# ethz-asl/maplab

A Modular and Multi-Modal Mapping Framework

Repository: https://github.com/ethz-asl/maplab
Canonical: https://ross.abutalabs.com/products/maplab
Homepage: https://maplab.asl.ethz.ch
Language: C++
License: Apache-2.0
License Family: permissive
Topics: mapping, slam, not-matlab
Last push: 2024-05-31T08:49:33+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": 3201, "days_push": 824, "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 2867, forks 750 (observed 2026-08-28T04:07:26.762773+00:00)

## What it is
maplab 2.0 is an open, research-oriented C++ mapping framework for multi-session and multi-robot SLAM, built on ROS. It provides robust visual-inertial odometry, large-scale map optimization, and dense reconstruction, extensively tested on real robots.

## Use cases
- build a visual-inertial SLAM system for a robot
- merge and optimize maps from multiple sessions
- run multi-robot collaborative mapping
- generate dense 3D reconstructions from camera data
- localize a robot against a prebuilt visual map
- research platform for SLAM algorithm development

## When to choose
- you need multi-session or multi-robot mapping with map optimization
- you want a proven visual-inertial odometry and localization stack on Ubuntu/ROS
- you are doing SLAM research and want an extensible C++ framework

## When to avoid
- you need a lightweight out-of-the-box SLAM for non-Linux platforms
- your project is not ROS-based
- you need active feature development rather than a maintained research codebase

## Facets
- artifact type: framework
- maturity: maintenance
- function: computer-vision, robotics, simulation, graphics
- domain: robotics, computer-vision, autonomous-vehicles
- platform: cpp
- tags: slam, visual-inertial-odometry, multi-session-mapping, multi-robot, ros, dense-reconstruction, research-framework, algorithms, linux

## Member repositories
- ethz-asl/maplab (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:26.762773+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 2026-08-30T07:36:05.663031+00:00, confidence not recorded.
  - readme: https://github.com/ethz-asl/maplab (fetched 2026-08-28T04:07:26.762773+00:00, sha be5504909657)
- Data as of 2026-08-30T08:39:29.467469+00:00.