Pick and place robotics has been around for decades, and it
can be straightforward if the parts are always in a precise location. But in
the real world, parts can come in boxes such as gaylord packaging.
To automate bin
picking, robots need to be able to see and adapt to random part locations and
orientations. Some bin picking systems
use 2D cameras to determine part location for picking, but these systems can
fail when the bin is very full or nearly empty.
To avoid this issue, Bluewrist
uses time of flight algorithms to build a 3D point cloud of the bin, enabling
it to select a part for picking, while avoiding collision with the bin walls
and with other parts.
Moreover, this software can be configured with any hardware.
In the video below, Bluewrist has set up FlexiPick with an ABB Yumi cobot and an Xbox Kinect
2 off-the-shelf sensor, but it can be set up with other sensors, robots or PLCs.
The system can be used to pick small parts with a cobot,
assist human operators with assembly tasks or in conjunction with larger material
handling robots, such as those in automotive manufacturing. FlexiPick can also
be used for machine tending and other robotic cell tasks.
Watch the video to see Flexipick in action:
For more on machine vision, check out Machine
Vision Technology for Pick and Place and Assembly.