Graham, Conor John (Queensland University of Technology), Gonzalez, Luis Felipe (Queensland University of Technology), Sanoe, Abdullay (Queensland University of Technology)

Implementation of Partial Observable Markov Decision Process (POMDP) Algorithm Using Bitcraze Crazyflie Drones

Scheduled for presentation during the Regular Session "Micro- and Mini- UAS" (ThC2), Thursday, June 8, 2023, 15:00−15:20, Room 130

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

This paper develops a complex navigation solution for sequential drone swarm configuration using Partially Observable Markov Decision Process (POMDP) with the Bitcraze Crazyflie platform with a single localization anchor. The objective is to generate a stable control system for a swarm of drones to navigate a controlled environment toward a waypoint. The POMDP solver takes observations of the drones’ real-world positions and determines specific actions based on a network of functions designed to optimize a path toward the waypoint. Once the solver defines the next action the swarm navigates toward the selected direction sequentially. Through extensive developmental and formal testing, the developed system performs the objective with an average trajectory deviation of fewer than 0.1 meters with a duration of approximately 18 seconds. Deficiencies have been identified in the software control structure. This research highlights the importance of drone control and localization redundancies for complex navigation solutions for micro-UAV swarm configurations.