(July 3, 2012) Researchers Develop an Artificial Cerebellum than Enables Robotic Human-like Object Handling
* University of Granada researchers –in
collaboration with other European institutions– are developing a system with
ability to interact with humans.
* Researchers are developing a robotic system
with ability to predict the specific action or movement that they should
perform when handling an object.
University
of Granada researchers have developed an artificial cerebellum (a
biologically-inspired adaptive microcircuit) that controls a robotic arm with
human-like precision. The cerebellum is the part of the human brain that
controls the locomotor system and coordinates body movements.
To date,
although robot designers have achieved very precise movements, such movements
are performed at very high speed, require strong forces and are power
consuming. This approach cannot be applied to robots that interact with humans,
as a malfunction might be potentially dangerous.
The developers of the
new cerebellar model have obtained a robot that performs automatic learning by
extracting the input layer functionalities of the brain cortex. Furthermore,
they have developed two control systems that enable accurate and robust control
of the robotic arm during object handling.
To solve this challenge,
University of Granada researchers have implemented a new cerebellar spiking model
that adapts to corrections and stores their sensorial effects; in addition, it
records motor commands to predict the action or movement to be performed by the
robotic arm. This cerebellar model allows the user to articulate a
state-of-the-art robotic arm with extraordinary mobility.
Automatic Learning