EllipseLIO: Adaptive LiDAR Inertial Odometry with an Ellipsoid Representation

TL;DR

EllipseLIO is a real-time LiDAR inertial odometry method that adapts to various environments and sensors without manual tuning, outperforming existing approaches in diverse scenarios.

Contribution

The paper introduces EllipseLIO, a novel adaptive LIO approach that generalizes across different environments and sensors without scenario-specific tuning.

Findings

Achieves 38% lower odometry error on average compared to state-of-the-art methods.

Is the only approach that does not diverge in any tested experiment.

Outperforms existing LIO methods across five diverse datasets.

Abstract

LiDAR Inertial Odometry (LIO) is a critical component for many mobile robots that need to navigate without relying on external positioning (e.g., GPS). Platforms that operate autonomously in different environments and with heterogeneous LiDAR sensors require a LIO approach that can adapt to these different scenarios without human intervention. Existing LIO approaches can typically provide reliable and accurate odometry in scenarios with similar environments and sensors when suitably tuned. However, many approaches struggle to retain robust odometry across heterogeneous environments and sensors while using a consistent configuration. This paper presents EllipseLIO, a real-time LIO approach that generalises between scenarios by using methods for LiDAR scan filtering and registration that adapt to the sensor capabilities and environment without requiring scenario-specific tuning. Experiments with EllipseLIO and state-of-the-art LIO approaches on five datasets with diverse and challenging scenarios demonstrate that EllipseLIO is the best-performing approach overall. It achieves a 38% lower odometry error on average than the second-best approach and is the only approach that does not diverge in any experiment. An open-source version of EllipseLIO will be available at github.com/v4rl-ucy/ellipselio.