Towards Autonomous Surveying of Underground Mine Using MAVs

Abstract

Micro Aerial Vehicles (MAVs) are platforms that received great attention during the last decade. Recently, the mining industry has been considering the usage of aerial autonomous platforms in their processes. This article initially investigates potential application scenarios for this technology in mining. Moreover, one of the main tasks refer to surveillance and maintenance of infrastructure assets. Employing these robots for underground surveillance processes of areas like shafts, tunnels or large voids after blasting, requires among others the development of elaborate navigation modules. This paper proposes a method to assist the navigation capabilities of MAVs in challenging mine environments, like tunnels and vertical shafts. The proposed method considers the use of Potential Fields method, tailored to implement a sense-and-avoid system using a minimal ultrasound-based sensory system. Simulation results demonstrate the effectiveness of the proposed strategy.

Where to look: a collection of methods forMAV heading correction in underground tunnels

“…The image stream from the looking forward camera is denoted by I . Additionally, the potential fields method [33] is implemented to generate velocity references , to avoid collisions to the local surrounds using range measurements R of the 2D lidar placed on top of the MAV. Furthermore, for tracking the desired velocity and altitude references the Non‐linear Model Predictive Control (NMPC) [34] is implemented to generate the corresponding thrust and attitude commands for the low level controller.…”

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

“…The mission planner initially accepts the desired state references from the operator once. Afterwards, a potential field obstacle avoidance method is activated, generating linear x-axis and yaxis reference velocity commands in order to avoid collisions to the walls or any other obstacle standing in the way of the MAV, as shown in [26].…”

MAV Navigation in Unknown Dark Underground Mines Using Deep Learning

“…This article presents the DL method for correcting the heading direction of the MAV without relying on accurate localization schemes. The platform is flying at constant altitude and potential field [1] from 2D lidar ranges R generates linear velocities, while the CNN module provides heading rate commands for avoiding collisions based on the image stream.…”