Towards a self-organizing pre-symbolic neural model representing sensorimotor primitives

TL;DR

This paper presents a neural model that self-organizes pre-symbolic representations of sensorimotor primitives, enabling robots to recognize and predict actions through visual stimuli, inspired by Piaget's developmental stages.

Contribution

It introduces a neural network architecture combining RNNPB and a horizontal product model for self-organizing sensorimotor primitives in robots.

Findings

Pre-symbolic units self-organize during observation learning.

Units guide recognition and prediction of sensorimotor primitives.

Model accounts for latent learning of primitives.

Abstract

The acquisition of symbolic and linguistic representations of sensorimotor behavior is a cognitive process performed by an agent when it is executing and/or observing own and others' actions. According to Piaget's theory of cognitive development, these representations develop during the sensorimotor stage and the pre-operational stage. We propose a model that relates the conceptualization of the higher-level information from visual stimuli to the development of ventral/dorsal visual streams. This model employs neural network architecture incorporating a predictive sensory module based on an RNNPB (Recurrent Neural Network with Parametric Biases) and a horizontal product model. We exemplify this model through a robot passively observing an object to learn its features and movements. During the learning process of observing sensorimotor primitives, i.e. observing a set of trajectories of arm movements and its oriented object features, the pre-symbolic representation is self-organized in the parametric units. These representational units act as bifurcation parameters, guiding the robot to recognize and predict various learned sensorimotor primitives. The pre-symbolic representation also accounts for the learning of sensorimotor primitives in a latent learning context.