Year: 2024
Type: dissertation
Abstract: Autonomously operating unmanned aerial vehicles (UAVs) are vital for exploring unknown spaces. Search and rescue missions, building mapping, surveying, reconnaissance, and extraterrestrial cave and lava tube exploration all benefit from a robust system of vehicles capable of remote exploration. This work realizes a system of drones for the exploration of such spaces. The presented system consists of lightweight quadcopters that employ Visual-Inertial SLAM for real-time localization and Time of Flight occupancy grid mapping for real-time 3D mapping, yielding similar results to the online SLAM solution but without the need for a 360-degree 3D LiDAR scanner. A custom 3D printed mounting system is utilized to carry a headlamp for illuminating dark environments during viSLAM flight. A waypoint-based Leader-Follower algorithm and a custom MAVLink-based ground station are deployed to control the system and direct the swarm of UAVs in a train configuration. A DCNN is integrated into the UAV system to facilitate real-time object detection and empower autonomous navigation. Complete system flight tests in an artificial cave environment are conducted to evaluate system communication, navigation, and 3D mapping ability. Robust leader-follower configuration, 3D occupancy mapping at resolutions of 0.05 meters, accurate localization in GPS-denied and low-light conditions, and autonomous mission capabilities are all demonstrated.
Authors: Blanchard, Nicolas, Blanchard, Nicolas
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7006441560
