Grounding the Experience of a Visual Field through Sensorimotor Contingencies

TL;DR

This paper introduces a sensorimotor approach grounded in the sensorimotor contingencies theory, enabling an autonomous agent to discover and model its visual field through active exploration and sensory regularities.

Contribution

It proposes a formalism and method for discovering the visual field by capturing sensorimotor regularities, inspired by biological perception theories.

Findings

Successful discovery of visual field regularities in simulation

Development of a sensorimotor predictive model for perception

Demonstration of autonomous perceptive ability in a simulated system

Abstract

Artificial perception is traditionally handled by hand-designing task specific algorithms. However, a truly autonomous robot should develop perceptive abilities on its own, by interacting with its environment, and adapting to new situations. The sensorimotor contingencies theory proposes to ground the development of those perceptive abilities in the way the agent can actively transform its sensory inputs. We propose a sensorimotor approach, inspired by this theory, in which the agent explores the world and discovers its properties by capturing the sensorimotor regularities they induce. This work presents an application of this approach to the discovery of a so-called visual field as the set of regularities that a visual sensor imposes on a naive agent's experience. A formalism is proposed to describe how those regularities can be captured in a sensorimotor predictive model. Finally, the approach is evaluated on a simulated system coarsely inspired from the human retina.