A ROS2-based package for Simultaneous Localization and Mapping (SLAM) using AprilTag fiducial markers.
TagSLAM is a ROS2-based software package that performs Simultaneous Localization and Mapping (SLAM) using AprilTag fiducial markers. It processes visual data from cameras—optionally fused with odometry—to estimate a robot's position and build a map of its surroundings in real-time. This solves the problem of accurate spatial awareness for autonomous robots operating in environments where visual landmarks are available.
Robotics engineers and researchers working on autonomous systems, particularly those using ROS2 and needing reliable visual SLAM with fiducial markers. It's suited for projects involving multi-camera setups or requiring offline bag file processing.
Developers choose TagSLAM for its tight integration with ROS2, support for synchronized multi-camera inputs, and robust AprilTag-based landmark detection. It offers flexibility for both online operation and bag file analysis, making it a practical tool for prototyping and deployment in robotic navigation.
SLAM with apriltags
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Handles synchronized data from multiple cameras with consistent timestamp alignment, as shown in the sync_and_detect component that processes images across cameras and emits synchronized tag messages.
Supports both online live operation as a ROS2 node and offline processing from rosbag files, allowing for real-time deployment and post-analysis, as detailed in the usage instructions.
Incorporates odometry messages to improve localization accuracy, with sync_and_detect dropping non-matching odometry and aligning timestamps, enhancing robustness in sensor-fusion setups.
Relies on AprilTag fiducial markers for reliable detection and tracking, providing accurate visual landmarks that are critical for SLAM in controlled environments.
Requires ROS2 Rolling/Jazzy or newer, excluding older stable versions, which limits compatibility and may force upgrades in existing systems, as stated in the README.
The README notes 'ROS2 is WORK IN PROGRESS' and lacks comprehensive guides, making setup and troubleshooting more challenging for new users.
Demands multiple YAML files (e.g., cameras.yaml, tagslam.yaml) and careful parameter tuning for synchronization, increasing the risk of errors in deployment.
For troubleshooting issues like jerky motions, it depends on external packages like apriltag_detector, adding extra steps and potential compatibility headaches.