A distributed deterministic approximation algorithm for data association

The data association problem appears in many applications and is considered as the most challenging problem in intelligent systems. In this paper, we consider the Bayesian formulation of data association problems and present a deterministic polynomial-time approximation algorithm with guaranteed error bounds using correlation decay from statistical physics. We then show that the proposed algorithm naturally partitions a complex problem into a set of local problems and develop a distributed version of the algorithm. The performance of the proposed algorithm is evaluated in simulation.