OKVIS2: Realtime Scalable Visual-Inertial SLAM with Loop Closure

TL;DR

OKVIS2 introduces a real-time, scalable VI-SLAM system that effectively handles long and repeated loop closures, outperforming many existing open-source solutions in accuracy and robustness.

Contribution

It presents a novel pose-graph based VI-SLAM approach that efficiently manages loop closures and large-scale environments with real-time performance.

Findings

Achieves state-of-the-art accuracy in VI-SLAM tasks.

Handles long and repeated loop closures effectively.

Operates in real-time with scalable graph optimization.

Abstract

Robust and accurate state estimation remains a challenge in robotics, Augmented, and Virtual Reality (AR/VR), even as Visual-Inertial Simultaneous Localisation and Mapping (VI-SLAM) getting commoditised. Here, a full VI-SLAM system is introduced that particularly addresses challenges around long as well as repeated loop-closures. A series of experiments reveals that it achieves and in part outperforms what state-of-the-art open-source systems achieve. At the core of the algorithm sits the creation of pose-graph edges through marginalisation of common observations, which can fluidly be turned back into landmarks and observations upon loop-closure. The scheme contains a realtime estimator optimising a bounded-size factor graph consisting of observations, IMU pre-integral error terms, and pose-graph edges -- and it allows for optimisation of larger loops re-using the same factor-graph asynchronously when needed.