Search-based co-creation of software models: The case of particle systems for video games

Abstract

Context:The video game industry is one of the fastest-growing industries in the world. However, the creation of content is the bottleneck of the industry nowadays. Objective:In this paper, we propose a new approach for co-creating content by means of combining an evolutionary algorithm Map-Elites, and software models. Our approach involves generating a large number of software models and selecting the best ones based on a fitness function. This fitness function is guided by the human, who chooses which content fits their interests best. Method:We evaluated this approach in the domain of Particle Systems (PS). PS are a popular type of content used to create visual effects such as explosions, fire, smoke, or rain. Our evaluation also involves industry experts of different roles in the video game development process. Using our approach, they were tasked to create PS for their games. Then, they compared the generated models with handmade ones. Results:Our results show that practitioners chose the generated models four out of five times over handmade ones as a better fit for their projects. Furthermore, models created with our approach by non-experts in five minutes are similar in quality to the ones hand-made by an expert in 15 min. Conclusion:In conclusion, using human artistic taste to guide the algorithm renders positive results in creative tasks such as content generation for video games. With minor adjustments, the generated content can be game-ready, accelerating development.