An Autonomous Drone Swarm for Detecting and Tracking Anomalies in Dense Vegetation

Abstract: Swarms of drones offer an increased sensing aperture, and by mimicking the behavior observed in natural swarms allows adapting the aperture to local conditions for enhancing sampling. Here we demonstrate that detecting and tracking heavily occluded targets is feasible in practice with such an approach. While object classification applied to conventional aerial images cannot generalize well the randomness of occlusion and is therefore inefficient even under sparse conditions, anomaly detection applied to synthetic aperture integral images is robust for dense vegetation, such as forest, and independent of pre-trained classes. Our autonomous swarm explores the environment for unknown or unexpected appearances and tracks them while continuously adapting its sampling pattern to optimize for local viewing conditions. In our real-life field experiments with a swarm of six drones, we achieve an average positional accuracy of 0.39m with an average precision 93.2% and an average recall of 95.9%. Here, adapted particle swarm optimization considers detection confidences and predicted target appearance. We show that sensor noise can be effectively included in the synthetic aperture image integration process without a computationally costly optimization of high-dimensional parameter spaces. Finally, we present a complete hard- and software framework that supports low-latency transmission (approx. 80ms round-trip-time) and fast processing (approx, 600ms per formation step) of extensive (70-120 Mbits/s) video and telemetry data, and swarm control for swarms of up to ten drones.