Distributed localization using Levenberg-Marquardt algorithm

Abstract In this paper, we propose a distributed algorithm for sensor network localization based on maximum likelihood formulation. It relies the Levenberg-Marquardt where computations are among different computational agents using message passing, or equivalently dynamic programming. The resulting provides good accuracy, and it converges to same solution as its centralized counterpart. Moreover, requires fewer iterations communications between compared first-order methods. performance of is demonstrated with extensive simulations in Julia which shown that our method outperforms methods approximate formulations.