Distributed adaptive estimation with probabilistic data association

✍ Scribed by K.C. Chang; Y. Bar-Shalom

• Book ID: 102989676
• Publisher: Elsevier Science
• Year: 1989
• Tongue: English
• Weight: 668 KB
• Volume: 25
• Category: Article
• ISSN: 0005-1098
• DOI: 10.1016/0005-1098(89)90004-6

✦ Synopsis

A fusion algorithm for target state estimation under cluttered environment with uncertain measurement origins and uncertain system models in a distributed manner can be applied for tracking a maneuvering target in a cluttered and low detection environment Key Weeds--Distributed estimation; multiple model; target tracking; probabilistic data association;

Bayesian methods; distributed sensor networks.

Alwlrat/--The probabilistic data association filter (PDAF) estimates the state of a target in a cluttered environment. This suboptimal Bayesian approach assumes that the exact target and measurement models are known. However, in most practical applications, there are difficulties in obtaining an exact mathematical model of the physical process. In this paper, the problem of estimating target states with uncertain measurement origins and uncertain system models in a distributed manner is considered. First, a scheme is described for local processing, then the fusion algorithm which combines the local processed results into a global one is derived. The algorithm can be appfied for tracking a maneuvering target in a cluttered and low detection environment with a distributed sensor network.