Swarm LIO2: Decentralized, Efficient LiDAR-inertial Odometry for UAV Swarms скачать в хорошем качестве

Swarm LIO2: Decentralized, Efficient LiDAR-inertial Odometry for UAV Swarms

[Preprint: https://arxiv.org/abs/2409.17798] This paper proposes Swarm-LIO2: a fully decentralized, plug-and-play, computationally efficient, and bandwidth-efficient LiDAR-inertial odometry for aerial swarm systems. Swarm-LIO2 can perform robust, real-time swarm state estimation (both ego-state and mutual state) and has broad adaptability to large-scale aerial swarm systems and complicated scenarios, including GPS-denied scenes, degenerated scenes for cameras (lack of illumination) or LiDARs (lack of point constraints). Diverse applications demonstrate the potential of Swarm-LIO2 to serve as reliable infrastructure for various aerial swarm missions. In addition, we open-source all the system designs on GitHub to benefit society: https://github.com/hku-mars/Swarm-LIO2