A Survey of Spatial Memory Representations for Efficient Robot Navigation

Ma. Madecheen S. Pangaliman, Steven S. Sison, Erwin P. Quilloy, Rowel Atienza

Keywords: spatial memory, SLAM, memory efficiency, neural implicit representations, 3D Gaussian Splatting, overhead factor, robot navigation, NeRF, visual SLAM, resource-constrained deployment

TL;DR: We introduce the overhead factor α, the ratio of runtime memory to saved map size, for robot spatial representations. Profiling neural SLAM systems reveals α spans 2.3–215×, showing that map size alone misrepresents deployment cost.

Abstract: As vision-based robots navigate larger environments, their spatial memory grows without bound, eventually exhausting computational resources, particularly on embedded platforms (8--16\,GB shared memory, $<$30\,W) where adding hardware is not an option. This survey examines the spatial memory efficiency problem across 88 references spanning 52 systems (1989--2025), from occupancy grids to neural implicit representations. We introduce the \textit{overhead factor} $\alpha = M_{\text{peak}} / M_{\text{map}}$, the ratio of peak runtime memory (the total RAM or GPU memory consumed during operation) to saved map size (the persistent checkpoint written to disk), exposing the gap between published map sizes and actual deployment cost. Independent profiling on an NVIDIA A100 GPU reveals that $\alpha$ spans two orders of magnitude within neural methods alone, ranging from 2.3 (Point-SLAM) to 215 (NICE-SLAM, whose 47\,MB map requires 10\,GB at runtime), showing that memory architecture, not paradigm label, determines deployment feasibility. We propose a standardized evaluation protocol comprising memory growth rate, query latency, memory--completeness curves, and throughput degradation, none of which current benchmarks capture. Through a Pareto frontier analysis with explicit benchmark separation, we show that no single paradigm dominates within its evaluation regime: 3DGS methods achieve the best absolute accuracy at 90--254\,MB map size on Replica, while scene graphs provide semantic abstraction at predictable cost. We provide the first independently measured $\alpha$ reference values and an $\alpha$-aware budgeting algorithm enabling practitioners to assess deployment feasibility on target hardware prior to implementation.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 11