Vijay Kumar: The future of flying robots
Виджай Кумар: Будущее летающих роботов
As the dean of the University of Pennsylvania's School of Engineering and Applied Science, Vijay Kumar studies the control and coordination of multi-robot formations. Full bio
Double-click the English transcript below to play the video.
autonomous aerial robots
строят автономных летающих роботов,
that you can buy today,
которых вы можете купить сегодня,
to determine their position.
своё местоположение.
cameras and laser scanners,
камеры и лазерные сканеры
рельефа местности
relative to those features,
all these features into a map,
to understand where the obstacles are
где находятся препятствия,
we did inside our laboratory,
из нашей лаборатории,
to go for longer distances.
на более длинные расстояния.
what the robot sees with the camera.
что робот видит с помощью камеры.
by a factor of four --
the map that it's building.
которую он выстраивает.
of the corridor around our laboratory.
коридора около нашей лаборатории.
you'll see it enter our lab,
by the clutter that you see.
который вы видите.
of building high-resolution maps
карты с высоким разрешением,
or outside the building
или вне здания
without actually going inside,
what happens inside the building.
with robots like this.
about 100 watts per pound.
на каждые полкилограмма веса.
a very short mission life.
that end up being very expensive --
оказавшиеся очень дорогими:
and the processors.
can you buy in an electronics store
что продаются в магазинах электроники,
that has sensing onboard and computation?
и процессорами на нём?
smartphone that you can buy off the shelf,
Samsung Galaxy, его можете купить и вы,
can download from our app store.
загрузить наше приложение.
reading the letters, "TED" in this case,
в нашем случае слово «TED»,
of the "T" and the "E"
flying autonomously.
и движется автономно.
to make sure if the robot goes crazy,
если робот спятит,
these small robots,
behaviors, like you see here.
агрессивным поведением.
at two to three meters per second,
as it changes direction.
smaller robots that can go faster
маленькие быстрые роботы,
very unstructured environments.
в очень хаотичных средах.
gracefully coordinating its wings,
которая изящно управляет своими крыльями,
to grab prey out of the water,
жертву из воды,
hoagie that it's grabbing out of thin air.
сэндвич «Филадельфия».
going at about three meters per second,
coordinating its arms, its claws
координирует свою клешню
to achieve this maneuver.
чтобы выполнить этот манёвр.
how the robot adapts its flight
than the width of the window.
длину подвеса и высоту,
and adjust the altitude
to make these even smaller,
сделать их ещё меньше,
in particular by honeybees.
and this is a slowed down video,
the inertia is so lightweight --
they bounce off my hand, for example.
столкновение с моей рукой.
that mimics the honeybee behavior.
поведение пчёл.
you get lower inertia.
уменьшается и инерция.
you're resistant to collisions.
восприимчивость к столкновениям ниже.
we build small robots.
таких же, как эти пчёлы.
is only 25 grams in weight.
up to six meters per second.
ten times the speed of sound.
в 10 раз больше скорости звука.
collision, at one-twentieth normal speed.
в воздухе, замедленное в 20 раз.
of two meters per second,
prevents the propellers from entangling,
защищает пропеллеры от столкновения,
and the robot responds to the collisions.
и робот реагирует на него.
to these small robots.
of the number of Band-Aids we've ordered
как мы заказывали пластыри,
to compensate for these disadvantages.
их компенсировать,
to form large groups, or swarms.
больших групп, или роёв.
we try to create artificial robot swarms.
создать искусственные рои роботов.
about networks of robots.
о взаимодействии роботов.
of sensing, communication, computation --
коммуникацию и вычисления,
quite difficult to control and manage.
three organizing principles
организации у природы —
to develop our algorithms.
need to be aware of their neighbors.
знать о своих соседях.
and communicate with their neighbors.
и общаться с ними.
hijacked by a human operator, literally.
оператором-человеком буквально.
interact with each other,
able to lead this network of followers.
эту сеть последователей.
know where they're supposed to go.
знает, куда он должен идти,
to the positions of their neighbors.
на местонахождение своих соседей.
the second organizing principle.
второй принцип организации.
with the principle of anonymity.
to the identities of their neighbors.
кто именно их соседи.
you introduce into the formation,
вы в это вовлечёте,
reacting to its neighbor.
реагирует на своего соседа.
to form the circular shape,
without central coordination.
централизованного управления.
essentially give these robots
of the shape they need to execute.
которые они должны построить.
as a function of time,
с течением времени,
start from a circular formation,
stretch into a straight line,
вытянулись по прямой линии
kind of split-second coordination
координируясь посекундно,
that we are very interested in.
которые нам очень интересны.
that we're facing worldwide.
in this earth is malnourished.
на планете недоедает.
has already been cultivated.
хозяйства земли уже возделана.
in the world is improving,
в мире растёт,
efficiency is actually declining.
shortage, crop diseases, climate change
заболевания злаков, изменение климата
called Precision Farming in the community.
известный как точное земледелие.
aerial robots through orchards,
precision models of individual plants.
отдельных растений.
to treat every patient individually,
подбирают отдельно,
models of individual plants
отдельного растения
what kind of inputs every plant needs --
нужно конкретному растению:
fertilizer and pesticide.
traveling through an apple orchard,
two of its companions
building a map of the orchard.
of every plant in this orchard.
каждого растения этого сада.
that are being used on this robot.
a standard color camera.
is a thermal camera.
a three-dimensional reconstruction
объёмная реконструкция
as the sensors fly right past the trees.
построенная во время облёта.
we can do several things.
thing we can do is very simple:
и очень простое:
на каждом дереве.
how many fruits she has in every tree
the yield in the orchard,
chain downstream.
с самого начала.
three-dimensional reconstructions,
объёмную реконструкцию,
to the amount of leaf area on every plant.
с листовой поверхностью каждого растения.
photosynthesis is possible in every plant,
возможного для каждого растения,
how healthy each plant is.
насколько здорово каждое растение.
and infrared information,
и тепловизора,
you can essentially see
not doing as well as other crops.
которым хуже, чем остальным.
а объединённому
detecting the early onset of chlorosis --
by yellowing of leaves.
по желтеющим листьям.
can easily spot this autonomously
that he or she has a problem
что у него или неё проблемы
that can improve by about ten percent
примерно на 10%,
the amount of inputs such as water
например, потребления воды,
aerial robot swarms.
роёв аэророботов.
the people who actually create the future,
которые создают будущее:
and Giuseppe Loianno,
и Джузеппе Лоиано,
demonstrations that you saw.
сегодняшние демонстрации.
ABOUT THE SPEAKER
Vijay Kumar - RoboticistAs the dean of the University of Pennsylvania's School of Engineering and Applied Science, Vijay Kumar studies the control and coordination of multi-robot formations.
Why you should listen
At the General Robotics, Automation, Sensing and Perception (GRASP) Lab at the University of Pennsylvania, flying quadrotor robots move together in eerie formation, tightening themselves into perfect battalions, even filling in the gap when one of their own drops out. You might have seen viral videos of the quads zipping around the netting-draped GRASP Lab (they juggle! they fly through a hula hoop!). Vijay Kumar headed this lab from 1998-2004. He's now the dean of the School of Engineering and Applied Science at the University of Pennsylvania in Philadelphia, where he continues his work in robotics, blending computer science and mechanical engineering to create the next generation of robotic wonders.
Vijay Kumar | Speaker | TED.com