The exploitation of dependencies between state estimates from distributed trackers plays a vital role in so-called track-to-track fusion and has been extensively studied for state estimates with the same state space. In contrast, dependencies are often neglected when considering heterogeneous state estimates referring to different state spaces, since the necessary transformations make the analytic calculation complex or infeasible. This paper aims to develop an overarching framework for the reconstruction of cross-covariances between state estimates obtained in heterogeneous state spaces. The proposed method uses a set of deterministic samples to calculate dependent information. Thus, it allows for a distributed track-keeping of correlations that also encodes the transformation into the local subsystems. To highlight the algorithm, we use a linear problem with heterogeneous trackers only and discuss the correlation problem in detail. The results show superior performance compared to neglecting the correlations.
展开▼
