ADVANCES
24 Scientific American, May 2019ANYBOTICShttp://www.anybotics.comicist who helped to develop the simula-
tion-based training method, says it was
created for rescue operations and oil
rig inspections. It can climb stairs and
crawl through tunnels while carrying its
heavy digital brain inside its dustproof
and watertight body. A Kevlar belly
helps it survive half-meter falls.
Others are developing quadruped
bots that rival ANYmal’s abilities. In
2008 Boston Dynamics gained notice
for comical (and creepy) footage of its
noisy, gas-powered “BigDog” trudging
up treacherous terrain. The newer
“SpotMini” is its 25-kilogram electric
cousin. Sangbae Kim, a mechanical
engineer at the Massachusetts Institute
of Technology, who is not affiliated with
Boston Dynamics, says SpotMini has
the world’s most advanced algorithm
for navigating around and over obsta-
cles. The company plans to start selling
it this year for jobs ranging from con-
struction to home assistance. A top-
mounted port allows users to attach
tools, including a five-kilogram arm that
can fetch drinks and load the dishwash-
er—truly a human’s best friend.
Kim’s team at M.I.T. has built a
40-kilogram bot named “Cheetah 3,”
which he says moves more efficiently
than four-legged animals of similar
weight. The robot also has the most
powerful joints of any legged robot of
its size, he adds—they were built from
scratch and produce as much torque as
a car engine. The joints also regenerate
energy and handle impacts well. Chee-
tah 3 is not as fast as its predecessor,
Cheetah 2, which can run at 23 kilome-
ters an hour, Kim says. But it can per-
form backflips (at least in theory) as well
as climb stairs and obstacles without
relying on camera vision. It is built for
research, however, so do not expect to
adopt one soon. — Matthew HutsonTECHGood Bot
Doglike robots simulate their skills
before entering the real worldProgramming robots that can walk, run and
grasp is laborious, so researchers would prefer
that they learn on their own. To solve the
problem of wear-and-tear on real robots
learning by trial-and-error, groups of research-
ers are developing ways to simulate the bots
and download the skills they learn to real hard-
ware. A new method improves these simula-
tions with data from the real robots, closing
the feedback loop. The result is robots with
boosted speed and agility.
Working with a robotic quadruped called
ANYmal, roboticists at the Swiss Federal Insti-
tute of Technology Zurich (ETH Zurich) aug-
mented its algorithms with neural networks
(software inspired by the human brain). As
the robot fumbles around in the real world, the
neural networks learn the quirks of each of
the bot’s motors. That information feeds backinto the simulation, helping it more accurately
model the real bot and thus produce more
effective skills for downloading. In experi-
ments, ANYmal broke its previous trotting
speed record by 25 percent, the researchers
reported in January in Science Robotics. It could
also regain its balance after being pushed and
its footing after being flipped.
ANYmal is commercially available
through the ETH Zurich spinoff ANYbotics.
Motors in its joints have tendonlike springs
that absorb shock, store energy and provide
sensory feedback. Each leg has three motors,
all interchange able. Jemin Hwangbo, a robot-Four-legged robot ANYmal, developed by ANYbotics.© 2019 Scientific American © 2019 Scientific AmericanADVANCES
24 Scientific American, May 2019ANYBOTICShttp://www.anybotics.comicist who helped to develop the simula-
tion-based training method, says it was
created for rescue operations and oil
rig inspections. It can climb stairs and
crawl through tunnels while carrying its
heavy digital brain inside its dustproof
and watertight body. A Kevlar belly
helps it survive half-meter falls.
Others are developing quadruped
bots that rival ANYmal’s abilities. In
2008 Boston Dynamics gained notice
for comical (and creepy) footage of its
noisy, gas-powered “BigDog” trudging
up treacherous terrain. The newer
“SpotMini” is its 25-kilogram electric
cousin. Sangbae Kim, a mechanical
engineer at the Massachusetts Institute
of Technology, who is not affiliated with
Boston Dynamics, says SpotMini has
the world’s most advanced algorithm
for navigating around and over obsta-
cles. The company plans to start selling
it this year for jobs ranging from con-
struction to home assistance. A top-
mounted port allows users to attach
tools, including a five-kilogram arm that
can fetch drinks and load the dishwash-
er—truly a human’s best friend.
Kim’s team at M.I.T. has built a
40-kilogram bot named “Cheetah 3,”
which he says moves more efficiently
than four-legged animals of similar
weight. The robot also has the most
powerful joints of any legged robot of
its size, he adds—they were built from
scratch and produce as much torque as
a car engine. The joints also regenerate
energy and handle impacts well. Chee-
tah 3 is not as fast as its predecessor,
Cheetah 2, which can run at 23 kilome-
ters an hour, Kim says. But it can per-
form backflips (at least in theory) as well
as climb stairs and obstacles without
relying on camera vision. It is built for
research, however, so do not expect to
adopt one soon. — Matthew HutsonTECHGood Bot
Doglike robots simulate their skills
before entering the real worldProgramming robots that can walk, run and
grasp is laborious, so researchers would prefer
that they learn on their own. To solve the
problem of wear-and-tear on real robots
learning by trial-and-error, groups of research-
ers are developing ways to simulate the bots
and download the skills they learn to real hard-
ware. A new method improves these simula-
tions with data from the real robots, closing
the feedback loop. The result is robots with
boosted speed and agility.
Working with a robotic quadruped called
ANYmal, roboticists at the Swiss Federal Insti-
tute of Technology Zurich (ETH Zurich) aug-
mented its algorithms with neural networks
(software inspired by the human brain). As
the robot fumbles around in the real world, the
neural networks learn the quirks of each of
the bot’s motors. That information feeds backinto the simulation, helping it more accurately
model the real bot and thus produce more
effective skills for downloading. In experi-
ments, ANYmal broke its previous trotting
speed record by 25 percent, the researchers
reported in January in Science Robotics. It could
also regain its balance after being pushed and
its footing after being flipped.
ANYmal is commercially available
through the ETH Zurich spinoff ANYbotics.
Motors in its joints have tendonlike springs
that absorb shock, store energy and provide
sensory feedback. Each leg has three motors,
all interchange able. Jemin Hwangbo, a robot-Four-legged robot ANYmal, developed by ANYbotics.sad0519Adva3p.indd 24 3/21/19 3:21 PM
Scientific American is a registered trademark of Springer Nature America, Inc.squareTemplate.indd 9 8/20/18 2:03 PMUntitled-10 1 3/22/19 9:44 AM