Caption: Visualization of a generated spaceship in-game.
Dr. Kai Arulkumaran, Team Leader in Araya's R&D Department, and Roberto Gallotta, Researcher, have developed an open source "AI Spaceship Generator" as part of a research project to develop novel evolutionary algorithms (EA) for procedural content generation (PCG). The algorithms based on this research will be released as a standalone application for the space exploration game " Space Engineers " on October 27.
Note that this research was funded by GoodAI, an international Czech R&D company.
Background of this research
Evolution serves as inspiration for a subset of AI programs known as evolutionary algorithms (EA), which, like their biological counterpart, have the potential to continually generate new entities. EAs are commonly used in PCG methods to (semi-)automatically generate content for video games.
While many video games rely on PCG in order to generate diverse visual and audio content, assets such as spaceships require the generated content to be functional as well as aesthetically-pleasing, which is a challenge for current PCG algorithms. Led by Kai Arulkumaran and supported by the GoodAI Grants program, the project was initiated to pursue research in the fields of evolutionary computation and computational creativity, with the goal of making an application for human-machine collaborative design.
Caption: Control panel to generate spaceships.
Caption: Araya’s (L) Kai Arulkumaran and (M) Roberto Gallotta, and Barnard College’s (R) Lisa Soros.
Description of this study
Working alongside Arulkumaran is Araya researcher Roberto Gallotta, the primary developer of the application, and Barnard College teaching and research fellow Dr. Lisa Soros, an experienced EA researcher.
Since its inception, the researchers have developed several novel algorithms [1,2,3] for PCG, and implemented a visual interface for use by game developers and players without requiring additional coding. By combining rule-based systems, PCG methods and EAs, we have succeeded in developing an automatic generation algorithm that generates content that is both visually appealing and functional.
The open source AI Spaceship Generator combines PCG techniques and evolutionary computation to enable new vessels to continually "evolve" from an initial population. At each interval, an EA produces an assortment of options for modification by users. A working blueprint can then be imported into Space Engineers for in-game piloting. User interactions with the generator will form the basis of a new experimental study that further investigates the dynamics of human-AI collaboration.
The algorithms based on this research will be released as a standalone application for the space exploration game "Space Engineers" on October 27th.
URL: https: //www.spaceengineersgame.com/
The application and source code can be downloaded here.
A live stream will take place on Thursday Oct. 27, 26:00(JST),(19:00 CEST), on the Space Engineers’ Youtube channel, where researchers will discuss and answer questions from the audience.
For more info
For inquiries, please contact https://www.araya.org/contact/
 Gallotta, R., Arulkumaran, K., & Soros, L. B. (2022). Evolving Spaceships with a Hybrid L-system Constrained Optimisation Evolutionary Algorithm. In Genetic and Evolutionary Computation Conference Companion. https://dl.acm.org/doi/abs/10.1145/3520304.3528775
 Gallotta, R., Arulkumaran, K., & Soros, L. B. (2022). Surrogate Infeasible Fitness Acquirement FI-2Pop for Procedural Content Generation. In IEEE Conference on Games. h ttps://ieeexplore.ieee.org/document/9893592
 Gallotta, R., Arulkumaran, K., & Soros, L. B. (2022). Surrogate Infeasible Fitness Acquirement FI-2Pop for Procedural Content Generation. arXiv preprint arXiv:2210.13839. Available at: https://arxiv.org/abs/2210.13839