Cooperative Localization of UAVs in Multi-Robot Systems Using Deep Learning-Based Detection

Abstract

The integration of multiple Uncrewed Aerial Vehicles (UAVs) across diverse domains, including agriculture, disaster management, and environmental monitoring, has demonstrated immense potential due to their operational flexibility and advanced maneuverability. However, achieving precise localization remains a significant challenge, particularly when these vehicles operate in close proximity. Standard Global Navigation Satellite System (GNSS) sensors typically provide a positional accuracy of approximately 2.5 meters, and environments with GNSS disruptions exacerbate this challenge. This paper introduces a novel cooperative localization framework designed to enhance localization accuracy in multi-robot systems comprising UAVs and Unmanned Ground Vehicles (UGVs). The proposed method leverages deep learning-based detection, specifically utilizing the YOLOv8 convolutional neural network, to enable real-time object detection and localization. By integrating perception with Kalman Filtering (KF), the approach achieves improved localization accuracy, even in challenging environments, thus advancing the state-of-the-art in cooperative multi-robot systems.