Use of Artificial Fiducial Markers for USV Swarm Coordination is a Naval Post Graduate thesis by Matthew Heubach.
Typical swarm algorithms (leader-follower, artificial potentials, etc.) rely on knowledge about the pose of each vehicle and inter-vehicle proximity. This information is often obtained via Global Positioning System (GPS) and communicated via radio-frequency means.. This research examines the capabilities and limitations of using a fiducial marker system in conjunction with an artificial potential field algorithm to achieve inter-vehicle localization and coordinate the motion of unmanned surface vessels operating together in an environment where satellite and radio communications are inhibited. Using Gazebo, a physics-based robotic simulation environment, a virtual model is developed for incorporating fiducial markers on a group of autonomous surface vessels. A control framework using MATLAB and the Robot Operating System (ROS) is developed that integrates image processing, AprilTag fiducial marker detection, and artificial potential control algorithms. This architecture receives multiple video streams, detects AprilTags, and extracts pose information to control the forward motion and inter-vehicle spacing in a swarm of autonomous surface vessels. This control architecture is tested for a variety of trajectories and tuned so that the swarm can successfully maintain formation control.
Publication Date- December 2022
Use of Artificial Fiducial Markers for USV Swarm Coordination contain the following major sections:
- Results and Analysis
Approved for public release. Distribution is unlimited.
C-UAS Hub does not own this content and provides a link for users at the bottom of the page to access it in its original location. This allows the author(s) to track important article metrics related to their work. All credit goes to its rightful owner.
Author- Andrew J. Horos
For additional multimedia resources, please visit the Multimedia Library.
Post Image- Futuristic Unmanned Surface Vessel (Image Credit: Adobe Stock by Andrey VP)