Social Computational Design Method for Generating Product Shapes with GAN and Transformer Models

TL;DR

This paper introduces a social computational design method that leverages AI technologies like GANs and Transformers, supported by multi-agent systems, to generate and recommend product shapes and solutions efficiently.

Contribution

It presents a novel integrated framework combining multiple AI models and systems for intelligent product shape design and solution recommendation.

Findings

Successfully defines a design solution space.

Capable of recommending solutions from incomplete data.

Demonstrated on product shape design tasks.

Abstract

A social computational design method is established, aiming at taking advantages of the fast-developing artificial intelligence technologies for intelligent product design. Supported with multi-agent system, shape grammar, Generative adversarial network, Bayesian network, Transformer, etc., the method is able to define the design solution space, prepare training samples, and eventually acquire an intelligent model that can recommend design solutions according to incomplete solutions for given design tasks. Product shape design is used as entry point to demonstrate the method, however, the method can be applied to tasks rather than shape design when the solutions can be properly coded.