Modular Procedural Generation for Voxel Maps
This work addresses the need for automated environment generation in AI research, particularly for human-machine teaming, but is incremental as it builds on existing PCG concepts for a specific domain.
The authors tackled the problem of manually constructing Minecraft task environments for AI research by introducing mcg, an open-source library for procedural content generation (PCG) in voxel-based environments, enabling rapid, scalable development with semantic control and real-time generation.
Task environments developed in Minecraft are becoming increasingly popular for artificial intelligence (AI) research. However, most of these are currently constructed manually, thus failing to take advantage of procedural content generation (PCG), a capability unique to virtual task environments. In this paper, we present mcg, an open-source library to facilitate implementing PCG algorithms for voxel-based environments such as Minecraft. The library is designed with human-machine teaming research in mind, and thus takes a 'top-down' approach to generation, simultaneously generating low and high level machine-readable representations that are suitable for empirical research. These can be consumed by downstream AI applications that consider human spatial cognition. The benefits of this approach include rapid, scalable, and efficient development of virtual environments, the ability to control the statistics of the environment at a semantic level, and the ability to generate novel environments in response to player actions in real time.