An international team of scientists, including researchers from the University of Granada, have designed an artificial cerebellum for robots capable of mimicking the way humans manipulate objects . The research has been carried out for 4 years, framed within two European projects (SENSOPAC and REALNET).
The new model of artificial cerebellum allows robots to “learn” the intrinsic characteristics of an object that is presented to them (mass, inertia, resistance to movement) and associate them with another series of chance characteristics (color or shape) that help them to distinguish it from other objects and to carry out a more precise manipulation. That is, it artificially imitates how the nervous system precisely directs the performance of movements and gains knowledge of the objects it handles.
In the medium term, this study will allow the creation of a new generation of robots capable of interacting with humans in a much safer way than the current ones. In addition, this type of study can help the development of new treatments for diseases related to the cerebellum (such as ataxia), as well as new rehabilitation methods and “smart” prostheses.
