Set Joint Probabilistic Data Association for Relative Space Object Tracking

Abstract

Joint probabilistic data association (JPDA) is a suboptimal filtering method that has been studied and utilized for over thirty years. It addresses the problem of tracking multiple targets in a cluttered environment without guaranteed target detection, a nearly unavoidable problem in target tracking. The JPDA filter has been shown to be a suitable filter selection in a variety of applications; however, an approximation in the algorithm makes the filter vulnerable to issues such as track coalescence, which can potentially result in filter divergence. A variant of this method known as set JPDA (SJPDA) has recently been proposed that leverages finite set statistics to improve this approximation, thus diminishing the vulnerabilities present. This paper restates the derivation of the SJPDA filter, beginning with its ancestral probabilistic data association (PDA) formulation and its extension to the multi-target domain via JPDA. The JPDA/SJPDA formulations are applied to a simulation example to illustrate the differences in performance between the two.

Department(s)

Mechanical and Aerospace Engineering

International Standard Book Number (ISBN)

978-162410445-9

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2024 American Institute of Aeronautics and Astronautics, All rights reserved.

Publication Date

01 Jan 2016

This document is currently not available here.

Share

 
COinS