Maplets: An Efficient Approach for Cooperative SLAM Map Building Under Communication and Computation Constraints

TL;DR

The paper tackles scalable cooperative SLAM in indoor/underground environments under SWaP constraints by introducing Maplets, a two-tier framework that generates small, overlapping local maplets and a global skeleton. Local maplets are compact plane-based representations with marginalized delta-poses that feed into a global batch optimizer, enabling robust cooperation with limited communication. Key contributions include a pair of maplet-alignment algorithms (ICaP) for maplet-to-maplet transforms, a Plane-based SLAM representation reducing data by over two orders of magnitude, and a PoseSLAM-based skeleton optimization that preserves global consistency while tolerating communication drops. The approach offers significant data-bandwidth reductions and graceful degradation to single-agent SLAM, with the ability to layer high-fidelity maps when resources permit.

Abstract

This article introduces an approach to facilitate cooperative exploration and mapping of large-scale, near-ground, underground, or indoor spaces via a novel integration framework for locally-dense agent map data. The effort targets limited Size, Weight, and Power (SWaP) agents with an emphasis on limiting required communications and redundant processing. The approach uses a unique organization of batch optimization engines to enable a highly efficient two-tier optimization structure. Tier I consist of agents that create and potentially share local maplets (local maps, limited in size) which are generated using Simultaneous Localization and Mapping (SLAM) map-building software and then marginalized to a more compact parameterization. Maplets are generated in an overlapping manner and used to estimate the transform and uncertainty between those overlapping maplets, providing accurate and compact odometry or delta-pose representation between maplet's local frames. The delta poses can be shared between agents, and in cases where maplets have salient features (for loop closures), the compact representation of the maplet can also be shared. The second optimization tier consists of a global optimizer that seeks to optimize those maplet-to-maplet transformations, including any loop closures identified. This can provide an accurate global "skeleton"' of the traversed space without operating on the high-density point cloud. This compact version of the map data allows for scalable, cooperative exploration with limited communication requirements where most of the individual maplets, or low fidelity renderings, are only shared if desired.

Figures (3)

• Figure 1: (a) High-density point cloud based DVO SLAM results. (b) Reduced order SLAM results with planar representations of surfaces in the scene using less than $1/100^{th}$ the data.
• Figure 2: Example maplets and alignment: (a) Maplet 1 and (b) Maplet 2, which have overlapping data. (c) coarse alignment of maplets and (d) refined alignment after ICaP, which provides the necessary delta-pose, or transform, $T$, from Maplet 1 to Maplet 2.
• Figure 3: (a) Unoptimized (blue) and optimized (red) map skeleton. Green dashed and green solid lines indicate the maplet-based loop closures pre- and post-optimization, respectively. (b) Maplet-overlays of independent vehicle delta-pose map skeletons. (c) Map generated after loop closure (green lines) included in skeleton optimization, the orange rectangular areas show the maplets alignment from optimization.