The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Nous proposons un modèle d'apprentissage et de contrôle du bras pour une tâche de chargement dans laquelle un objet est chargé sur une main avec l'autre main, dans le plan sagittal. Le contrôle postural lors des interactions avec des objets fournit des points importants aux théories du contrôle moteur en termes de façon dont les humains gèrent les changements dynamiques et utilisent les informations de prédiction et de retour sensoriel. Pour le modèle d'apprentissage et de contrôle, nous avons couplé un schéma d'apprentissage par rétroaction-erreur avec une méthode Acteur-Critique utilisée comme contrôleur de rétroaction. Pour surmonter les retards sensoriels, un modèle dynamique de rétroaction (FDM) a été utilisé dans le chemin de rétroaction sensorielle. Nous avons testé le modèle proposé en simulation en utilisant un bras à deux articulations comportant six muscles, chacun avec des retards dans la génération de la force musculaire. En appliquant le modèle proposé à la tâche de chargement, nous avons montré que les commandes motrices commençaient à augmenter, avant qu'un objet ne soit chargé, pour stabiliser la posture du bras. Nous avons également constaté que le FDM contribue à la stabilisation en prédisant comment la main change en fonction du contexte de l'objet et des signaux efférents. Pour comparaison avec d'autres modèles informatiques, nous présentons les résultats de simulation d'un modèle à variance minimale.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Kyoungsik KIM, Hiroyuki KAMBARA, Duk SHIN, Yasuharu KOIKE, "Learning and Control Model of the Arm for Loading" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 4, pp. 705-716, April 2009, doi: 10.1587/transinf.E92.D.705.
Abstract: We propose a learning and control model of the arm for a loading task in which an object is loaded onto one hand with the other hand, in the sagittal plane. Postural control during object interactions provides important points to motor control theories in terms of how humans handle dynamics changes and use the information of prediction and sensory feedback. For the learning and control model, we coupled a feedback-error-learning scheme with an Actor-Critic method used as a feedback controller. To overcome sensory delays, a feedforward dynamics model (FDM) was used in the sensory feedback path. We tested the proposed model in simulation using a two-joint arm with six muscles, each with time delays in muscle force generation. By applying the proposed model to the loading task, we showed that motor commands started increasing, before an object was loaded on, to stabilize arm posture. We also found that the FDM contributes to the stabilization by predicting how the hand changes based on contexts of the object and efferent signals. For comparison with other computational models, we present the simulation results of a minimum-variance model.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.705/_p
Copier
@ARTICLE{e92-d_4_705,
author={Kyoungsik KIM, Hiroyuki KAMBARA, Duk SHIN, Yasuharu KOIKE, },
journal={IEICE TRANSACTIONS on Information},
title={Learning and Control Model of the Arm for Loading},
year={2009},
volume={E92-D},
number={4},
pages={705-716},
abstract={We propose a learning and control model of the arm for a loading task in which an object is loaded onto one hand with the other hand, in the sagittal plane. Postural control during object interactions provides important points to motor control theories in terms of how humans handle dynamics changes and use the information of prediction and sensory feedback. For the learning and control model, we coupled a feedback-error-learning scheme with an Actor-Critic method used as a feedback controller. To overcome sensory delays, a feedforward dynamics model (FDM) was used in the sensory feedback path. We tested the proposed model in simulation using a two-joint arm with six muscles, each with time delays in muscle force generation. By applying the proposed model to the loading task, we showed that motor commands started increasing, before an object was loaded on, to stabilize arm posture. We also found that the FDM contributes to the stabilization by predicting how the hand changes based on contexts of the object and efferent signals. For comparison with other computational models, we present the simulation results of a minimum-variance model.},
keywords={},
doi={10.1587/transinf.E92.D.705},
ISSN={1745-1361},
month={April},}
Copier
TY - JOUR
TI - Learning and Control Model of the Arm for Loading
T2 - IEICE TRANSACTIONS on Information
SP - 705
EP - 716
AU - Kyoungsik KIM
AU - Hiroyuki KAMBARA
AU - Duk SHIN
AU - Yasuharu KOIKE
PY - 2009
DO - 10.1587/transinf.E92.D.705
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2009
AB - We propose a learning and control model of the arm for a loading task in which an object is loaded onto one hand with the other hand, in the sagittal plane. Postural control during object interactions provides important points to motor control theories in terms of how humans handle dynamics changes and use the information of prediction and sensory feedback. For the learning and control model, we coupled a feedback-error-learning scheme with an Actor-Critic method used as a feedback controller. To overcome sensory delays, a feedforward dynamics model (FDM) was used in the sensory feedback path. We tested the proposed model in simulation using a two-joint arm with six muscles, each with time delays in muscle force generation. By applying the proposed model to the loading task, we showed that motor commands started increasing, before an object was loaded on, to stabilize arm posture. We also found that the FDM contributes to the stabilization by predicting how the hand changes based on contexts of the object and efferent signals. For comparison with other computational models, we present the simulation results of a minimum-variance model.
ER -