Abstract
We present a Perception-Action architecture and experiments to simulate imprinting the establishment of strong attachment links with a “caregiver”—in a robot. Following recent theories, we do not consider imprinting as rigidly
timed and irreversible, but as a more flexible phenomenon that allows for further adaptation as a result of reward-based learning through experience.
Our architecture reconciles these two types of perceptual learning traditionally considered as different and even incompatible. After the initial imprinting, adaptation is achieved in the context of a history of “affective” interactions between
the robot and a human, driven by “distress” and “comfort” responses in the robot
timed and irreversible, but as a more flexible phenomenon that allows for further adaptation as a result of reward-based learning through experience.
Our architecture reconciles these two types of perceptual learning traditionally considered as different and even incompatible. After the initial imprinting, adaptation is achieved in the context of a history of “affective” interactions between
the robot and a human, driven by “distress” and “comfort” responses in the robot
Original language | English |
---|---|
Title of host publication | Procs 5th Int Workshop on Epigenetic Robotics |
Subtitle of host publication | Modeling Cognitive Development in Robotic Systems |
Publisher | Lund University |
Pages | 23-30 |
ISBN (Print) | 91-974741-4-2 |
Publication status | Published - 2005 |
Publication series
Name | Lund University Cognitive Studies |
---|---|
Volume | 123 |