are the kinds of robots we're shooting for. And then finally, we think about swarms, so that's the fifth S in our vernacular.
So having just given you a flavor of the kinds of problems we're interested in, I want to tell you a little bit about how we think about autonomous control. First, you're trying to control something which really lives in six dimensions. There's three positions and three orientations that you have to simultaneously control. So you might think in terms of X, Y, Z variables. You might think in terms of roll pitch and your angles. Some of you may prefer to think of them in terms of a matrix, which is what we do, a rotation matrix.
But the bottom line is, you're trying to control six things. And a robot like this has four rotors, and you only have four inputs. You have four motors and you're trying to control with these four motors six different things. The system is under-actuated. It's sort of an unfair problem mathematically because you're trying to do six things with only four inputs.
So these robots are called quad rotors because they have four rotors. Even if you add more rotors you are fundamentally under-actuated. And so we spend a lot of time just attacking this problem.
The second thing we do is think about how to design software that runs in real time. So I'm showing you a picture here. I'm just trying to impress you with a blog diagram, but the thing I want to get to you is the fact that you have these feedback loops. So if you look at the inner most feedback loop you will see that it operates at roughly a millisecond. That means every millisecond the robot is estimating its rotation, its attitude in the real world and its velocity, and trying to regulate that to get the precise orientation it wants.
So then the intermediate feedback loop in the middle, you're feeding back positon and velocity, and that operates roughly at 10 milliseconds. And then finally, the outermost loop, you're thinking about trajectories in the real world and how to plan trajectories, and that operates roughly at 100 milliseconds.
So those are the three levels of intelligence that need to be built into the system. And although all of our students are engineers, they spend 80 percent of their time thinking about software. So therefore, they also become computer scientists in this field.
Just going back to where these computations actually happen. The most critical things are the computations that happen onboard. These are the orientation calculations to figure out how to control the orientation. Some of the other computations actually don't happen to happen onboard. So if you look at the position, sometimes we get estimates of positions from external cameras, and those computations can actually happen off board. In fact, a lot of the trajectory planning software that we write and test in the lab happens on a laptop like mine.
Today we hear a lot about cloud infrastructure. Well, we use the cloud infrastructure to run real time control loops for vehicles like this as they maneuver through the environment.
We try to make these robots as small as possible. This is work of Yosh [indiscernible 8:31]. This is the smallest robot we've built. It's only 11 centimeters tip to tip. It has a max speed of about six meters per second. And in terms of the size and the velocity, in terms of body lengths per second, it is equivalent to a Boeing 787 flying 50 times the speed of sound. So it actually flies pretty fast for something this small.
By making it small, we automatically make it safe. And by making it small, we also make it more maneuverable, as I'll explain in a minute. The inspiration from this really comes from nature. So if you look at honeybees, for example, they're extremely small. They've very maneuverable. In fact, unlike all the big robots we build, they don't even think about avoiding collisions.
So for us, the nightmare is, we build this big behemoth, and the first thing we think about is, we don't want to bump into other features in the environment, bump into each other. Well, you look at these honeybees and they love collisions, because by colliding, they learn. So by contacting your neighbor you actually know who your neighbor is and you know a little bit about your environment. So we'd love to be able to create robots of this scale.
In our lab, we actually think about how to scale things down. Here you see Daniel Mellinger on the top, and then on the bottom, work of Yosh. And that's the sound of the robots. You can see that one of the things you notice is that when the robots become small, they're able to respond more quickly to perturbations. In fact, we can show through scaling laws that the maximum acceleration you can get goes as one over the characteristic length. In other words, you make a robot half the size and their ability to maneuver and the rotational direction doubles.
Likewise, the robustness, which we call the basin of attraction, grows dramatically as you shrink the size of the vehicle. This might be counterintuitive. All of us who fly on large aircrafts prefer those to smaller turboprops, but the turboprops or the large aircrafts are never subject to perturbations like this. If you want to respond to collisions and react to them and be robust to them, you really want to think about sizing things that are much smaller, and that's what we try to do.
Anecdotally, when we first started working on this we realized we needed to have a first aid kit, so we started buying Band-Aids and things like that. If you plot a histogram of Band-Aids over the years, now it's tailed off when we moved to these little guys, people don't get hurt, which is great.
And this is, again, 1/20th speed, probably the first planned mid-air collision, and vehicles bumping into each other and recovering from these collisions. These robots are traveling at roughly two meters per second, walking speed. So imagine one person standing still and you walk right into that person. You feel the impact. Well, these robots feel it, but they're able to recover from it quite spontaneously.
So that's the advantage of size. In terms of figuring out how to plan these motions, we think a lot about how to represent the dynamics of these vehicles. So if you look on the right hand side, there's this huge vector of things that the robot stores—its position, its velocity, its rotation, its angle of velocity. And we think of clever ways in which to abstract from this a smaller dimensional representation, which consists only of the positon and the orientation, the heading angle, much like you would when you drive a car. When you drive a car you think of your position in the road and you think of the angle of the car, and that's roughly what you see in this left hand side picture.
If you work in the smaller abstraction, then you can think about planning trajectories in that space that are safe, and then some fancy mathematics that ensures that these trajectories are as smooth as possible. So again, the intuition is, if you have lots of inertia, you don't want your trajectories to be jerky. You want them to be smooth. We try to minimize what is called a snap, which is the fourth derivative of positon over time. So the derivative is velocity, second is acceleration, third is jerk, fourth is snap. You can also do crackle and pop, but we don't. But we try to minimize that and then find the right trajectory. So that's the essence of the planning problem.
Once you do that in the simpler space, which is the problem in computational geometry, then we transform this over into this more complex space and then we execute them. And that's basically what you see in these videos. You see the robot going through these planned obstacles. So if the robot knows where the obstacles are, it can plan these minimum snap trajectories at a fraction of a second, often 20, 30 times a second. And it doesn't matter if the obstacle is moving. If the robot knows how the obstacle is moving, it can determine how to plan trajectories to go through the obstacle. So this is a bread and butter for all planning algorithms that we use.
Some of you may have seen videos of birds fishing to catch their prey, and this is amazing. Look at this bird coordinating its flight, its vision and so on, and its claws. We try to do the same thing with robots. So here's a robot fishing for Philly cheesesteak hoagies, and it's able to pick that out. So again, we focus on the split second timing, coordinating vision, coordinating arms, coordinating hands, and flight as you fly through complex environments.
Then finally, work of Sarah Tang, where she's able to use this framework to think about transporting suspended payloads whose length is more than the height of the window. So you have to figure out how to get the momentum of the object to be such that the suspended payload swings through first before the robot actually goes through it. So these calculations look complicated, but by abstracting the dynamics of the simplest space, we're able to solve this in real time and then feed it to the robot.
And then lastly, this problem of trying to perch in complex environments. Again, you want to perch to save energy, to rest. And the challenge for us is to purge on vertical surfaces. So we have a gripper which is made out of a dry adhesive. I call these the Spiderman claws, and they're able to hold onto flat surfaces; a gripper designed by colleagues at Stanford at Mark Cutkosky's lab. And again, this framework allows us to land on any vertical surface, or any tilted surface for that matter, at just the right velocity to achieve perching. So we're able to get autonomy in a wide variety of settings. Not just in flight, but also perching, grasping and things of that nature.
I want to tell you a little bit about the problem of state estimation. Everything I've shown you thus far we have cheated. We have cheated in the following way. In the lab, our robots are equipped with motion capture cameras and reflective markers. So the cameras see the reflective markers and they compute the position of the robot a hundred to two hundred times a second, and then deliver that information to the robot.
The robot knows where it is at all times. It's like having GPS on steroids. You know exactly where you are, and unlike in the city when you're going around and you lose GPS, here you never lose GPS. So this gives the robots an unfair advantage and they'd be able to do all the things that you just saw with amazing precision.
In the real world, and here's a typical building on the Penn campus, it becomes really challenging. Without external cameras you don't know where you are. In fact, in this building, GPS doesn't work. My cellphone doesn't work. We barely get Wi-Fi coverage. So how do you get robots to localize in complex environments like this?
So we work a lot on this problem, and I want to show you a prototype that was built by a former student who is now a professor at Hong Kong University of Science and Technology, [indiscernible]. The system he built consists of two forward facing cameras, and you can see the GPS receiver on top. You can see a laser scanner, which is this orange band on the top. And then there's a downward facing camera, too, which you don't see.
So this package allows the vehicle to sense features in the environment and determine where it is relative to those features. Then as it moves, much like humans, when we walk we're looking at things in the environment. We take steps. We know roughly how far we've walked. And then we look at how these features are flying past our retina. We integrate that motion to then figure out where we are in the real world. And that's what this robot is able to do.
Here you'll see work of [indiscernible 17:55] that essentially takes this information coming from the robots and it's able to construct the three dimensional maps. This is just outside our lab. You can see it build high resolution maps at five centimeter resolution, and how it's entering the lab as you can see, with all the clutter. And the bottom, you see the map that it's building and you'll see that the color of the objects that it sees is overlaid on this map.
So this is now leading to "smart." And it's not really smart in the sense that it's not making any intelligent decisions in this particular experiment. But it's smart enough now that it's able to perceive the environment and represent it in terms of this three dimensional map.
Which is a great starting point. Imagine being outside a building and then deploying the vehicle inside the building where you have a complete picture of what's inside the building. You know something about its structural integrity. If there's an active shooter in the building you can probably detect that shooter. And if there are victims in the building you can localize and tell rescue workers where they are. So this basic technology, while it might not appear to be very smart to us, is actually smart enough to do lots of useful things.
Here's the same type of technology, an outdoor flight. Many of us have now heard about Amazon and Google wanting to deliver packages to our doorstep. This, in theory, works. It works when you are flying at let's say 400 feet, just at the FAA ceiling, where GPS is clear and you're relatively unobstructed. But what happens when you get to features such as trees, where your GPS might not work? And in our case, when you have cameras, the cameras might not have enough illumination to function.
So we look at combinations of sensors, as you see on the top left. And at every instant, the robot is able to estimate its error. So if you see that ellipsoid in the middle, this is not unlike the ellipsoid you see in your Google maps which tells you the error in your position. So the vehicle not only calculates where it is, it's also able to tell the software what its estimate of the error is. And as it goes around this complex, indoor and outdoor, using lasers indoors where cameras and GPS don't work, and outdoors in bright sunlight where the camera doesn't work but maybe GPS works, it's able to navigate its way through a fairly complex environment.
So is a half a kilometer flight at roughly walking speed, and it's able to do all of this autonomously. So this is a very important technology as you sort of get close to human build environments, like buildings or trees that just happen to grow since the last time you were there. So you need to detect that. You have to react to it and then behave in a safe way. So that's another form of smart.
So one problem that we run into is that these vehicles burn a lot of power. So if you look at rotor crafts, they burn roughly 200 watts per kilo. That's a lot. That's like four light bulbs for every kilo of payload you carry. And part of the problem is that all this hardware I've shown you is actually quite heavy. The cameras are about 80 grams, the laser range finder is about 370 grams. Our Intel processor of the board is about 200 grams. So you add all of this up, not only are you burning power to power the devices, you're also burning power just to carry these devices.
So a big challenge for us is to actually limit the power consumption. If you don't limit the power consumption you have to carry bigger batteries, and if you carry bigger batteries that's extra payload and you're burning even more power. All the things I've been telling you about, being small, being safe, that goes right out the window because your devices keep getting bigger.
So this is a big challenge for us. But consumer electronics sometimes comes to the rescue. So if you ask yourself the question, what is an inexpensive device that you can buy today that has sensing and computing in a lightweight package and low power, of course it's your smart phone. So we started asking the question, could we build something that's powered exclusively through smart phones?
So we came up with this idea of a flown. So you buy an off-the-shelf, in this case Samsung Galaxy S5 phone, and you download our app. And then you buy a USB cable—and make sure the USB cable is as small as possible because you want to limit the weight—and you plug it into a drone. This just happens to be the robot that we built, but it will work with most drones. Then you can actually power the device using a smart phone.
So I want to show you—this is Giuseppe [indiscernible] work, and show you the robot that he built, where this phone is actually taking pictures of everything it sees in the environment 30 times a second, calculating features in the environment, estimating distance to the features, and from that, estimating its position.
So all the computation and all the sensing is done onboard using the phone's camera, the phone's processor and the phones inertial measurement unit, which is basically a system of accelerometers and gyros that measure accelerations and angular accelerations.
So this is in collaboration with Qualcomm, but you can see three meters per section autonomous flight, all planned by Giuseppe through his software. And of course, you can get it to do whatever you want, and you can just imagine, you can take the mother of all selfies if you position it wherever you want. So this give us some hope that you can actually build really lightweight devices with off-the-shelf hardware. So it's inexpensive, lightweight, and also safe.
The other S-word I talk about is speed. So this is what we'd like to be able to do. This is actually being driven by an expert pilot. Imagine again responding to 911 calls and getting there and responding to things quickly, finding out where the bad guys are. We'd like to be able to do this autonomously. There's only one small segment of this, and I'll show you this in a minute, where the flight is autonomous.
So this piece, flying down the hallway. This is about three or four meters per second, maybe a little more than that. So we know how to do that autonomously. But navigating these bends at high speeds and going up and down the stairs, these are things we're still working on. But that is something we'd like to do before this then becomes an effective tool that we might imagine using in a search and rescue and first response.
Finally, I'd like to talk a little bit about cooperative control, where we look at the problem of how to get all of these robots to collaborate and do something useful. And of course, once again, we're inspired by nature. So this is a picture with half a million to a million starlings off the coast of Denmark, and you can see them form these incredible patterns in the sky. To my knowledge, they don't use a whole lot of mathematics to do this, but mathematics is the tool that we have at our disposal. So to really be inspired by nature, and then work with tools that we know to create these kinds of behaviors.
Instead of trying to mimic them, what we have tried to do is, instead, understand some basic organizing principles that we believe allows us to accomplish these kinds of movements. So it's not just about flight. I want to also show you examples of physical interactions.
So on the bottom left we see ants spontaneously forming bridges to escape from wetlands to drier lands. In the middle, you can see ants cooperatively carrying objects, and they carry this object back to their nest. They think it's food. The reason they think it's food is because this plastic object we created is coated with the juice from figs, so they think it's food and they carry it back to their nest. But this allows us to study cooperation. This is actually an elastic disk, so it allows us to see which ants are pulling, as you can see on the top, and which ants are pushing at the bottom. You can also see which ants are not doing anything. They're just goofing off and they're there for the light.
But it's really intriguing how these ants spontaneously form teams and are able to accomplish these incredibly complex tasks. At least from a robotics standpoint, these are very complex tasks.
So again, the organizing principle is, first, each bird acts independently. So we want robots to think about being completely autonomous and being self-contained.
Second, we'd really like them to work with local information. There is no way in a room like this, if we had to make decisions, that we wait for consensus to emerge and do something as a group. Maybe that's what the government does today. That's why we don't do anything. But it's very hard to achieve that. So you really have to work based on what you know locally, and then act based on that.
The third idea is also fairly simple. This notion of anonymity. We want individuals to be agnostic to who their neighbors are. So if you think about a completely altruistic society of robots, then the robots shouldn't care who their neighbors are. We want them to collaborate and be exactly the same way, independent of the specificity of who they're surrounded by.
So we try to incorporate all of these elements into our software. I want to take three clips from a recent Nova episode, actually it's two years ago, that illustrate these three elements. And all these three episodes, the main character is David Pogue, who writes for The New York Times. You could see here that he's demonstrating the first idea. This is Katie Powers' work, where she has encoded these leader/follower behaviors into the robots.
So the first robot is literally hijacked by David Pogue, and he is able to manipulate it. The other robots are basically responding to their neighbors. And they don't care that one of them has actually been lifted up by a human being and is moving it. They're just reacting to the position.
The simple idea here is that a single individual can actually manipulate, maybe not quite a swarm, but in principle a swarm. So the control computations that have to be done don't scale with the number of robots. It's just the same computations you'd have to do if you just had a single robot. And then everything else follows, because every robot is following a leader, and then that robot has another leader and so on and so forth.
The second idea is this concept of anonymity, Matt Turpin's work. And here you could see that the robots have been asked to form a circular pattern. They know the patter that they have to form, but again, they are agnostic to their specific neighbors. They're agnostic to even the number of robots on the team. So as long as they know where the pattern has to be formed and what the shape of the pattern is, they're able to find their place, adjust their spacing with respect to their neighbors.
And now we're beginning to see something that might resemble the pattern formation that we saw in the starlings. Admittedly, for a very simple circular pattern, but still, doing them autonomously without worrying about the number of robots on the team.
Then finally, you see some of these things put together where the pattern actually changes shape, starting with a rectangle, then into an ellipse, into a straight line, back into a circle. In all of these computations, a programmer is essentially telling the robots what patterns to form by giving the robots different shapes as a function of time. And the robots figure out which robot needs to be where in order to describe the shape and they adapt to the commands.
So you could see how these kinds of algorithms might be used now for half a million robots if we had them. And if there was a place we could do these kinds of experiments, these algorithms would scale to those large numbers.
I want to talk a little bit about why we're doing what we're doing, besides creating these cool videos and publishing them on YouTube. And of course, everybody loves those, but ultimately, we're interested in solving some real problems.
The first problem area that we're very excited about is agriculture. If you look at the challenges facing society, you quickly come to the conclusion that water and food, and actually these challenges are related, are our number one challenge. The efficiency of almost all production systems in the world has gone up over time, but for food it's actually going down for a variety of reasons.
So one thing we're really interested in is trying to see how we can use robots to monitor and tend crops. Here's our robot flying in an apple orchard carrying all kinds of sensors. And they're able to, in this environment, do fairly simple things. On the bottom left, they're gathering infrared information. On the bottom right, they're building three dimensional maps of apple trees. And in the center, they're computing an index called NDVI. So each of these pieces of information is useful in order to assess the health of a plan.
So for instance, if you know something about the size of the plan, if you have a three dimensional map, you can fly by that plan week to week and measure the state of growth, and you can estimate how healthy it is. If you look at this NDVI, the central thing, that essentially tells you something about the vigor of the plan. Something even more basic, flying past these plants we can count apples and we can estimate the yield on the plants.
In this video, you see two other robots flying with this robot, and we do this because we oftentimes have a very small window to do our operations, and we'd like to cover large areas while we do that. That's where this notion of swarms comes in. But something as simple as telling the farmer how many apples he or she has on the farm helps them estimate the yield of that farm, and helps them plan for downstream picking, harvesting and then shipping; something quite basic with every manufacturing facility has, but farmers don't have.
So thinking about the efficiency of food production, this is a very simple trick that we know how to do that can actually change the way that farmers think about produce in their orchards.
Another thing we're working on is this notion of robot first responders. So imagine you have a 911 call from a building. You can imagine a swarm of robots equipped with cameras getting to the building and surrounding it long before search and rescue workers come to the scene, long before first responder police officers come to the scene.
What we are really trying to do with these, on the top left you see the operator interface, what the dispatcher might see before he or she even reacts to the 911 call. The robots are surrounding the building deciding who takes up what position around what ingress or egress point, all the time assimilating information and building a mosaic, as you see on the top right, and our three dimensional map on the bottom.
So now, if a police car were to drive up to the scene, they would be equipped with all this information before they even get there. And they would know what to do before they got there. This is a very important tool in operations, where oftentimes speed of response is so critical.
This is not true just for outdoor operations, but also indoor operations. I want to show you some experiments we did. This was about five years ago, after the Fukushima earthquake. This was in a town not too far from Fukushima where our aerial robot is hitching a ride on one of our Japanese colleagues' ground robots. And by the way, the reason it hitches a ride is because our robots are programmed to be lazy. They burn a lot of power, so anytime they can ride on top of something else, they do.
But you can see in this collapsed doorway they quickly realize that the team cannot go through. So the aerial robot takes off, is able to cross over the bookshelf, see what's on the other side, all the time creating a three dimensional map. And this kind of information then can be made available to somebody who is standing outside the room or outside the building, and providing valuable information in terms of the structure integrity of the collapsed building, in terms of potential victims, and assessing the state of the building to people who are outside the building.
Again, this was five years ago. In this particular experiment, we were able to build three dimensional maps. And this is three stories—the seventh, eighth and ninth floor of a nine story building. So the map is a five centimeter resolution map, and this took a long time to build. This experiment lasted about two and a half hours, and that's one of the challenges of robotics. If I tell a search and rescue worker or a first responder that I want you to give me two and a half hours so I go into this building and give you this wonderful map, nobody is going to give me that time. I'll be lucky if they give me two and a half minutes, or maybe two and a half seconds.
That's where this idea of swarms come in. We really want systems that can go in really quickly, collect the data, and by the time they cut out, they've assimilated this information and built a three dimensional map. And that's the kind of thing we're shooting for.
So let me just conclude with a poster of an upcoming Warner Brothers movie called The Swarm. Actually, some of you might be old enough to actually remember this movie. Has anyone seen this? If you've seen it you probably know that you won't recommend it to your friends. It's actually a terrible movie. It's about killer bees that attack mankind and so on. But I love the poster because everything about this poster is true. The size is immeasurable. I hope I've convinced you the power is limitless. Even that last piece, it's enemy is man, which is true. We have the technology and we have to find a way to harness the technology and use it in a way that could be beneficial to society and to mankind. So even that part is true.
So thank you very much.
Moderator:
So as always, we now will open it up to you to ask some questions. I'm going to start right here in the front.
Question:
Thank you. Dr. Kumar, since you're indicating that [indiscernible 39:55] ratio is critical with aeronautical robots, what new chemistries are coming down the pike to increase the power and at the same time reduce weight?
Kumar:
There are lots of things you can do from a technology perspective. But from what makes sense from an economics perspective, I think at this scale you are somewhat restricted to electric power and batteries. I don't see anything dramatically new coming down the pipeline. Although people say that batteries are improving, and certainly Elon Musk's vision for batteries has gone a long way, they're mostly focusing on the amount of power per unit volume, not amount of power per unit mass. And that has not changed a whole lot. We might get 10 to 20 percent improvement in the next five years, but I don't see anything big coming down the pipeline. That's why for us, scaling down in size and reducing weight is the way to go.
Question:
It's amazing what you have said and what you have shown us. If, God forbid, a similar 911 should occur, these little devices will be there before humans. How soon after these little devices have affected the situation will humans come to the aid of the human race?
Kumar:
This is a difficult question to answer, because I think one of the things—and again, some of you who saw the Nova episode on robotics last week will quickly appreciate that robots are not terribly good at doing physical things. So the best thing we can do with these kinds of lightweight, small robots is provide information, provide situational awareness.
As you well know from 911, if we had had that situational awareness, we could have prevented a lot of people from losing their lives. So that's the part we're working on right now.
As to how you would act on that information, that really depends on what it is you're trying to do. And I'm afraid that today, I would not be suggesting that robots would provide an answer to it quite today. In the near future, I think there are a lot of people working in robotics challenges. I think industry is also getting excited by this, and that can only mean good things for all of us.
Moderator:
We have our first Twitter question for you, Dr. Kumar, which is, how much correlation is there between autonomous cars to autonomous drones?
Kumar:
The parallels between autonomous cars and autonomous drones are striking. I think the problem with autonomous cars is somewhat simpler because you're doing things in two dimensions. And more importantly, you don't worry about the weight. So the fraction of weight you will ascribe to processes and sensors is quite small compared to the amount of other stuff you're carrying in a car.
Therefore, you can actually sensorize the car a lot better, and that makes the problem paradoxically a lot simpler, even when you drive in New York City. But on the other hand, when you're flying in New York City in the presence of tall buildings, I think putting things in a smaller package, being more robust, and making sure that there are safety critical systems that are all verified, that's a big challenge.
But the parallels are there. In some sense, both problems are about navigating environments in which bad things can happen suddenly.
Question:
I was just curious about the potential for not just aerial vehicles but as well as underwater or other context. Do you feel like there are advances possible there?
Kumar:
I do believe so. If I were to give you a quick history of robotics, which is about 50, 60 years, the first 20 years we spent—not we literally, but people spent building robots that were bolted to the shop floor. So you had these arms that were doing things. The next 20 years, robots started moving, perhaps with the arms, to the applications. And now the next 10 years we've seen robots take off this way, and the 10 years after that we'll see robots go down into the water. And the problems actually between underwater, if you look at underwater robots and aerial robots, the problems are quite similar.
Again, you have to think about autonomy and environments where you don't have GPS. Underwater operation is considerably harder because communications don't work. But I do believe that there's a push towards that, particularly if you look at some of the challenges we have in food production and so on. Some of the solutions might be underwater. You need robots. Certainly looking at, 30 percent of the Earth's surface is covered by water, and we know a tiny fraction of what's underneath the water. So I do think there's a push for that, and that push will make underwater robots more economical and viable.
Question:
I guess this is sort of an autonomy question. What kind of memory demands are you seeing for all of this imaging and GPS information? And is it happening onboard, or is it wirelessly being networked in?
Kumar:
That's a good question. Again, in everything I showed you in the lab things were happening off board. But when you go outside, we don't rely on off board memory. There's no reason why you cannot. Certainly, for self-driving cars, you can have maps on the cloud which you can download and upload, etc. But in everything I showed you, everything was done onboard.
Having said that, this is a great question. You think about swarms, and have implicitly assumed that every vehicle is identical. There's no reason why you can't have some vehicles that are much bigger that are storing more information and not moving, and supplying information to vehicles that are moving. And so there's an interesting architecture design question as to where you store stuff, where you compute, and how you sense.
Question:
How secure is that data, and how vulnerable is it for someone who wants to use it for nefarious reasons?
Kumar:
Another great question. We don't worry too much about security when we work on research. But we have spinoff companies that do think a lot about this. So the bottom line is, if you take one of our lab prototypes, somebody who knows what they're doing will take 10 minutes to hack into this. Of course, if you want to build commercial prototypes, that's the first thing you have to worry about.
Question:
How close is this robotic technology to nanotechnology?
Kumar:
There are aspects of robotics that lend themselves to nanotechnology. In fact, today people are thinking about small, micro-scale or nano-scale robots that can actually navigate the human body the same way we have robots navigating three dimensional environments. So you can imagine I think the first small-scale robots we'll see might resemble something like what you see in an MRI machine.
So imagine the MRI machine, which is basically a collection of magnets that's imaging your body. What if those magnets were used to steer a robot that's magnetic through your body, perhaps using the robot's motion to deliver drugs locally with some targeting? Or using cameras onboard the robot to do imaging that you couldn't otherwise do?
So there are lots of these kinds of devices that are under development. So you might imagine robots shrinking down in scale at that level. But the technologies you use to scale them down will look very different from the kinds of things that I just talked to you about.
Question:
I have a question about swarm behavior. So you were showing us the search and rescue application where it makes sense that a swarm of robots could really quickly collect a lot of data. But what about the computational cost of putting all the data together? So how long does that usually take?
Kumar:
This relates to the question over there about exactly this. So where you do the computation and where you do storage is not immediately clear. You might imagine robots collecting data and storing them locally. But when they come out of the building, you might have huge servers sitting in a back of a truck that are sucking this data and integrating this information in real time or close to real time.
So you wouldn't be able to do that onboard. At these smaller length scales it's very hard to get something like GPUs onboard, or large storage devices onboard. So that is a challenge for us.
Question:
Would you say that adding a language component to the drones would expedite search and rescue efforts?
Kumar:
One thing I completely ignored is how humans would interact with a system of drones. That's not what we do in the lab. That doesn't mean it's not important, but that's not what we do. There's been lots of advances in human/machine interaction, and how humans might communicate with not just one machine, but groups of machines, or swarms. Certainly, the holy grail is to have natural language style interactions between humans and machines as you do between humans and humans. And ultimately, that's what people are trying to work towards. We don't do that, but a technology like this would be incredibly useful in search and rescue.
Question:
I was wondering what considerations you were taking into the sky as an environment. I know in Prospect Park the hawks are already attacking the man controlled drones. I was just wondering how you're taking that into consideration when you're building them.
Kumar:
You're worried about the drones being harmed or the hawks?
Question:
The hawks.
Kumar:
We don't. And it is true that when you fly high, that could be an issue. But remember, we're more interested in flight at lower altitudes, near buildings. We seldom fly higher than 10, 20 meters, and there, these problems are less prevalent.
Question:
I'm very curious about the adhesive that you're using in your perching tests. In the video demonstrations that we saw, the robot was always nailing the landing, and then it appears to have some sort of cable attachment that lets it hand a bit. Have you tackled the relaunching aspect of that and what sort of force and lift you'd need?
Kumar:
Again, the gripper, the feet design, is not my work. This is Professor Cutkosky's work from Stanford. But the structure of the feet is similar to the structure you see in gecko feet. That's the idea. I did not describe how we detach, but yes, we can do that. Yes, I didn't show that, but we do do that.
Moderator:
Please join me again in thanking Dr. Kumar.
Kumar:
Thank you very much.
[Applause]
[End of audio]
Autonomous aerial robots, commonly referred to as drones, could soon be used for search and rescue, emergency first response, and precision farming. Join roboticist Vijay Kumar, dean and professor of engineering at the University of Pennsylvania, as he describes the advantages and the challenges of coordinating and controlling teams of small robots.
This SciCafe took place on March 2, 2016. To learn about upcoming SciCafe events, visit amnh.org/scicafe. To hear the full lecture, download the podcast.