Active Neural Mapping at Scale
This work addresses the problem of efficient and robust active mapping for robots in large-scale indoor environments, offering an incremental improvement to existing NeRF-based methods.
This paper introduces a NeRF-based active mapping system designed for efficient and robust exploration of large indoor environments. By extracting a generalized Voronoi graph (GVG) from the neural map, the system achieves competitive results in reconstruction accuracy, coverage completeness, and exploration efficiency across various scales.
We introduce a NeRF-based active mapping system that enables efficient and robust exploration of large-scale indoor environments. The key to our approach is the extraction of a generalized Voronoi graph (GVG) from the continually updated neural map, leading to the synergistic integration of scene geometry, appearance, topology, and uncertainty. Anchoring uncertain areas induced by the neural map to the vertices of GVG allows the exploration to undergo adaptive granularity along a safe path that traverses unknown areas efficiently. Harnessing a modern hybrid NeRF representation, the proposed system achieves competitive results in terms of reconstruction accuracy, coverage completeness, and exploration efficiency even when scaling up to large indoor environments. Extensive results at different scales validate the efficacy of the proposed system.