TY - GEN
T1 - Proprioceptive Feedback and Intrinsic Motivations in Early-Vocal Development
AU - Acevedo-Valle, J. M.
AU - Angulo, C.
AU - Agell, N.
AU - Moulin-Frier, C.
N1 - Publisher Copyright:
© 2015 The authors and IOS Press. All rights reserved..
PY - 2015
Y1 - 2015
N2 - This work introduces new results on early-vocal development in infants and machines using artificial intelligent agents. It is addressed using the perspective of intrinsically-motivated learning algorithms for autonomous exploration. The agent autonomously selects goals to explore its own sensorimotor system in regions where a certain competence measure is maximized. Unlike previous experiments, we propose to include a somatosensory model to provide a proprioceptive feedback to reinforce learning. We argue that proprioceptive feedback will drive the learning process more efficiently than algorithms taking into account only auditory feedback. Considering the proprioceptive feedback to generate a constraint model, which is unknown beforehand to the learner, guarantees that the agent is less prone to selecting goals that violated the system constraints in previous experiments.
AB - This work introduces new results on early-vocal development in infants and machines using artificial intelligent agents. It is addressed using the perspective of intrinsically-motivated learning algorithms for autonomous exploration. The agent autonomously selects goals to explore its own sensorimotor system in regions where a certain competence measure is maximized. Unlike previous experiments, we propose to include a somatosensory model to provide a proprioceptive feedback to reinforce learning. We argue that proprioceptive feedback will drive the learning process more efficiently than algorithms taking into account only auditory feedback. Considering the proprioceptive feedback to generate a constraint model, which is unknown beforehand to the learner, guarantees that the agent is less prone to selecting goals that violated the system constraints in previous experiments.
KW - Developmental robotics
KW - Early-vocal development
KW - Gaussian mixture models
KW - Intrinsic motivations
UR - http://www.scopus.com/inward/record.url?scp=84948747253&partnerID=8YFLogxK
U2 - 10.3233/978-1-61499-578-4-9
DO - 10.3233/978-1-61499-578-4-9
M3 - Conference contribution
AN - SCOPUS:84948747253
T3 - Frontiers in Artificial Intelligence and Applications
SP - 9
EP - 18
BT - Artificial Intelligence Research and Development - Proceedings of the 18th International Conference of the Catalan Association for Artificial Intelligence
A2 - Boixader, Dionis
A2 - Grimaldo, Francisco
A2 - Armengol, Eva
PB - IOS Press
T2 - 18th International Conference of the Catalan Association for Artificial Intelligence, CCIA 2015
Y2 - 21 October 2015 through 23 October 2015
ER -