# Global Mapping & Localization

**Community-standard packages for state estimation.**

Kompass is designed to be modular. While it handles the core *Navigation*, it relies on standard community packages for **Global Localization** and **Mapping**.

We recommend the following battle-tested solutions to integrate with Kompass:

<br>

::::{grid} 1 2 2 3
:gutter: 3

:::{grid-item-card} {material-regular}`gps_fixed;1.5em;sd-text-primary` Robot Localization
:link: https://github.com/cra-ros-pkg/robot_localization

**Sensor Fusion (EKF)**
The standard for fusing IMU, Odometry, and GPS data. Use this to provide the robust `odom` $\rightarrow$ `base_link` transform required by Kompass.
:::

:::{grid-item-card} {material-regular}`map;1.5em;sd-text-primary` SLAM Toolbox
:link: https://github.com/SteveMacenski/slam_toolbox

**2D SLAM & Localization**
A highly efficient laser-based SLAM package. Use this to generate your initial map or for "Lifelong" mapping in changing environments.
:::

:::{grid-item-card} {material-regular}`view_in_ar;1.5em;sd-text-primary` Glim
:link: https://koide3.github.io/glim/

**3D LiDAR-Inertial Mapping**
A GPU-accelerated mapping framework. Use this for high-fidelity 3D SLAM and mapping using LiDAR and IMU data.
:::
::::

:::{admonition} Kompass Map Server
:class: tip
Remember that Kompass includes its own [**3D-capable Map Server**](map_server.md) if you need to work directly with Point Cloud (`.pcd`) files generated by tools like Glim.
:::