The company developing the robo-beast with the Army Research Laboratory funding calls in an arm, though, and in a recent video you can see it grabbing, lifting and hurling 35-lb cinder blocks to the side and rear.
“The goal is to use the strength of the legs and torso to help power motions of the arm,” a company official said. “This sort of dynamic, whole-body approach to manipulation is used routinely by human athletes and will enhance the performance of advanced robots.”
Big Dog funding originally came from DARPA, the Defense Advanced Research Projects Agency, but was subsequently picked up by the ARL’s Robotics Collaborative Technology Alliance. The objective is to field a fully autonomous robotic mule – something with “animal-like mobility,” says Boston Dynamics – that can operate in terrain too rough for vehicles.
It’s easy to see the advantage of having a robot mule able to clear its own path. In the video demonstration Big Dog’s best cinderblock throw was about 17 feet.
To date Big Dog still requires a human operator commanding it via wireless radio, according to the company. Its own onboard control system operates the legs and provides stability, so that even without command assistance it can handle rough terrain and react quickly to balance itself and stay upright if bumped, as shown in this video from 2013, when Marines put it through some paces as a pack robot.
But future versions will use computer vision, GPS, and light detection and ranging technology for accurately gauging distance to provide more autonomy. This will enable the robot to travel to pre-programmed locations without additional human input.
Ultimately, the Army wants a number of military unmanned ground vehicle systems of various sizes and abilities that can operate largely or entirely autonomously.
In a 2011 report, the alliance said the future of unmanned systems rests with the machines being able to function with intelligence-based technologies enabling them to team with combat troops.
“To act as teammates,” the report said, “robotic systems will need to reason about their missions, move through the world in a tactically correct way, observe salient events … communicate efficiently with soldiers and other autonomous systems, and effectively perform a variety of mission tasks.”