fiducials
A ROS-based system for robot localization and mapping using ceiling or floor-mounted fiducial markers.
What is fiducials?
Fiducials is a ROS package that implements a Simultaneous Localization and Mapping (SLAM) system using fiducial markers (like QR codes) mounted on ceilings or floors. It allows robots to build a map of these markers and then use them to determine their precise location and orientation in an environment. This solves the problem of reliable indoor localization for robots without relying on expensive hardware.
Robotics developers and researchers working on autonomous mobile robots, especially those needing cost-effective indoor localization solutions in structured environments.
It offers a simple, vision-based approach to robot localization using easily deployable fiducial markers, avoiding the complexity and cost of systems like LIDAR or motion capture. The ability to use both ceiling and floor mounting provides flexibility for different robot designs and applications.
Overview
Simultaneous localization and mapping using fiducial markers.
Use Cases
Best For
- Indoor robot localization in warehouses or factories
- Educational robotics projects teaching SLAM concepts
- Augmenting existing robot navigation with fiducial-based correction
- Low-cost alternatives to LIDAR-based localization systems
- Robots operating in environments with structured ceilings or floors
- Applications like EZ-Map or Conveyorbot requiring additional localization data
Not Ideal For
- Robots operating in outdoor or unstructured environments without mounted markers
- Applications requiring real-time localization without visual dependencies (e.g., high-speed drones)
- Teams that need ad-hoc deployment without pre-installing fiducials
- Projects demanding sub-millimeter precision that fiducial detection may not guarantee
Pros & Cons
Pros
Uses simple fiducial markers instead of expensive systems like LIDAR, making it accessible for educational and low-budget robotics projects as highlighted in the README's philosophy.
Supports both ceiling and floor fiducials, allowing adaptation to different robot designs such as EZ-Map and Conveyorbot, as specified in the README.
Requires only one known fiducial position to start building the map, reducing setup complexity according to the README's overview.
Provides accurate localization in structured indoor environments by detecting visual markers, avoiding drift issues common in odometry-based methods.
Cons
Necessitates pre-installed fiducial markers, making it unsuitable for dynamic or unprepared spaces where marker deployment isn't feasible.
Localization fails if markers are occluded, dirty, or out of camera range, reducing robustness in cluttered or low-light conditions.
As a ROS package, it requires familiarity with the ROS ecosystem, which can add complexity for developers new to robotics software frameworks.
Frequently Asked Questions
Related Projects
ORB_SLAM3ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM
VINS-FusionAn optimization-based multi-sensor state estimator
hlocVisual localization made easy with hloc
open_vinsAn open source platform for visual-inertial navigation research.
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.