Masahiko Haruno, Daniel M. Wolpert, Mitsuo Kawato
Humans demonstrate a remarkable ability to generate accurate and appropriate motor behavior under many different and oftpn uncprtain environmental conditions. This paper describes a new modular ap(cid:173) proach to human motor learning and control, baspd on multiple pairs of inverse (controller) and forward (prpdictor) models. This architecture simultaneously learns the multiple inverse models necessary for control as well as how to select the inverse models appropriate for a given em'i(cid:173) ronm0nt. Simulations of object manipulation demonstrates the ability to learn mUltiple objects, appropriate generalization to novel objects and the inappropriate activation of motor programs based on visual cues, followed by on-line correction, seen in the "size-weight illusion".