Intuitive Human-Swarm Interaction with Gesture Recognition and Machine Learning

Abstract

Unmanned Aerial Systems (UAS), commonly known as drones, have revolutionized various industries with their diverse applications. As the demand for seamless and intuitive drone control grows, researchers are exploring innovative approaches to improve human-swarm interaction. This paper presents a novel method for operating a swarm of drones in real time using wearable technology and machine learning. Through the integration of motion capture data and classification algorithms, we strive to achieve an intuitive level of control that is accessible to users with varying skill levels. While the full realization of this approach remains a work in progress, our research lays the groundwork for future endeavors in this domain. In this paper, we discuss the limitations of existing control methods and present our methodology for data preprocessing, model training and testing, and result analysis. Our findings indicate the potential of this approach and open avenues for refining the interaction between humans and drone swarms.