PREDICTION OF HUMAN REACH POSTURE USING A NEURAL-NETWORK FOR ERGONOMIC MAN MODELS

For proper evaluation of operator's usability through ergonomic man mo dels, accurate prediction of human reach is one of the essential funct ions that those models should possess. This study examined the applica bility of artificial neural networks to the prediction of human reach posture. The three-dimensional motion trajectories of the joints of up per limb (shoulder, elbow, and wrist) in the right arm from 5 percenti le female to 95 percentile male were obtained through a motion analysi s system that photographed actual human reach. The data obtained were divided into two data sets - training data set and test data set. The backpropagation method being usually used for a pattern associator was employed as a tool for predicting such human movements. Comparisons b etween prediction and real measurements were made using a pairwise t-t est, and no significant differences were found between the two data se ts for all the joints considered. Thus, the neural network approach ad opted in this study showed a very promising prediction capability of h uman reach and it is, therefore, expected that this method be used to accurately simulate human reach better than existing heuristic or anal ytic methods as well as to improve a human modelling capability in gen eral.