张宁 On Data Sharing Strategy for Decentralized Collaborative Visual-Inertial Simultaneous Localization and Mapping
分散式协同视觉惯性同时定位与建图的数据共享策略研究
链接：https://pan.baidu.com/s/1DGEZtJ7H7eITfyyns7h06A
提取码：zvcu
Rodolphe Dubois, Alexandre Eudes, Vincent Fr´emont
Abstract—This article introduces and evaluates two decentralized data sharing algorithms for multi-robot visualinertial simultaneous localization and mapping (VI-SLAM): Factor Sparsification for Visual-Inertial Packets (FS-VIP) and Min-K-Cover Selection for Visual-Inertial Packets (MKCS-VIP). Both methods make robots regularly build and exchange data packets which describe the successive portions of their map, but rely on distinct paradigms. While FS-VIP builds on consistent marginalization and sparsification techniques, MKCSVIP selects raw visual and inertial information which can best help to perform a faithful and consistent re-estimation while reducing the communication cost. Performances in terms of accuracy and communication loads are evaluated on multirobot scenarios built on both available (EUROC) and custom datasets (SOTTEVILLE).
本文介绍并评估了用于多机器人视觉惯性同时定位和建图（VI-SLAM）的两种分散式数据共享算法：视觉惯性数据包的因子稀疏（FS-VIP）和视觉惯性数据包的最小K覆盖选择（ MKCS-VIP）。两种方法都使机器人可以定期构建和交换描述其地图连续部分的数据包，但要依靠不同的范例。FS-VIP建立在一致的边缘化和分散技术之上，而MKCSVIP选择原始的视觉和惯性信息，这些信息可以最有效地执行忠实一致的重新估计，同时降低通信成本。在基于可用（EUROC）和自定义数据集（SOTTEVILLE）的多机器人方案中评估准确性和通信负载方面的性能。