Autonomous drone coordination in RF-denied environments through leader-follower systems and computer vision

Endrowednes Kuantama*, Alice James, Avishkar Seth

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

Abstract

Drone swarm technology often employs a leader-follower strategy, where a single drone assumes the role of the leader and directs multiple follower drones. The leader and followers communicate through a designated protocol for seamless data exchange and coordination. This paper addresses scenarios where traditional radio frequency (RF) communication is disrupted or denied, focusing on enhancing the robustness and reliability of drone operations for follower drones. The leader drone can use communication-resistant technologies and advanced computer vision algorithms to guide the follower drones. Additionally, the leader drone features a tail LED light with a directional arrow symbol and three colour variants of blue, yellow and pink for speed display with 0.89,0.98 and 0.96 accuracy rates, respectively. In this proposed design, follower drones maintain a consistent distance, altitude, and angle relative to the leader drone, with the machine learning algorithm utilizing region-based segmentation for practical guidance. Experimental results demonstrate that the system achieves an impressive response time of 10 ms per frame, with an 18 m detection range and less than 1% error for altitude adjustments in low-light conditions. Notably, the follower drones consistently maintain a 9 5% reliability in following the leader with the specified distance and altitude.

Original languageEnglish
Title of host publication2024 9th IEEE International Conference on Advanced Robotics and Mechatronics
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages741-746
Number of pages6
ISBN (Electronic)9798350385724, 9798350385717
ISBN (Print)9798350385731
DOIs
Publication statusPublished - 2024
Event9th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2024 - Tokyo, Japan
Duration: 8 Jul 202410 Jul 2024

Publication series

Name
ISSN (Print)2993-4982
ISSN (Electronic)2993-4990

Conference

Conference9th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2024
Country/TerritoryJapan
CityTokyo
Period8/07/2410/07/24

Cite this