Skip to content
RobothecaBeta
Log in

GLIM

  • Software
  • Navigation and mapping
  • Library

GLIM is an extensible range-based 3D mapping framework that builds maps from multi-scan registration on factor graphs, usable with many kinds of range sensors.

Source on GitHub: github.com/koide3/glim (opens in a new tab). Facts read at commit 1a197c9 (opens in a new tab).

Licenses

Code
MIT (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) (MIT) at commit 1a197c9 (opens in a new tab), on 16 Oct 2026.

Commercial use
Yes

What it does

  • Minimizes direct multi-scan registration error on factor graphs to keep mapping results consistent.
  • Supports GPU acceleration to speed up mapping and improve quality.
  • Offers an interactive map correction interface for manually fixing mapping failures.
  • Works with spinning, non-repetitive and solid-state LiDARs as well as RGB-D cameras.
  • Provides a global callback mechanism to access internal states and add constraints to the factor graph.
  • Related glim_ext package includes example extensions such as loop detection and LiDAR-visual-inertial odometry.

Written by Robotheca from the project's README (opens in a new tab) at commit 1a197c9.

Getting started

Difficulty
Advanced
Hardware it needs, as the project states it
Tested on Ubuntu 22.04 and 24.04 with CUDA 12.2, 12.6 and 13.1, and on NVIDIA Jetson Orin (Jetpack 6.1).

Maintenance

Status
Active: a commit in the last 90 days
Newest commit
8 Oct 2026 on master
Latest release
None published on GitHub

Checked on GitHub on 16 Oct 2026.

Links

Robots on Robotheca that use it

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.