# vectr-ucla/direct_lidar_inertial_odometry

[IEEE ICRA'23] A new lightweight LiDAR-inertial odometry algorithm with a novel coarse-to-fine approach in constructing continuous-time trajectories for precise motion correction.

Repository: https://github.com/vectr-ucla/direct_lidar_inertial_odometry
Canonical: https://ross.abutalabs.com/products/direct_lidar_inertial_odometry
Language: C++
License: MIT
License Family: permissive
Topics: 3d-mapping, imu, lidar, lidar-inertial-odometry, lidar-slam, localization, mapping, odometry, robotics, ros, slam, lidar-odometry
Last push: 2026-04-03T00:24:37+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 75, release rhythm 8, longevity 84
- inputs: {"age_days": 1181, "days_push": 153, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1039, forks 260 (observed 2026-08-28T04:03:19.937358+00:00)

## What it is
DLIO is a lightweight LiDAR-inertial odometry algorithm that constructs continuous-time trajectories using a coarse-to-fine approach for precise motion correction. It is a C++/ROS package supporting common LiDARs (Ouster, Velodyne, Hesai, Livox) and was published at IEEE ICRA 2023.

## Use cases
- estimate robot trajectory from LiDAR and IMU data
- build 3D maps while localizing a moving robot
- perform real-time odometry on resource-constrained robots
- correct motion distortion in LiDAR point clouds
- run SLAM-style localization with a Livox or Ouster sensor
- replace heavier LIO pipelines like LIO-SAM with a lighter alternative

## When to choose
- you need lightweight, real-time LiDAR-inertial odometry in a ROS stack
- your robot has a 6-axis IMU and a supported LiDAR (Ouster, Velodyne, Hesai, Livox)
- you need precise motion correction for fast-moving platforms
- you want an MIT-licensed, research-backed odometry algorithm

## When to avoid
- you need visual or visual-inertial SLAM with cameras
- your LiDAR and IMU cannot be time-synchronized
- you need a pure LiDAR solution without an IMU
- you are not using ROS or Linux

## Facets
- artifact type: library
- maturity: active
- function: simulation, computer-vision, middleware
- domain: robotics, autonomous-vehicles
- platform: cpp
- tags: lidar-inertial-odometry, slam, lidar, imu, odometry, mapping, localization, continuous-time-trajectory, ros, point-clouds, algorithms, linux

## Member repositories
- vectr-ucla/direct_lidar_inertial_odometry (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:19.937358+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:03:56.103691+00:00, confidence not recorded.
  - readme: https://github.com/vectr-ucla/direct_lidar_inertial_odometry (fetched 2026-08-28T04:03:19.937358+00:00, sha 0203f6a52a20)
- Data as of 2026-08-30T08:39:29.467469+00:00.