LVI-SAM: Tightly-coupled Lidar-Visual-Inertial Odometry via Smoothing and Mapping

TL;DR

LVI-SAM is a real-time, tightly-coupled lidar-visual-inertial odometry framework that enhances accuracy and robustness in diverse environments through joint smoothing and mapping.

Contribution

It introduces a novel tightly-coupled factor graph approach integrating lidar, visual, and inertial data for improved odometry and mapping.

Findings

Achieves high accuracy in diverse environments.

Maintains robustness even when one subsystem fails.

Operates in real-time with extensive dataset validation.

Abstract

We propose a framework for tightly-coupled lidar-visual-inertial odometry via smoothing and mapping, LVI-SAM, that achieves real-time state estimation and map-building with high accuracy and robustness. LVI-SAM is built atop a factor graph and is composed of two sub-systems: a visual-inertial system (VIS) and a lidar-inertial system (LIS). The two sub-systems are designed in a tightly-coupled manner, in which the VIS leverages LIS estimation to facilitate initialization. The accuracy of the VIS is improved by extracting depth information for visual features using lidar measurements. In turn, the LIS utilizes VIS estimation for initial guesses to support scan-matching. Loop closures are first identified by the VIS and further refined by the LIS. LVI-SAM can also function when one of the two sub-systems fails, which increases its robustness in both texture-less and feature-less environments. LVI-SAM is extensively evaluated on datasets gathered from several platforms over a variety of scales and environments. Our implementation is available at https://git.io/lvi-sam