Arie Soeteman

PhD Candidate; Machine Learning for Automated Reasoning

University of Amsterdam

Spatial Unity for the Apperception Engine | Arie Soeteman

Spatial Unity for the Apperception Engine

January 02, 2024

We develop a logical approach for computational agents to spatially explore their environment, extending on the Kant-inspired logical unification methods of the Apperception Engine. Evaluating models of the Regional Connection Calculus as Alexandroff Topologies, we axiomatise connectedness and unity of space. We further define dimensionality for tolerance spaces and prove that locally verifiable properties guarantee global consistency of space as the existence of isomorphisms to grids, turbands or tori. Finally, we provide a generally competent and explainable computational agent that unifies intuition in space, the Spatial Apperception Engine.

by Arie Soeteman & Michiel van Lambalgen

https://www.sciencedirect.com/science/article/pii/S0888613X23002372