A biocybernetic method to learn hand grasping posture

@article{citeulike:2824609, abstract = {In this paper, a biocybernetic method to learn hand grasping posture definition with few knowledge about the task is proposed. The developed model is composed of two stages. The first is dedicated to the fingers inverse kinematics learning in order to locally define a single finger posture given its desired fingertip position. This motor function is fulfilled by a modular neural network architecture that tackles the discontinuity problem of inverse kinematics function (called Fingers Configuration Neural Network (FCNN)). Following the concept of direct associative learning, a second neural model is used to search the space of hand configuration and optimize it according to an evaluative function based on the results of the FCNN. Simulation results show good learning of grasping posture determination of various object types, with different numbers of fingers involved and different contact configurations.}, author = {Rezzoug, N. and Gorce, P. }, citeulike-article-id = {2824609}, doi = {http://dx.doi.org/10.1108/03684920310463885}, issn = {0368-492X}, journal = {Kybernetes: The International Journal of Systems \&\#38; Cybernetics}, keywords = {grasping, learning, neural\_network}, pages = {478--490}, posted-at = {2008-05-23 08:34:04}, priority = {2}, publisher = {Emerald Group Publishing Limited}, title = {A biocybernetic method to learn hand grasping posture}, url = {http://dx.doi.org/10.1108/03684920310463885}, year = {2003} }

TY - JOUR ID - citeulike:2824609 L3 - citeulike-article-id:2824609 TI - A biocybernetic method to learn hand grasping posture JF - Kybernetes: The International Journal of Systems & Cybernetics SP - 478 EP - 490 PB - Emerald Group Publishing Limited SN - 0368-492X N2 - In this paper, a biocybernetic method to learn hand grasping posture definition with few knowledge about the task is proposed. The developed model is composed of two stages. The first is dedicated to the fingers inverse kinematics learning in order to locally define a single finger posture given its desired fingertip position. This motor function is fulfilled by a modular neural network architecture that tackles the discontinuity problem of inverse kinematics function (called Fingers Configuration Neural Network (FCNN)). Following the concept of direct associative learning, a second neural model is used to search the space of hand configuration and optimize it according to an evaluative function based on the results of the FCNN. Simulation results show good learning of grasping posture determination of various object types, with different numbers of fingers involved and different contact configurations. KW - grasping KW - learning KW - neural_network AU - Rezzoug, N AU - Gorce, P PY - 2003/// UR - http://dx.doi.org/10.1108/03684920310463885 ER -