Leveraging conditional generative adversarial networks (C-GAN) and deep reinforcement learning (DRL) for innovative product concept design generation

Abstract

One significant change to the product design lifecycle is the use of Generative AI to generate ideas for product designs based on Artificial Intelligence (AI). By enhancing human designers’ imaginative and analytical capacities, AI allows for the rapid development of fresh, optimal, and individually tailored ideas. In order to improve creativity and originality in cultural as well as creative product design, this research suggests a new AI-assisted design model that integrates Conditional Generative Adversarial Networks (C-GAN) and Deep Reinforcement Learning (DRL) and the Penguin Optimization Algorithm (POA). The approach simplifies the design process and greatly enhances design quality by integrating AI-driven decision help. Extensive trials validate the performance of the model, which is applied to four separate design tasks inside the study’s complete framework. Structured surveys as well as expert input are used to assess important criteria, such as practicality, cultural adaptation, and inventiveness. The Penguin Optimization Algorithm (POA) is a nature-inspired optimization technique based on the social behavior of penguins in search of food. It uses a population of candidate solutions, referred to as “penguins,” to explore the design space. The algorithm evaluates and refines the candidate solutions through a series of iterative steps, optimizing the design based on predefined criteria. The results show that compared to other methods, the C-GAN + DRL+ POA model is superior. Reduction of loss to 0.07, 93% model accuracy, 95% user satisfaction, and 0.92 Structural Similarity Index score are highlights. The results show that the model is the best at producing satisfying designs for users. Also, the model is quite efficient and has good generalizability, thus it may help with data and insights for cultural product design technologies.