Position-Constrained Stochastic Inference for Cooperative Indoor Localization

We address the problem of distributed cooperative localization in wireless networks, i.e., nodes without prior position knowledge (agents) wish to determine their own positions. In non-cooperative approaches, positioning is only based on information from reference nodes with known positions (anchors). However, in cooperative positioning, information from other agents is considered as well. Cooperative positioning requires encoding of the uncertainties of agents' positions. To cope with that demand, we consider stochastic inference for localization, which inherently takes the position uncertainties of agents into consideration. Generally, stochastic inference comes at the expense of high costs in terms of computation and information exchange. To relax the requirements of inference algorithms, we propose the framework of position-constrained stochastic inference, in which we first confine the positions of nodes to constrained regions. These regions assist inference algorithms to concentrate on the important areas of the sample space rather than the entire sample space. In contrast to many state-of-the-art approaches, our approach does not require prior knowledge on the positions of agents. We show through simulations that increased localization accuracy, reduced computational complexity, and quicker convergence can be achieved when compared to state-of-the-art non-constrained inference algorithms.