Modeling and driving a reduced human mannequin through motion captured data: a neural network approach

Abstract

One of the major problems which arises in the field of virtual design is the realization of virtual mannequins able to move in a human like way. This work focuses on the analysis of the human sitting working posture, which is described by a 30-DOF mannequin, modeling the upper part of the body (pelvis, trunk, arms, and head). Trajectories formation in point to point reaching movements represents the main topic. Our approach is based on the acquisition of real human kinematics data, collected by means of an automatic motion analyzer. Starting from the kinematics database of one subject, sit in front of a desk, a neural network was trained in order to generate the movements of the virtual mannequin. The work is divided into four parts: mannequin modeling, 3D human data collection, data preprocessing according to the biomechanical model, and design and training of a multilayer perceptron neural network.