Menu

MILITARY

DARPA unveils one of world's most advanced humanoid robots

  • Atlas Robot.jpg

    ATLAS is a hydraulically powered robot in the form of an adult human. It is capable of a variety of natural movements, including dynamic walking, calisthenics and user-programmed behavior.DARPA

  • ATLAS robot front.jpg

    DARPA's Atlas robot, developed by Boston Dynamics, is six-foot-two and weighs 290 pounds.DARPA

He’s six-two, weighs 330 pounds, and has arms that stretch wider than a car -- but the NFL doesn’t want this guy in its lineup.

By the numbers

ATLAS is a hydraulically powered robot in the form of an adult human. Here's ATLAS, by the numbers:

Weight (incl. powerpack): 330 lbs
Height: 74”
Shoulder Width: 30”

Number of hydraulic joints: 28

Other features: Crash protection, modular wrists, LIDAR, stereo sensors

Defense contractors on Thursday unveiled one of the most advanced humanoid robots ever built as part of the DARPA Virtual Robotics Challenge in Waltham, Mass. Called ATLAS, the giant is controlled by a human operator, who guides the sensors, hydraulics, and limbs through a range of natural motions, the military said.

He can walk up stairs, stay upright after getting hit with heavy weights, and climb over or around obstacles in his path -- and may ultimately boost the ability of first responders in a disaster scenario.

Related: Giant robots, monsters invade theaters

“We have dramatically raised the expectations for robotic capabilities with this Challenge, and brought together a diverse group of teams to compete,” said Gill Pratt, program manager for the DARPA Robotics Challenge.

And ATLAS is just one of the robots in the military’s latest robobuilding contest.

“The Virtual Robotics Challenge was a proving ground for teams’ ability to create software to control a robot in a hypothetical scenario. The DRC Simulator tasks were fairly accurate representations of real world causes and effects, but the experience wasn’t quite the same as handling an actual, physical robot,” Pratt said.

“Now these seven teams will see if their simulation-honed algorithms can run a real machine in real environments. And we expect all teams will be further refining their algorithms, using both simulation and experimentation.”