Proto-symbol emergence

Abstract

Robotics can serve as a testbed for cognitive theories. One behavioral criterion for comparing theories is the extent to which their implementations can learn to exploit new environmental opportunities. Furthermore, a robotics testbed forces researcher to confront fundamental issues concerning how internal representations are grounded in activity.In our approach, a mobile robot takes the role of a creature that must survive in an unknown environment. The robot has no a przori knowledge about what constitutes a suitable goalwhat is edible, inedible, or dangerousor even its shape or how its body works. Nevertheless, the robot learns how to survive. The robot does this by tracking segmented regions of its camera image while moving. The robot projects these regions into a canonical wavelet domain that highlights color and intensity changes at various scales. This reveals sensory invariance that is readily extracted with Bayesian statistics. The robot simultaneously learns an adaptable sensorimotor mapping by recording how motor signals transform the locations of regions on its camera image. The robot learn about its own physical extension when it touches an object. But it also undergoes an internal state change analogous to the thirst quenching or nausea producing effects of intake in animals. This allows the robot to learn what an object affordsis it edible or poisonous?by relating these effects to learned clusters of invariance. In this way primitive symbols emerge. These proto-symbols provide the robot with goals that it can achieve by using its sensorimotor mapping to navigate, for example, toward food and away from danger.

What baboons, babies and Tetris players tell us about interaction: a biosocial view of norm-based social learning

“…Of course, computers have been programmed to model norms in the narrow sense of statistical regularities; this has been a major focus of research on learning in artificial neural networks (Bishop 1995). A number of robotic systems have been built in which robots affectively appraise their environment based on internal drives directed toward maintaining physiological or emotional equilibrium (MacDorman et al 2000, Breazeal 2002, 2003, Arkin et al 2003, Sawada et al 2004. The behaviour of these robots is normative in so far as it functions to maintain the well-being of the whole 'organism'.…”

Toward Monitoring and Increasing Exercise Adherence in Older Adults by Robotic Intervention: A Proof of Concept Study

“…Face detection is a part of object recognition research [47], and much work has been conducted on it since the inception of vision processing. Turk and Pentland [48] developed an automatic recognition system based on eigenfaces that compares the features of novel faces to already known faces.…”

Towards Imitation Learning from a Viewpoint of an Internal Observer

“…However, the agent could not distinguish its body from the environment without a priori knowledge how its motor system affects its vision. Although another study proposed a method by which an agent finds the boundary of its tactile sensor in the vision based on experience of collision [8], the agent needs to be taught which object in the vision collides with its body.…”