Developing Smart MAVs for Autonomous Inspection in GPS-denied Constructions
Paoqiang Pan, Kewei Hu, Xiao Huang, Wei Ying, Xiaoxuan Xie, Yue Ma, Naizhong Zhang, Hanwen Kang
TL;DR
The paper tackles autonomous inspection of indoor infrastructure in GPS-denied environments by introducing a hierarchical perception and planning framework paired with a smart MAV system. Key contributions include structoriented perception (ground/roof, columns, walls), instance-aware SHM task planning, robust indoor localization via an ESKF with LiDAR/IMU fusion, and a motion-planning/control pipeline that ensures collision-free, kinematically-feasible flight. The approach is validated in a $4000\ \mathrm{m}^2$ subterranean facility, achieving $100\%$ success in scan-path generation/execution and sub-$0.1$ m tracking errors, along with high-fidelity 3D reconstructions using $3$D Gaussian Splatting. While the system significantly improves autonomous inspection in constrained indoor spaces, it incurs high computational load and is bounded by MAV flight-time, suggesting directions for efficiency and endurance improvements in future work.
Abstract
Smart Micro Aerial Vehicles (MAVs) have transformed infrastructure inspection by enabling efficient, high-resolution monitoring at various stages of construction, including hard-to-reach areas. Traditional manual operation of drones in GPS-denied environments, such as industrial facilities and infrastructure, is labour-intensive, tedious and prone to error. This study presents an innovative framework for smart MAV inspections in such complex and GPS-denied indoor environments. The framework features a hierarchical perception and planning system that identifies regions of interest and optimises task paths. It also presents an advanced MAV system with enhanced localisation and motion planning capabilities, integrated with Neural Reconstruction technology for comprehensive 3D reconstruction of building structures. The effectiveness of the framework was empirically validated in a 4,000 square meters indoor infrastructure facility with an interior length of 80 metres, a width of 50 metres and a height of 7 metres. The main structure consists of columns and walls. Experimental results show that our MAV system performs exceptionally well in autonomous inspection tasks, achieving a 100\% success rate in generating and executing scan paths. Extensive experiments validate the manoeuvrability of our developed MAV, achieving a 100\% success rate in motion planning with a tracking error of less than 0.1 metres. In addition, the enhanced reconstruction method using 3D Gaussian Splatting technology enables the generation of high-fidelity rendering models from the acquired data. Overall, our novel method represents a significant advancement in the use of robotics for infrastructure inspection.