Putting together flat-pack furniture. It shouldn't be difficult, but somehow we always end up bleeding, broken and surrounded by Allen keys.
That might be about to change, depending on your level of obsessive technological acquisition, after the unveiling of a robot that can help you put your shelves together.
Developed by Italian researchers Leonel Rozo and Sylvain Calinon, the robot is able to use a force sensor and a vision tracking system to learn instructions. It is then able to follow commands to repeat those instructions in a natural way - turning over the tabletop and helping it screw parts together.
The result is a cool and expensive way to build a table - and a neat development in robotics and computer learning techniques.
The team behind it explains:
One user is grasping the robot and moving it by hand to demonstrate how it should collaborate with another user (kinesthetic teaching). A force sensor mounted at the wrist of the robot and a marker-based vision tracking system is used to track the position and orientation of table legs that need to be mounted at four different point on the table top.
After demonstration, the robot learns that it should first be compliant to let the user re-orient the table-top in a comfortable pose to screw the current leg. Once the user starts to screw the leg, the robot becomes stiff to facilitate the task. This behavior is not pre-programmed, but is instead learn by the robot by extracting the regularities of the task from multiple demonstrations.
Take a look, above.