Artificial Enactive Inference in Three-Dimensional World - Unité de Recherche CONFLUENCE : Sciences et Humanités (EA 1598) - UCLy Accéder directement au contenu
Article Dans Une Revue Cognitive Systems Research Année : 2024

Artificial Enactive Inference in Three-Dimensional World

Résumé

The theory of Enactive Inference was proposed by Karl Friston and his colleagues to explain how the brain infers knowledge about the world through the subject's interactive experiences. Sensorimotor states induce perturbations in neural activity, and the brain infers hypothetical causes in the world that may explain these perturbations. This article aims to reconcile this neuroscience theory with computer science and artificial-intelligence theories wherein artificial agents receive input data derived from the environment's state and infer internal data structures used to guide decisions. Two critical challenges arise in both the agent's active role and the inference algorithm's scalability as the environment's complexity increases. To address these challenges, we formalize artificial enactive inference through a new Spatial Enactive Markov Decision Process (SEMDP) model. This model rests on low-level control loops enacted in a three-dimensional Euclidean space containing objects. Based on the SEMDP, we present a proof-of-concept cognitive architecture and an experiment to demonstrate the transcription of the theory of enactive inference into the domain of artificial intelligence and robotics.
Fichier principal
Vignette du fichier
georgeon.pdf (1.45 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04587508 , version 1 (24-05-2024)

Identifiants

Citer

Olivier L. Georgeon, David Lurie, Paul Robertson. Artificial Enactive Inference in Three-Dimensional World. Cognitive Systems Research, 2024, 86, pp.101234. ⟨10.1016/j.cogsys.2024.101234⟩. ⟨hal-04587508⟩
15 Consultations
7 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More