An AI-Based Pedagogical Tool for Creating Sketched Representation of Emotive Product Forms in the Conceptual Design Stages

Abstract

This paper presents an AI-based pedagogical solution to aid designers in an appropriate analysis of existing product forms, and to provide feedback to them in the ideation of new forms pertaining to specific emotions and attributes. Sketching is often used as a tool for ideation and communication, especially by artists and designers. It is the non-ambiguity in the sketched representation that is crucial for the effective communication of ideas amongst the stakeholders involved in the product development process. Sketching, therefore, becomes the critical skill that an aspiring designer should acquire in design schools or during the learning phases of their careers. Hence, a pedagogical support system to assist novice designers in developing their ideas unambiguously through sketched representations is necessary. In this study, an image classification-based machine learning (ML) model is trained on a dataset containing images of lines. Further, this model is validated on a set of concept sketches, and a smartphone-based learning application for novice designers is proposed as a pedagogical feedback tool for the conceptual design stage.