Abstract
SUMMARYThis paper presents a generalization of the Compressed Extended Kalman Filter (CEKF) by introducing the definition of the compressed operation for Bayesian estimation processes and the definition of the Generalized Compressed Kalman Filter (GCKF). The GCKF extends the original definition of the CEKF, formerly introduced for treating a family of estimation problems, such as the Simultaneous Localization and Mapping (SLAM). The new proposed approach, the GCKF, is capable of treating problems that are more general than those of the original CEKF, such as estimation processes that involve certain stochastic Partial Differential Equation (SPDE) models. In addition to solving the SLAM and multi-agent SLAM problem in an efficient way, the GCKF can be applied to more general cases. As a proof of the capabilities of the new method for solving practical estimation problems, a multi-agent SLAM process is presented in the experimental section of this paper.
Publisher
Cambridge University Press (CUP)
Subject
Computer Science Applications,General Mathematics,Software,Control and Systems Engineering
Reference25 articles.
1. Simultaneous localization and mapping (SLAM): part II
2. S. Williams , Efficient Solutions to Autonomous Mapping and Navigation Problems Ph.D. Thesis (Sydney: The University of Sydney, 2001).
3. J. Guivant , Efficient Simultaneous Localization and Mapping in Large Environments Ph.D. Thesis (The University of Sydney, Sydney, Australia, 2002).
4. The Ensemble Kalman Filter: theoretical formulation and practical implementation
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献