Artificial Interactionism: Avoiding Isolating Perception From Cognition in AI - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Frontiers in Artificial Intelligence Année : 2022

Artificial Interactionism: Avoiding Isolating Perception From Cognition in AI

Résumé

We discuss the influence upon the fields of robotics and AI of the manner one conceives the relationships between artificial agents' perception, cognition, and action. We shed some light upon a widespread paradigm we call the isolated perception paradigm that addresses perception as isolated from cognition and action. By mobilizing the resources of philosophy (phenomenology and epistemology) and cognitive sciences, and by drawing on recent approaches in AI, we explore what it could mean for robotics and AI to take distance from the isolated perception paradigm. We argue that such a renouncement opens interesting ways to explore the possibilities for designing artificial agents with intrinsic motivations and constitutive autonomy. We then propose Artificial Interactionism, our approach that escapes the isolated perception paradigm by drawing on the inversion of the interaction cycle. When the interaction cycle is inverted, input data are not percepts directly received from the environment, but outcomes of control loops. Perception is not received from sensors in isolation from cognition but is actively constructed by the cognitive architecture through interaction. We give an example implementation of artificial interactionism that demonstrates basic intrinsically motivated learning behavior in a dynamic simulated environment.

Dates et versions

hal-03552075 , version 1 (02-02-2022)

Identifiants

Citer

Mathieu Guillermin, Olivier L. Georgeon. Artificial Interactionism: Avoiding Isolating Perception From Cognition in AI. Frontiers in Artificial Intelligence, 2022, 5, ⟨10.3389/frai.2022.806041⟩. ⟨hal-03552075⟩
47 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More