MOLA-LIO integrates lidar and inertial data for real-time localization
MOLA LiDAR-Inertial Odometry (MOLA-LIO) on the COMFORT Localization Benchmark
Robotics
Summary
Knowing exactly where a robot is can be tricky. This paper describes how the authors improved a system called MOLA-LO to better figure out a robot’s position by combining laser scanning data (LiDAR) with motion sensors (IMU) and optionally leg movement information. They tested their system on a special dataset and explained how they chose their setup to work in real time. Their work is part of a challenge to compare different localization methods.
What this means in practice
- •For robotics engineers: Use combined LiDAR and inertial sensor data to improve real-time robot position estimation in complex environments.
- •For legged robot developers: Incorporate leg kinematic feedback alongside LiDAR and IMU data to enhance localization accuracy on uneven terrain.
Authors
Jose Luis Blanco-Claraco
Abstract
This short report documents our entry to the COMFORT Localization Benchmark (IROS 2026), evaluated on the GrandTour dataset recorded with the Boxi payload. It extends MOLA-LO into a LiDAR-inertial system that also ingests IMU and, optionally, legged kinematic odometry. We describe the architecture, the streams consumed, the local protocol that selected the submitted configuration, and the measurements backing our real-time claim.