Weaving ML with Human Aesthetic Assessments to Augment Design Space Exploration: An Automotive Wheel Design Case Study

Consumers’ emotional and cognitive attachment to product design plays a pivotal role in influencing purchasing choices. Therefore, product designers incorporate this signal as they develop new products. The goal of our work is to reduce the psychological distance between designers and consumers in the automotive concept design process. While generative AI models hold the potential to amplify creativity, these models do not have any of this specialized knowledge. In this work, we developed a novel framework and system that combines machine learning, human aesthetic assessments, and visualization to support designers in organizing a large space of automotive wheel designs. We present a case study with 10 automotive designers using the tool to inspire novel wheel designs and end with a discussion of use cases and design implications for using this framework to support professional product design practice.