Autonomous drone hunter operating by deep learning and all-onboard computations in GPS-denied environments

作者：Philippe Martin Wyder, Yansong Chen, Adrian J. Lasrado, Rafael J. Pelles, Robert Kwiatkowski, Edith O. A. Comas, Richard Kennedy, Arjun Mangla, Zixi Huang, Xiaotian Hu, Zhiyao Xiong, Tomer Aharoni, Tzu-Chan Chuang, Hod Lipson · 发表于：PLoS ONE · 年份：2019 · DOI：10.1371/journal.pone.0225092 · 被引用次数：46 · 研究领域：Robotics and Sensor-Based Localization、Advanced Neural Network Applications、Video Surveillance and Tracking Methods

This paper proposes a UAV platform that autonomously detects, hunts, and takes down other small UAVs in GPS-denied environments. The platform detects, tracks, and follows another drone within its sensor range using a pre-trained machine learning model. We collect and generate a 58,647-image dataset and use it to train a Tiny YOLO detection algorithm. This algorithm combined with a simple visual-servoing approach was validated on a physical platform. Our platform was able to successfully track and follow a target drone at an estimated speed of 1.5 m/s. Performance was limited by the detection algorithm's 77% accuracy in cluttered environments and the frame rate of eight frames per second along with the field of view of the camera.