This project focuses on developing an autonomous drone system capable of real-time 3D mapping and environmental perception. Traditional inspection and mapping processes are often time-consuming, labor-intensive, and unsafe in complex environments such as construction sites or disaster areas. Our system addresses this problem by integrating onboard sensing and computing to enable automated data collection and mapping. This project is relevant to industries such as infrastructure inspection, search and rescue, and environmental monitoring, where efficient and safe data acquisition is critical.
Our system integrates a LiDAR sensor (Livox Mid-360), depth camera, and onboard computer (Jetson Orin Nano) to perform real-time SLAM (Simultaneous Localization and Mapping). Sensor data is processed using ROS2-based pipelines, including Fast-LIO2 for LiDAR-inertial odometry and point cloud generation. The drone was equipped with a Pixhawk 6C flight control with PX4 firmware and 4 powerful motors with each 4.4kg maximum trust. Tests generate dense point-cloud reconstructions of nearby buildings, indicating reliable mapping and state estimation.
By the end of this project, we will deliver a fully functional drone platform capable of autonomous flight and real-time 3D mapping. The system will generate accurate point cloud models of outdoor environments and demonstrate stable integration between hardware and software components. Additional deliverables include system documentation, flight test results, and visualization of reconstructed environments. A live demonstration and recorded video will be provided to showcase system performance.