Towards virtual assessment of human factors: A concept for data driven prediction and analysis of physical user-product interactions

Abstract

The early consideration of human factors in product development hugely favours the development of products, which excel with a positive user experience. The virtual environment of product development however, still has significant gaps in the virtual assessment and simulation of human factors, especially for user-product interactions composed of human movements. This motivates us to introduce a concept for data-driven prediction and analysis of user-product interactions. Heart of the concept is a predictive component that models the interaction between the user, represented by a musculoskeletal model, and the product, represented by product characteristics. We describe the implementation of this concept based on a pilot study for a lifting task. Motion capturing was performed to build a database and compare the results of our novel approach. The resulting kinematic and dynamic quantities show similar curve profiles with a small constant offset to the measured data. This indicates that the concept enables the virtual comparison of different designs or concepts regarding human factors.