Background
Many future space missions will require robots with high levels of autonomy that can interact with objects in space, just as current terrestrial robots operate. This requires reasoning about and operating in three-dimensional (3D) environments, which in turn requires an autonomous robot to reconstruct 3D models of objects in its environment. However, these space robots will face severe computational resource constraints compared to their terrestrial counterparts, which makes it imperative to develop resource-constrained photogrammetry algorithms for these applications.
Approach
We adapted the Fast Lightweight Mesh Estimation Algorithm (FLaME) for use in space applications. This algorithm using variational smoothing on Delaunay graphs to reconstruct 3D surfaces in real time on limited hardware [1, 2]. Delaunay triangulation decomposes an image into geometric primitives, and then a regularization function aligns the vertices of the primitives into a mesh that is iteratively grown. This approach enables granular control over the quality of the reconstruction, allowing the user to exchange reconstruction fidelity for processing power.
Accomplishments
We adopted FLaME for space applications. We built a pipeline with space-specific preprocessing steps to eliminate background objects from the reconstruction, and we modified the algorithm to work with long range views of target objects. Furthermore, we ported the algorithm to hardware suitable for space applications.