Olson, Jacob (Brigham Young University), Bidstrup, Craig (Uber ATG), Anderson, Brady (Brigham Young University), Parkinson, Alan (Brigham Young University), McLain, Tim (Brigham Young University)

Optimal Multi-Agent Coverage and Flight Time with Genetic Path Planning

Scheduled for presentation during the Regular Session "Path Planning II" (WeB2), Wednesday, September 2, 2020, 15:40−16:00, Kozani

2020 International Conference on Unmanned Aircraft Systems (ICUAS), September 1-4, 2020 (Postponed from June 9-12, 2020), Athens, Greece

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

Abstract

When generating 3D maps with unmanned aerial vehicles (UAVs), it is important for the mapping algorithm to have good coverage of the environment. It is also important, especially when planning paths for multiple agents, to have loop closures along each flight path and with other agents. Because multirotor UAVs are limited in flight time, the flight paths must be limited in length. Generating a good flight path to map a new environment can be difficult and tedious because of the free-form nature of a flight path. To solve this problem, we propose using a genetic algorithm designed to maximize total area coverage while minimizing flight time and enforcing sufficient loop closures. The natural ability of genetic algorithms to rapidly explore a design space is advantageous when solving complex free-form problems like path planning.