NEATWork: A Spatial Network Optimizer

Abstract

NASA’s planned sustained presence of humans on the Moon will require significant volumes of icy regolith transport across the lunar surface. Algorithmic planning of efficient spatial transport networks connecting multiple terminals and optimizing across a range of objectives remains an open challenge. To address this problem, we developed NEATWork, a spatial network planner. By modifying the well-known NEAT genetic algorithm—traditionally used for the development of neural networks—we present a graph optimization approach that can take into account various spatial and topological objectives. We illustrate our solution using the case of lunar transport network planning, though it can be easily deployed in other network planning scenarios where spatial cost maps can be made and the flexibility for a black box cost function optimization is of interest. We provide two open-source implementations.