Towards Autonomous Aerial Scouting Using Multi-Rotors in Subterranean Tunnel Navigation

Abstract

This work establishes a robocentric framework around a non-linear Model Predictive Control (NMPC) for autonomous navigation of quadrotors in tunnel-like environments. The proposed framework enables obstacle free navigation capabilities for resource constraint platforms in areas with critical challenges including darkness, textureless surfaces as well as areas with self-similar geometries, without any prior knowledge. The core contribution of the proposed framework stems from the merging of perception dynamics in a model-based optimization approach, aligning the vehicles heading to the tunnels' open space expressed in the x axis coordinate in the image frame of the most distant area. Moreover, the aerial vehicle is considered as a free-flying object that plans its actions using egocentric onboard sensors. The proposed method can be deployed in both fully illuminated indoor corridors or featureless dark tunnels, leveraging visual processing from either RGB-D or monocular sensors for generating direction commands to keep flying in the proper direction. Multiple experimental field trials demonstrate the effectiveness of the proposed method in challenging environments.

Research on Mapping Error Control of Underground Space Mobile LiDAR Constrained by Cooperative Targets

“…Although mobile LiDAR technology has been applied in underground spatial information measurement, there are still challenges for large-scale 3D data acquisition in long tunnels and indoor spaces without GNSS signals due to the lack of significant features or complex environments. The current research on the rapid acquisition and mapping of underground space information can be divided into four categories: mobile measurement system for measuring and its improvement [11][12][13][14][15][16][17][18][19][20][21], laser based on simultaneous localization and mapping (SLAM) algorithm [22][23][24][25], monocular/ binocular vision sensor [26], and RGBD (Red, Green, Blue, Depth map) vision sensor mobile robot system [27][28][29][30] and its corresponding unmanned aerial vehicle (UAV) [31][32][33][34][35] platform.…”

Ultrasonic- and IMU-Based High-Precision UAV Localization for the Low-Cost Autonomous Inspection in Oil and Gas Pressure Vessels

“…However, considering the dark and textureless environment, the localisation performance for vision based approaches will be influenced. Differently, authors in [7] and [8] from the same research group proposed a deep learning based direction identification approach for micro aerial vehicle (MAV) inspection inside a mining tunnel. Instead of the precise localisation, the images captured by the on-board camera were exploited for heading direction identification to prevent collision.…”