From State Transitions to Sensory Regularity: Structuring Uninterpreted Sensory Signals from Naive Sensorimotor Experiences - Archive ouverte HAL Access content directly
Journal Articles IEEE Transactions on Cognitive and Developmental Systems Year : 2023

From State Transitions to Sensory Regularity: Structuring Uninterpreted Sensory Signals from Naive Sensorimotor Experiences

Abstract

How could a naive agent build some internal, subjective, notions of continuity in its sensorimotor experiences? This is a key question for all sensorimotor approaches to perception when trying to make them face realistic interactions with an environment, including noise in the perceived sensations, errors in the generation of motor trajectories, or uncertainties in the agent's internal representation of this interaction. This paper proposes a detailed formalization, but also some experimental assessments, of the structure a naive agent can leverage from its own uninterpreted sensorimotor flow to capture a subjective sensory continuity, making it able to discover some notions of closeness or regularities in its experience. The precise role of the agent's actions is also questioned w.r.t. the spatial and temporal dynamics of its exploration of the environment. On this basis, the previous authors' contribution on sensory prediction is extended to successfully handle noisy data in the agent's sensorimotor flow.
Fichier principal
Vignette du fichier
goasguen_et_al.pdf (8.27 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03537409 , version 1 (20-01-2022)
hal-03537409 , version 2 (21-06-2022)
hal-03537409 , version 3 (28-09-2022)
hal-03537409 , version 4 (10-03-2023)

Identifiers

Cite

Loïc Goasguen, Jean-Merwan Godon, Sylvain Argentieri. From State Transitions to Sensory Regularity: Structuring Uninterpreted Sensory Signals from Naive Sensorimotor Experiences. IEEE Transactions on Cognitive and Developmental Systems, In press, ⟨10.1109/TCDS.2022.3226531⟩. ⟨hal-03537409v4⟩
172 View
131 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More