Emergence of Spatial Coordinates via Exploration
This addresses the challenge of spatial representation in robotics, offering a novel approach that could reduce reliance on manual engineering, though it appears incremental as it builds on existing self-supervised learning methods.
The paper tackles the problem of enabling naive agents to autonomously develop an internal coordinate system without predefined Euclidean coordinates, achieving a system with the same dimension and metric regularity as external space through self-supervised learning of sensorimotor transitions.
Spatial knowledge is a fundamental building block for the development of advanced perceptive and cognitive abilities. Traditionally, in robotics, the Euclidean (x,y,z) coordinate system and the agent's forward model are defined a priori. We show that a naive agent can autonomously build an internal coordinate system, with the same dimension and metric regularity as the external space, simply by learning to predict the outcome of sensorimotor transitions in a self-supervised way.