Development of a robot-supported measuring system for equivalence analysis of surface materials by means of sensor fusion

 

Knowing how customers perceive the quality of a product before it is on the market is a dream of every company. Thus, this research project shows an approach to realizing the prediction of perceived quality through the development of a robotic multisensory measurement system.

Today's products are highly developed and almost interchangeable in terms of their technical properties and functional quality aspects. Therefore the perceived quality becomes more and more important for product designers. It is no longer sufficient to develop a product that meets the functional requirements of the customer; a product must at the same time meet the sensory perception. The sensory design of products plays an important role in the overall assessment of quality by the customer. So far, sensory design usually considers visual, acoustic and haptic aspects of a product separately, but human perception is multi-sensory and multimodal by nature, so that the combined assessment is inevitable.

The aim of this research project is the development of a robot-supported, multisensory measurement system for predicting the perceived quality of surface materials by machine learning.

The literature offers approaches, mostly based on human studies, to capture the subjective perception of the customer and to derive design specifications for the product development process. In addition to subjective studies, this research project pursues the approach of making multisensory perception tangible and objective through alternative metrological solutions. The multisensory measuring system for surface material characterization fuses haptic, optical and acoustic sensors according to the human stimulus processing chain. Subsequently, the objective measurement data are linked with the subjective data via machine learning algorithms in order to predict the perceived quality. This approach can be used in the product development process to predict which materials add value for the customer.