Robot learning in a social robot
Salvador Dominguez, Eduardo Zalama, Jaime G. García-Bermejo and Jaime Pulido
Simulation of Adaptive Behavior 2006 (SAB 2006)
Rome, Italy, 25-29 September 2006
Summary
In this paper, research work on Arisco is described. Arisco is a social robot, built around a robotic head with gesture ability, visual and auditive perception and behaviour learning. It is intended for interacting with people. The general architecture is first described in the paper. Then, the learning capacity of Arisco is addressed. It learns and performs associations between different stimulus responses through several dynamic neural networks, guided by motivational drives. A number of experiments are discussed, covering stimu-lus competition, habituation and first and second order conditioning.