Kimera-Multi: a System for Distributed Multi-Robot Metric-Semantic Simultaneous Localization and Mapping

TL;DR

Kimera-Multi is a fully distributed multi-robot SLAM system that creates real-time 3D semantic maps, improving accuracy and robustness while reducing computational and communication costs.

Contribution

This work introduces Kimera-Multi, the first distributed multi-robot system for dense metric-semantic SLAM with novel outlier rejection and mesh correction techniques.

Findings

Builds accurate 3D semantic meshes in real-time

Robust to incorrect loop closures

Requires less computation and communication than existing methods

Abstract

We present the first fully distributed multi-robot system for dense metric-semantic Simultaneous Localization and Mapping (SLAM). Our system, dubbed Kimera-Multi, is implemented by a team of robots equipped with visual-inertial sensors, and builds a 3D mesh model of the environment in real-time, where each face of the mesh is annotated with a semantic label (e.g., building, road, objects). In Kimera-Multi, each robot builds a local trajectory estimate and a local mesh using Kimera. Then, when two robots are within communication range, they initiate a distributed place recognition and robust pose graph optimization protocol with a novel incremental maximum clique outlier rejection; the protocol allows the robots to improve their local trajectory estimates by leveraging inter-robot loop closures. Finally, each robot uses its improved trajectory estimate to correct the local mesh using mesh deformation techniques. We demonstrate Kimera-Multi in photo-realistic simulations and real data. Kimera-Multi (i) is able to build accurate 3D metric-semantic meshes, (ii) is robust to incorrect loop closures while requiring less computation than state-of-the-art distributed SLAM back-ends, and (iii) is efficient, both in terms of computation at each robot as well as communication bandwidth.