MODELING AND SIMULATION OF THE HAND GRASPING USING NEURAL NETWORKS

In this paper we present preliminary results of a study on the use of artificial neural networks to model and simulate the hand grasping. Re sults of this study will provide a basic understanding of the co-ordin ation and control of multiple degrees of freedom upper limb prosthetic devices and robotic end effectors when interacting with the environme nt. We assumed the hand to be a black box with the inputs being the ob ject and simulation time sequence, whilst the output is the grasping p ostures over time. We trained the network with samples of key postures of the hand grasping several object shapes and sizes. The back-propag ation technique was used to update the weights of the network. We foun d that the neural network is able to reproduce the postures of the han d grasping objects of different shapes and sizes from a single of neur al network weights. (C) 1997 IPEM. Published by Elsevier Science Ltd.