This paper considers fusion of dimension-reduced estimates in a decentralized sensor network. The benefits of a decentralized sensor network include modularity, robustness and flexibility. Moreover, since preprocessed data is exchanged between the agents it allows for reduced communication. Nevertheless, in certain applications the communication load is required to be reduced even further. One way to decrease the communication load is to exchange dimension-reduced estimates instead of full estimates. Previous work on this topic assumes global availability of covariance matrices, an assumption which is not realistic in decentralized applications. Hence, in this paper we consider the problem of deriving dimension-reduced estimates using only local information. The proposed solution is based on an estimate of the information common to the network. This common information estimate is computed locally at each agent by fusion of all information that is either received or transmitted by that agent. It is shown how the common information estimate is utilized for fusion of dimension-reduced estimates using two well-known fusion methods: the Kalman fuser which is optimal under the assumption of uncorrelated estimates, and covariance intersection. One main theoretical result is that the common information estimate allows for a decorrelation procedure such that uncorrelated estimates can be maintained. This property is crucial to be able to use the Kalman fuser without double counting of information. A numerical comparison suggests that the performance degradation of using the common information estimate, compared to having local access to the actual covariance matrices computed by other agents, is relatively small.

This paper deals with distributed Bayesian stateestimation of generally nonlinear stochastic dynamic systems. In particular, distributed point-mass filter algorithm is developed. It is comprised of a basic part that is accurate but data intense and optional step employing advanced copula theory. The optional step significantly reduces data transfer for the price of a small accuracy decrease. In the end, the developed algorithm is numerically compared to the usually employed distributed extended Kalman filter.

Network-centric multitarget tracking under communication constraints is considered, where dimension-reduced track estimates are exchanged. Previous work on target tracking in this subfield has focused on fusion aspects only and derived optimal ways of reducing dimensionality based on fusion performance. In this work we propose a novel problem formalization where estimates are reduced based on association performance. The problem is analyzed theoretically and problem properties are derived. The theoretical analysis leads to an optimization strategy that can be used to partly preserve association quality when reducing the dimensionality of communicated estimates. The applicability of the suggested optimization strategy is demonstrated numerically in a multitarget scenario.

Underwater surveillance using passive sonar and track-before-detect technology requires accurate models of the tracked signal and the background noise. However, in an underwater environment, the signal channel is time-varying and prior knowledge about the spatial distribution of the background noise is unavailable. In this paper, an autoregressive model that captures a time-varying signal level caused by multi-path propagation is presented. In addition, a multi-source model is proposed to describe spatially distributed background noise. The models are used in a Bernoulli filter track-before-detect framework and evaluated using both simulated and sea trial data. The simulations demonstrate clear improvements in terms of target loss and improved ability to discern the target from the noisy background. An evaluation of the track-before-detect algorithm on the sea trial data indicates a performance gain when incorporating the proposed models in underwater surveillance and tracking problems. 

Mean square error optimal estimation requires the full correlation structure to be available. Unfortunately, it is not always possible to maintain full knowledge about the correlations. One example is decentralized data fusion where the cross-correlations between estimates are unknown, partly due to information sharing. To avoid underestimating the covariance of an estimate in such situations, conservative estimation is one option. In this paper the conservative linear unbiased estimator is formalized including optimality criteria. Fundamental bounds of the optimal conservative linear unbiased estimator are derived. A main contribution is a general approach for computing the proposed estimator based on robust optimization. Furthermore, it is shown that several existing estimation algorithms are special cases of the optimal conservative linear unbiased estimator. An evaluation verifies the theoretical considerations and shows that the optimization based approach performs better than existing conservative estimation methods in certain cases.

Data fusion in a communication constrained sensor network is considered. The problem is to reduce the dimensionality of the joint state estimate without significantly decreasing the estimation performance. A method based on scalar subspace projections is derived for this purpose. We consider the cases where the estimates to be fused are: (i) uncorrelated, and (ii) correlated. It is shown how the subspaces can be derived using eigenvalue optimization. In the uncorrelated case guarantees on mean square error optimality are provided. In the correlated case an iterative algorithm based on alternating minimization is proposed. The methods are analyzed using parametrized examples. A simulation evaluation shows that the proposed method performs well both for uncorrelated and correlated estimates.

We consider a decentralized sensor network of multiple nodes with limited communication capability where the cross-correlations between local estimates are unknown. To reduce the bandwidth the individual nodes determine which subset of local information is the most valuable from a global perspective. Three information selection methods (ISM) are derived. The proposed ISM require no other information than the communicated estimates. The simulation evaluation shows that by using the proposed ISM it is possible to determine which subset of local information is globally most valuable such that both reduced bandwidth and high performance are achieved.

Sensor networks consist of sensors (e.g., radar and cameras) and processing units (e.g., estimators), where in the former information extraction occurs and in the latter estimates are formed. In decentralized estimation information extracted by sensors has been pre-processed at an intermediate processing unit prior to arriving at an estimator. Pre-processing of information allows for the complexity of large systems and systems-of-systems to be significantly reduced, and also makes the sensor network robust and flexible. One of the main disadvantages of pre-processing information is that information becomes correlated. These correlations, if not handled carefully, potentially lead to underestimated uncertainties about the calculated estimates. 

In conservative estimation the unknown correlations are handled by ensuring that the uncertainty about an estimate is not underestimated. If this is ensured the estimate is said to be conservative. Neglecting correlations means information is double counted which in worst case implies diverging estimates with fatal consequences. While ensuring conservative estimates is the main goal, it is desirable for a conservative estimator, as for any estimator, to provide an error covariance which is as small as possible. Application areas where conservative estimation is relevant are setups where multiple agents cooperate to accomplish a common objective, e.g., target tracking, surveillance and air policing. 

The first part of this thesis deals with theoretical matters where the conservative linear unbiased estimation problem is formalized. This part proposes an extension of classical linear estimation theory to the conservative estimation problem. The conservative linear unbiased estimator (CLUE) is suggested as a robust and practical alternative for estimation problems where the correlations are unknown. Optimality criteria for the CLUE are provided and further investigated. It is shown that finding an optimal CLUE is more complicated than finding an optimal linear unbiased estimator in the classical version of the problem. To simplify the problem, a CLUE that is optimal under certain restrictions will also be investigated. The latter is named restricted best CLUE. An important result is a theorem that gives a closed form solution to a restricted best CLUE. Furthermore, several conservative estimation methods are described followed by an analysis of their properties. The methods are shown to be conservative and optimal under different assumptions about the underlying correlations. 

The second part of the thesis focuses on practical aspects of the conservative approach to decentralized estimation in configurations where the communication channel is constrained. The diagonal covariance approximation is proposed as a data reduction technique that complies with the communication constraints and if handled correctly can be shown to preserve conservative estimates. Several information selection methods are derived that can reduce the amount of data being transmitted in the communication channel. Using the information selection methods it is possible to decide what information other actors of the sensor network find useful. 

This paper addresses the problem of retrieving consistentestimates in a distributed network where the communication between the nodes is constrained such that only the diagonal elements of the covariance matrix are allowed to be exchanged. Several methods are developed for preserving and/or recovering consistency under the constraints imposed by the communication protocol. The proposed methods are used in conjunction with the covariance intersection method and the estimation performance is evaluated based on information usage and consistency. The results show that among the proposed methods, consistency can be preserved equally well at the transmitting node as at the receiving node.