| Author: | Tong, Ho Wang |
| Title: | Coverage path planning for autonomous structural inspection using UAV |
| Advisors: | Li, Boyang (AAE) |
| Degree: | Ph.D. |
| Year: | 2026 |
| Subject: | Drone aircraft Structural health monitoring Hong Kong Polytechnic University -- Dissertations |
| Department: | Department of Aeronautical and Aviation Engineering |
| Pages: | xiii, 105 pages : color illustrations |
| Language: | English |
| Abstract: | With the emerging concept such as low-altitude economy, Unmanned Aerial Vehicles (UAVs) are becoming a hot topic in the research field, and different applications for UAVs have been proposed. With its unique mobility, one of the emerging civil applications of UAVs is autonomous inspection. UAVs can freely navigate around the inspection target and collect data needed for different inspection purposes. In order to perform the autonomous mission, a planning algorithm is required to plan a suitable inspection path for the inspection mission. In this thesis, different aspects of inspection path planning are studied, and different algorithms are proposed to improve these aspects. First, the scalability of the inspection path planning is studied. A mixed viewpoint generation technique is proposed to improve the scalability of the path planning algorithm such that suitable inspection path can be generated for different inspection purposes. The proposed algorithm utilizes two kinds of viewpoints. The revolving viewpoints ensure that uniform coverage is achieved while the gap-filling viewpoints ensure that the coverage requirement is satisfied. A Multi-layered Angle-distance Traveling Salesman Problem (ML-ADTSP) is also proposed such that a spiral inspection path can be obtained, guaranteeing the kinodynamic feasibility of the inspection path. Using the proposed approach, suitable inspection paths can be generated for different inspection purposes, ranging from crack detection to 3D reconstruction. Second, to improve the efficiency of the inspection task, a multi-UAV system for inspection purposes is proposed. A multi-objective multiple Traveling Salesman Problem (MO-MTSP) is proposed to compute the optimized inspection path for different UAVs. The NSGACO hybrid algorithm is proposed to solve the combinatorial optimization problem. The algorithm allows the benefit of Non-dominated Sorting Genetic Algorithm (NSGA-II) and Ant Colony Optimization (ACO) to be realized throughout the iteration, improving the quality and diversity of the solutions obtained. The proposed problem also treats the location of the depot as an optimization variable, and a migration mechanism is proposed to search for the optimal depot location that aligns with the optimization objectives. The proposed algorithm allows the deployment of autonomous inspection systems that can perform repeatable inspection missions, which can be applied in construction safety inspection or aircraft inspection, where frequent inspections are required. Lastly, a parameterization-based path planning algorithm is proposed to improve the quality of the inspection task. The algorithm makes use of the parameterized surface of the 3D model to directly plan a sweep path, and dimensions-related complications can be ignored during the planning process. A barycentric-based transformation and optimization-based re-planning module are used to transform the path into 3D while minimizing the distortion during the process. To further demonstrate the scalability of the planning approach, it is used with the multi-UAV system proposed, and simulation results verify the performance of the proposed algorithm. The proposed algorithm with improved inspection quality can be applied in aircraft inspection where the quality of the task is the first priority. |
| Rights: | All rights reserved |
| Access: | open access |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/14530