Provider: Ingenta Connect Database: Ingenta Connect Content: application/x-research-info-systems TY - ABST AU - Valente, C. M. O. AU - Schammass, A. AU - Araújo, A. F. R. AU - P.Caurin, G. A. TI - The influence of the radial basis function training strategy on the performance of a neural gripper JO - Advanced Robotics PY - 2001-02-01T00:00:00/// VL - 14 IS - 8 SP - 669 EP - 682 KW - GRIPPER KW - GRASPING KW - ROBOT KW - IMAGE PROCESSING KW - NEURAL NETWORKS N2 - In this article, a neural network-based grasping system that is able to collect objects of arbitrary shape is introduced. The grasping process is split into three functional blocks: image acquisition and processing, contact point estimation, and contact force determination. The paper focuses on the second block, which contains two neural networks. A competitive Hopfield neural network first determines an approximate polygon for an object outline. These polygon edges are the input for a supervised neural network model [radial basis function (RBF) or multilayer perceptions], which then defines the contact points. Tests were conducted with objects of different shapes, and experimental results suggest that the performance of the neural gripper and its learning rate are significantly influenced by the choice of supervised training model and RBF learning algorithm. UR - https://www.ingentaconnect.com/content/tandf/arb/2001/00000014/00000008/art00002 M3 - doi:10.1163/156855301750078739 UR - https://doi.org/10.1163/156855301750078739 ER -