The influence of the radial basis function training strategy on the performance of a neural gripper

Authors: Valente, C.M.O.¹; Schammass, A.¹; Araújo, A.F.R.²; P.Caurin, G.A.³

Source: Advanced Robotics, Volume 14, Number 8, 2001 , pp. 669-682(14)

Buy & download fulltext article:

Price: $35.00 plus tax (Refund Policy)

Abstract:

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.

Keywords: GRASPING; NEURAL NETWORKS; IMAGE PROCESSING; ROBOT; GRIPPER

Document Type: Research article

DOI: http://dx.doi.org/10.1163/156855301750078739

Affiliations: 1: Department of Mechanical Engineering, Universidade de São Paulo, P.O. Box 359, 13566-590, São Carlos, SP, Brazil 2: Department of Electrical Engineering, Universidade de São Paulo, P.O. Box 359, 13566-590, São Carlos, SP, Brazil 3: Campus ABC, Universidade Bandeirantes, São Paulo, Brazil

Publication date: 2001-02-01