daviddoji/Kalman-and-Bayesian-Filters-in-Python
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Added note about iterative LS schemes.

Browse Source 
ILS is used for overdetermined systems. I added a note that this is
a typical technique that I will be covering soon.
This commit is contained in:
Roger Labbe 2015-02-26 18:38:31 -08:00
parent 37743bf604
commit e89b950c2d
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
10_Unscented_Kalman_Filter.ipynb
View File

@ -1833,7 +1833,10 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"This is untenable behavior for a real world filter. `FilterPy`'s UKF code allows you to provide it a function to compute the residuals in cases of nonlinear behavior like this, but this requires more knowledge about `FilterPy`'s implementation than we yet process."
"This is untenable behavior for a real world filter. `FilterPy`'s UKF code allows you to provide it a function to compute the residuals in cases of nonlinear behavior like this, but this requires more knowledge about `FilterPy`'s implementation than we yet process.\n",
"\n",
"\n",
"**author's note: this is a fairly naive approach to overdetermined systems. For example, suppose you had 6 sensors, not the minimum of 2 which is needed for 2D positions. While you can use the approach above, systems like GPS use something like an iterative Least Squares approach to estimate the 3D position for each epoch based on the pseudorange it receives from each satellite. This estimate is then passed into the GPS as the measurement. I will be writing a section on this very soon. In the meantime if you google for 'gnss iterative least squares' tons of relevant links are returned.**"
]
},
{