Hybrid maximum a posteriori estimation under communication constraints

We consider the problem of joint-state estimation for mobile wireless sensor networks (WSN) using noisy analog observations from spatially-distributed sensors. Due to communication bandwidth constraints, sensors can transmit only quantized observations. As opposed to existing estimators that process either only quantized or only analog observations, we develop a Maximum A Posteriori-based hybrid estimation framework that enables each sensor to utilize its own local analog observations as well as quantized observations received from other sensors to improve estimation accuracy.