×

Data sharing among conditionally independent parallel filters

  • US 9,104,752 B2
  • Filed: 11/16/2012
  • Issued: 08/11/2015
  • Est. Priority Date: 11/16/2012
  • Status: Expired due to Fees
First Claim
Patent Images

1. A method for data sharing between a plurality of filters, the method comprising:

  • initializing at least a first filter and a second filter that operate in parallel with each other, the first filter having a first state vector (x1), the second filter having a second state vector (x2), the first filter estimating a distribution of the first state vector that contains a first subset (xa) and a third subset (xc), the second filter estimating a distribution of the second state vector that contains a second subset (xb) and the third subset (xc), such that;


    x1=[xcxa] and x2=[xcxb];

    wherein;

    the first subset includes one or more unique states of the first filter, the second subset includes one or more unique states of the second filter, and the third subset includes one or more common states between the first and second filters;

    the first subset, the second subset, and the third subset are selected such that the first subset and the second subset are conditionally independent given the third subset; and

    the third subset is a conditioning node for the first filter and the second filter;

    processing data measurements in the first filter;

    sharing conditioning node estimates with the second filter when it is time for conditionally independent data sharing;

    merging the shared conditioning node estimates in each of the filters; and

    performing a conditional update in each of the filters.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×