Ant Colony Optimization for Cooperative Inspection Path Planning Using Multiple Unmanned Aerial Vehicles

TL;DR

This work tackles cooperative inspection path planning for multiple UAVs by turning 3D structural models into formation-aware viewpoints and solving an extended traveling salesman problem with Ant Colony Optimization. The method integrates a virtual leader-follower UAV formation, camera footprint geometry, and DBSCAN-based viewpoint clustering to produce coverage-friendly viewpoints, then optimizes the inspection path via ACO using a carefully weighted cost function that penalizes altitude changes. Experimental results on real 3D models show the approach yields feasible inspection paths and, for complex structures, substantial path-length reductions (up to 29.47% vs a back-and-forth heuristic). The combination of viewpoint generation with ACO demonstrates practical effectiveness for real-world SHM tasks and is available as open-source code.

Abstract

This paper presents a new swarm intelligence-based approach to deal with the cooperative path planning problem of unmanned aerial vehicles (UAVs), which is essential for the automatic inspection of infrastructure. The approach uses a 3D model of the structure to generate viewpoints for the UAVs. The calculation of the viewpoints considers the constraints related to the UAV formation model, camera parameters, and requirements for data post-processing. The viewpoints are then used as input to formulate the path planning as an extended traveling salesman problem and the definition of a new cost function. Ant colony optimization is finally used to solve the problem to yield optimal inspection paths. Experiments with 3D models of real structures have been conducted to evaluate the performance of the proposed approach. The results show that our system is not only capable of generating feasible inspection paths for UAVs but also reducing the path length by 29.47\% for complex structures when compared with another heuristic approach. The source code of the algorithm can be found at https://github.com/duynamrcv/aco_3d_ipp.

Figures (9)

• Figure 1: Overview of the proposed method
• Figure 2: The camera's field of view
• Figure 3: Overlapping area of two footprints
• Figure 4: Horizontal and vertical overlapping requirements
• Figure 5: Virtual leader's viewpoint generation