Im, Jaehan (Nearthlab Inc), Kim, Youngjoo (Nearthlab Inc)

Spatiotemporal VRP for Collision-Free Multi-UAV Inspection Planning

Scheduled for presentation during the Regular Session "Path Planning III" (ThA3), Thursday, June 8, 2023, 10:20−10:40, Room 464

2023 International Conference on Unmanned Aircraft Systems (ICUAS), June 6-9, 2023, Lazarski University, Warsaw, Poland

This information is tentative and subject to change. Compiled on April 25, 2024

Abstract

The study proposes a method for planning optimal, collision-free routes for multiple UAVs for infrastructure inspections. The conventional approach of using the Vehicle Routing Problem (VRP) has proven to be inadequate due to the complexity of the routing problem and the difficulty in considering inter-vehicle conflict situations. To address these challenges, the Spatiotemporal VRP algorithm is introduced, which considers temporal occupation information over sparse inspection graphs. The proposed algorithm is capable of handling large-sized graphs with several hundreds of nodes and has been shown to be effective in finding feasible solutions without any failure through a series of Monte-Carlo experiments and a case study. The results of the case study demonstrate the potential of the proposed algorithm to be adapted to real-world scenarios and provide a promising solution for optimizing UAV inspection routes.