A Comparison of Probabilistic Representations for Decentralised Data Fusion
Lee‐Ling Sharon Ong, Matthew Ridley, Ben Upcroft, S. Srinivas Kumar, T.E.R. Bailey, Salah Sukkarieh, Hugh F Durrant-Whyte · 2005
This paper compares and constrasts three different probabilistic models - Particle representations, Parzen density estimates, and Gaussian mixture models - for non-Gaussian, non-linear feature tracking, when applied to multiple autonomous vehicles using the Decentralised Data Fusion (DDF) paradigm. These probabilistic models were chosen as they are all capable of approximating the probability distributions of an ideal Bayesian filter and have different properties with regard to computational efficiency and quality of the approximation. In order to show that each model satisfy the DDF requirements of modularity, scalability and robustness, the performance of each representation is taken from a simulation for multi-sensor bearing-only tracking. Performance is evaluated in three areas: (a) mathematical accuracy and optimality of fusion for correlated information between nodes, (b) computational efficiency and accuracy of various operations in the DDF framework and (c) bandwidth requirements for communicating the representations over a wireless network.