Autonomous Grounding of Visual Field Experience through Sensorimotor Prediction

TL;DR

This paper presents a sensorimotor-based computational model enabling autonomous robots to learn and master their visual environment through exploration and prediction, without prior knowledge of their system or environment.

Contribution

It introduces a novel sensorimotor prediction framework for autonomous visual field grounding in robots, demonstrated through simulation.

Findings

Successful learning of visual field through sensorimotor prediction

Model effectively captures regularities in sensorimotor interactions

Framework applicable to autonomous exploration and perception

Abstract

In a developmental framework, autonomous robots need to explore the world and learn how to interact with it. Without an a priori model of the system, this opens the challenging problem of having robots master their interface with the world: how to perceive their environment using their sensors, and how to act in it using their motors. The sensorimotor approach of perception claims that a naive agent can learn to master this interface by capturing regularities in the way its actions transform its sensory inputs. In this paper, we apply such an approach to the discovery and mastery of the visual field associated with a visual sensor. A computational model is formalized and applied to a simulated system to illustrate the approach.