Sigma Point Belief Propagation
This work addresses decentralized inference challenges in sensor networks by providing a more efficient method, though it is incremental as it extends existing sigma point filter techniques.
The authors tackled the problem of nonsequential Bayesian inference in loopy factor graphs by proposing sigma point belief propagation (SPBP) as a low-complexity alternative to belief propagation, demonstrating that SPBP outperforms nonparametric BP in a decentralized sensor localization task with significantly reduced computations and communications.
The sigma point (SP) filter, also known as unscented Kalman filter, is an attractive alternative to the extended Kalman filter and the particle filter. Here, we extend the SP filter to nonsequential Bayesian inference corresponding to loopy factor graphs. We propose sigma point belief propagation (SPBP) as a low-complexity approximation of the belief propagation (BP) message passing scheme. SPBP achieves approximate marginalizations of posterior distributions corresponding to (generally) loopy factor graphs. It is well suited for decentralized inference because of its low communication requirements. For a decentralized, dynamic sensor localization problem, we demonstrate that SPBP can outperform nonparametric (particle-based) BP while requiring significantly less computations and communications.