A biologically inspired learning to grasp system

We propose and implement a learning to grasp system inspired from the development of reaching and grasping in infants, and the neurophysiology of the monkey premotor cortex. The system is composed of a virtual 19 DOF kinematics arm/hand and a learning mechanism that enables it to perform a successful grasp. The learning is based on "motor babbling". The model performs open hand reaches to the vicinity of the targets, which human infants younger than 4 moths of age appear to do. The contact of the hand with the object triggers an enclosure of the hand simulating the palmer reflex, characteristic to infants that are younger than 6 months of age. The varying degree of enclosure of each finger and the randomness in the reaching phase enables the system to explore the grasp configuration space. The learning scheme employed is a Hebbian one.