Vision-Based Quadrotor Landing and Tracking on Moving Ground Vehicles

This project showcases the design and development of quadrotors with the capability for autonomous landing on both stationary and moving platforms, addressing the challenge of limited flight times requiring frequent recharging. These quadrotors are equipped with advanced sensors, including a gimbal-stabilized camera for visual sensing, a laser range sensor for altitude measurement, a PIXHAWK flight controller, and a Raspberry Pi 3 for onboard computation. Using ROS, the software integrates multi-threaded visual processing and PD-based control for position, altitude, and velocity, relying on visual feedback from an ArUco marker. The system was validated through Gazebo simulations and real-world experiments, achieving reliable autonomous landing with acceptable error and the ability to track a moving platform.

Leave a comment