Home

GRIP-LEARNING ROBOT

Engineers at Stanford University (Stanford, CA) have devised an
algorithm that allows a robot to recognize unfamiliar objects and
determine the best way to pick them up. The robot was first trained in
a computer-generated environment to pick up five items: a cup, pencil,
brick, book, and martini glass. The algorithm locates the best place
for the robot to grasp an object, such as a cup's handle or a pencil's
midpoint.

In tests with real objects, the robotic arm picked up items similar to
those with which it trained, and successfully grasped new, "alien"
objects such as keys, screwdrivers, and rolls of duct tape. To grasp a
roll of duct tape, the robot employs an algorithm that evaluates the
image against all prior strategies. The process differs from industrial
robots that follow precise programs to manipulate pre-set objects but
are unable to perform a new task spontaneously.

For more information, click here.