Unmanned aerial vehicle navigation in underground structure inspection: A review

Many years after construction, a number of existing old tunnels and underground structures are deteriorating with time as evidenced by cracks, large deformations, water leakage so forth, which usually require regular site inspections to record their structural deterioration taking high-pixel, high-overlap images along miles tunnel network. For complex (e.g., long caves), unmanned aerial vehicles (UAVs) may be adaptive in acquiring at multiple heights angles low operational costs. So far, UAV health monitoring has become mature for open-air surveying rapid developments robotic software hardware. However, the image acquisition working conditions still faces key challenges. This paper aims provide an overview navigation techniques confined dark spaces geotechnical engineers, geologists, drone developers other interdisciplinary researchers & professionals field. It specifies challenges application space, mainly including lack Global Navigation Satellite System (GNSS) signals, poor lighting conditions, weak features obstacle avoidance then followed strategic solutions. example, light GNSS fusion multi-sensors laser imaging, detection ranging (LiDAR) multi-cameras) can enhance localization accuracy low-luminance conditions. To address avoidance, computer vision (CV)-based algorithms deep reinforced learning [DRL]) enable effective 3D spaces, but adaptability is limited arithmetic power pre-training needs. The review relevant previous studies concludes that further development UAVs space inspection focus on operation large-scale geometric environments, semantic recognition.