PLUME: Procedural Layer Underground Modeling Engine

TL;DR

PLUME addresses the need for diverse, accessible underground environments for planetary exploration and robotics. It introduces a Blender-based procedural pipeline that generates complete meshes and baked textures from a graph-generated skeleton, enabling rapid creation of mine or cave environments. The approach integrates graph generation (single and multi-layer graphs), mesh construction, and texture synthesis (Voronoi-Perlin), with reproducible JSON configuration and compatibility with Gazebo, Unity, Unreal, and other simulators. The work demonstrates rendering realism and simulation viability, with open-source release on GitHub, supporting AI training and exploratory robotics research.

Abstract

As space exploration advances, underground environments are becoming increasingly attractive due to their potential to provide shelter, easier access to resources, and enhanced scientific opportunities. Although such environments exist on Earth, they are often not easily accessible and do not accurately represent the diversity of underground environments found throughout the solar system. This paper presents PLUME, a procedural generation framework aimed at easily creating 3D underground environments. Its flexible structure allows for the continuous enhancement of various underground features, aligning with our expanding understanding of the solar system. The environments generated using PLUME can be used for AI training, evaluating robotics algorithms, 3D rendering, and facilitating rapid iteration on developed exploration algorithms. In this paper, it is demonstrated that PLUME has been used along with a robotic simulator. PLUME is open source and has been released on Github. https://github.com/Gabryss/P.L.U.M.E

Figures (12)

• Figure 1: Procedural generated cave with PLUME
• Figure 2: Overview of the procedural generation process of PLUME
• Figure 3: Representation of a node during the generation process. The red highlighted area represent the "forbiden" zone preventing the graph to circle on itself. Each dots represent a node. The percentage on the circle represent the node spawning probability distribution around the current node.
• Figure 4: Graph generation process. Each dot represents a node, and each red area represents the forbidden node creation angle.
• Figure 5: Left: Single layer underground graph. Right: Multi-layer underground graph. The colour gradient illustrates the elevation of the environment.