A ROS-based 2D SLAM library for lifelong mapping, localization, and multi-robot SLAM with pose-graph optimization.
Slam Toolbox is a ROS/ROS2-based 2D SLAM library that enables robots to build, update, and localize within maps over extended periods. It solves the problem of lifelong operation in dynamic environments by providing tools for continuous mapping, pose-graph optimization, and multi-robot collaboration, going beyond traditional point-and-shoot SLAM.
Robotics engineers and researchers developing autonomous mobile robots for warehouses, retail, libraries, or research labs who need reliable, long-term SLAM and localization capabilities.
Developers choose Slam Toolbox for its production-ready performance, support for lifelong mapping and localization, multi-robot capabilities, and extensive tooling—offering a more mature and flexible alternative to other open-source SLAM libraries.
Slam Toolbox for lifelong mapping and localization in potentially massive maps with ROS
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Supports continuous map updates and serialization, allowing robots to refine maps over time without starting from scratch, as highlighted in the lifelong mapping section.
Benchmarked to map large areas up to 200,000 sq. ft. at 3-5x real-time speeds with efficient CPU and memory usage, based on the performance metrics.
Enables decentralized mapping across multiple robots by exchanging localized scans, facilitating collaborative mapping in shared spaces.
Includes an RVIZ plugin for manual loop closures, graph manipulation, and control over mapping sessions, enhancing debugging and manual correction.
Requires tuning numerous parameters for optimal performance, which can be daunting for users without deep SLAM expertise, as seen in the lengthy configuration section.
Serialized file formats have changed in the past, invalidating old maps and requiring conversion or re-mapping, as noted in the 03/23/2021 note on file incompatibility.
Some features, like the 'true lifelong' mapping mode and alternative solvers (GTSAM/G2O), are experimental or not actively maintained, limiting reliability.
slam_toolbox is an open-source alternative to the following products:
Cartographer is a mapping and geospatial data visualization tool or library, often used for creating interactive maps and handling geographic information in applications.
RTAB-Map is a real-time appearance-based mapping library for 3D mapping and localization using RGB-D cameras, stereo cameras, or lidar sensors.