Multi-drone inspection at MERL
Bring coordinated inspection missions into a real-drone experimental pipeline.
Visual description
I configured SLAM Toolbox for independent localization, generated 2D maps for subsequent point-cloud representations, and ran RViz2 and hardware experiments. The diagram is an original mission illustration; it is not footage of the MERL experiment or an output of the paper’s planner.
The problem
An inspection team must cover targets in a constrained environment while accounting for obstacles, separation and the need to recharge.
My work
During my MERL internship, I implemented, integrated and experimentally validated multi-agent trajectory planning and tracking for Crazyflie inspection missions. I set up and maintained the ROS2/CrazySwarm2 stack and integrated trajectory execution, tracking, visualization and testing.
Context & evidence
I configured SLAM Toolbox for independent localization, generated 2D maps for subsequent point-cloud representations, and ran RViz2 and hardware experiments. The diagram is an original mission illustration; it is not footage of the MERL experiment or an output of the paper’s planner.