# vectr-ucla/direct_lidar_odometry

[IEEE RA-L & ICRA'22] A lightweight and computationally-efficient frontend LiDAR odometry solution with consistent and accurate localization.

Repository: https://github.com/vectr-ucla/direct_lidar_odometry
Canonical: https://ross.abutalabs.com/products/direct_lidar_odometry
Language: C++
License: MIT
License Family: permissive
Topics: robotics, slam, lidar, mapping, odometry, localization, ros, imu, lidar-odometry, 3d-mapping, lidar-slam, lidar-inertial-odometry
Last push: 2024-06-08T17:36:29+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1737, "days_push": 816, "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 1046, forks 220 (observed 2026-08-28T04:03:21.689530+00:00)

## What it is
Direct LiDAR Odometry (DLO) is a lightweight, computationally-efficient frontend LiDAR odometry package for consistent and accurate pose estimation with dense point clouds, with optional IMU-based gravity alignment. Developed for NASA JPL's DARPA SubT effort, it runs as ROS nodes on Ubuntu with PCL and Eigen.

## Use cases
- estimate robot pose from lidar point clouds
- lidar-inertial odometry for drones and legged robots
- real-time state estimation on resource-constrained robots
- build 3D maps from lidar scans in ROS
- localize robots in GPS-denied environments
- replace heavy SLAM frontends with a fast odometry solution

## When to choose
- you need fast, accurate lidar odometry in a ROS1 pipeline
- you have a PointCloud2 stream and optionally an IMU
- you're working on aerial or legged robots with limited compute

## When to avoid
- you need full loop-closure SLAM or backend optimization
- you're not using ROS or Linux
- you need camera or visual-inertial odometry instead of lidar

## Facets
- artifact type: library
- maturity: stable
- function: robotics, simulation, computer-vision, middleware
- domain: robotics, autonomous-vehicles, developer-tools
- platform: cpp
- tags: lidar-odometry, slam, point-cloud-registration, state-estimation, ros, imu-fusion, localization, mapping, algorithms, linux, robotics

## Member repositories
- vectr-ucla/direct_lidar_odometry (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:21.689530+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 2026-08-30T07:02:00.271335+00:00, confidence not recorded.
  - readme: https://github.com/vectr-ucla/direct_lidar_odometry (fetched 2026-08-28T04:03:21.689530+00:00, sha 845b0456b72f)
- Data as of 2026-08-30T08:39:29.467469+00:00.