Omni-swarm: An Aerial Swarm System with Decentralized Omni-directional Visual-Inertial-UWB State Estimation

The collaboration of unmanned aerial vehicles (UAVs), also known as aerial swarm, has become a popular research topic for its practicality and flexibility in plenty of scenarios. However, one of the most fundamental components for autonomous aerial swarm systems in GPS-denied areas, the robust decentralized relative state estimation, remains to be an extremely challenging research topic. In order to address this research niche, the Omni-swarm, an aerial swarm system with decentralized Omni-directional visual-inertial-UWB state estimation, which features robustness, accuracy, and global consistency, is proposed in this paper. We introduce a map-based localization method using deep learning tools to perform relative localization and re-localization within the aerial swarm while achieving the fast initialization and maintaining the global consistency of state estimation. Furthermore, to overcome the sensors' visibility issues with the limited field of view (FoV), which severely affect the performance of the state estimation, Omni-directional sensors, including fisheye cameras and ultra-wideband (UWB) sensors, are adopted. The state estimation module, together with the planning and the control modules, is integrated on the aerial system with Omni-directional sensors to attain the Omni-swarm, and extensive experiments are performed to verify the validity and examine the performance of the proposed framework. According to the experiment result, the proposed framework can achieve centimeter-level relative state estimation accuracy while ensuring global consistency.