A Formal Account of Structuring Motor Actions With Sensory Prediction for a Naive Agent - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Frontiers in Robotics and AI Année : 2020

A Formal Account of Structuring Motor Actions With Sensory Prediction for a Naive Agent

Bruno Gas

Résumé

For naive robots to become truly autonomous, they need a means of developing their perceptive capabilities instead of relying on hand crafted models. The sensorimotor contingency theory asserts that such a way resides in learning invariants of the sensorimotor flow. We propose a formal framework inspired by this theory for the description of sensorimotor experiences of a naive agent, extending previous related works. We then use said formalism to conduct a theoretical study where we isolate sufficient conditions for the determination of a sensory prediction function. Furthermore, we also show that algebraic structure found in this prediction can be taken as a proxy for structure on the motor displacements, allowing for the discovery of the combinatorial structure of said displacements. Both these claims are further illustrated in simulations where a toy naive agent determines the sensory predictions of its spatial displacements from its uninterpreted sensory flow, which it then uses to infer the combinatorics of said displacements.
Fichier principal
Vignette du fichier
article_synchro.pdf (5.21 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02596671 , version 1 (15-05-2020)
hal-02596671 , version 2 (31-10-2020)

Identifiants

Citer

Jean Godon, Sylvain Argentieri, Bruno Gas. A Formal Account of Structuring Motor Actions With Sensory Prediction for a Naive Agent. Frontiers in Robotics and AI, In press, ⟨10.3389/frobt.2020.561660⟩. ⟨hal-02596671v2⟩
113 Consultations
72 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More