FHWS/IPIN2018
Archived
4
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

more experiments

Browse Source
This commit is contained in:
toni
2018-07-01 17:06:05 +02:00
parent d30d8cbe73
commit 8881557b99
1 changed files with 29 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
tex/chapters/experiments.tex
View File

@@ -84,7 +84,7 @@ An estimation on the wrong floor has a great impact on the location awareness of
Therefore, errors in $z$-direction are penalized by tripling the $z$-value.
%computation und monte carlo runs
For each walk we deployed 100 runs using \SI{5000}{particles}.
For each walk we deployed 100 runs using \SI{5000}{particles} and set $N_{\text{eff}} = 0.85$ for resampling.
Instead of an initial position and heading, all walks start with a uniform distribution (random position and heading) as prior.
The overall localisation results can be see in table \ref{table:overall}.
Here, we differ between the respective anti-impoverishment techniques presented in chapter \ref{sec:impo}.
@@ -140,16 +140,29 @@ Walking down the stairs at \SI{80}{\second} does also recover the localization s
\label{fig:errorOverTimeWalk0}
\end{figure}
A similar behaviour as described above can be seen in walk 3.
Without a method to recover from impoverishment, the system completely lost track in \SI{xx}{\percent} of the runs and produces high errors.
A similar behaviour as the above can be seen in walk 3.
Without a method to recover from impoverishment, the system lost track in \SI{100}{\percent} of the runs due to a not detected floor change in the last third of the walk.
By using the simple method, the overall error can be reduced and the impoverishment resolved. Nevertheless, unpredictable jumps of the estimation are causing the system to be highly uncertain in some situations, even if those jumps do not last to long.
Only the use of the $D_\text{KL}$ method is able to produce reasonable results.
As described in chapter \ref{}, we use a Wi-Fi model optimized for each floor instead of a single global one.
A good example why we do this, can be seen in fig. \ref{}, considering walk 3.
Here, the system using the global Wi-Fi model makes a big jump into the right-hand corridor and requires \SI{5}{\second} to recover.
This happens through a combination of environmental occurrences, like the many different materials and thus attenuation factors, as well as the limitation of the here used Wi-Fi model, only considering ceilings and ignoring walls.
Following, \docAPshort{}'s on the same floor level, which are highly attenuated by \SI{2}{\meter} thick stone walls, are neglected and \docAPshort{}'s from the floor above, which are only separated by a thin wooden ceiling, have a greater influence within the state evaluation process.
Of course, we optimize the attenuation per floor, but at the end this is just an average value summing up the \docAPshort{}'s surrounding materials.
Therefore, the calculated signal strength predictions do not fit the measurements received from the above in a optimal way.
In contrast, the model optimized for each floor only considers the respective \docAPshort{}'s on that floor, allowing to calculate better fitting parameters.
A major disadvantage of the method is the reduced number of visible \docAPshort{}'s and thus measurements within an area.
This could lead to an underrepresentation of \docAPshort{}'s for triangulation.
\todo{fuer eins brauchen wir aber noch estimated path}
\todo{neff = 0.85; boxkde 0.2 point2(1,1); wifi useregionalopt=true}
\todo{boxkde 0.2 point2(1,1);}
\todo{
BILD: Von einem Pfad der steckenbleibt und den beiden anderen verfahren mit fehler über die zeit.
@@ -172,6 +185,11 @@ BILD: Estimation Fehler
\subsection{Estimation Methods}
\label{sec:exp:est}
As discussed before, the single estimation methods only vary by a few centimetres in the overall localization error.
That means, they differ mainly in the representation of the estimated locations.
More easily spoken, in which way the estimated path is drawn and thus presented to the user.
Regarding the underlying particle set, different shapes of probability distributions need to be considered, especially those with multimodalities.
\begin{figure}
\centering
\input{gfx/walk.tex}
@@ -179,7 +197,7 @@ BILD: Estimation Fehler
\label{fig:realWorldMulti}
\end{figure}
As discussed in section \ref{sec:estimation}, the main advantage of a KDE-based estimation is that it provides the "correct" mode of a density, even under a multimodal setting.
The main advantage of a KDE-based estimation is that it provides the "correct" mode of a density, even under a multimodal setting (cf. section \ref{sec:estimation}).
A situation in which the system highly benefits from this is illustrated in fig. \ref{fig:realWorldMulti}.
Here, a set of particles splits apart, due to uncertain measurements and multiple possible walking directions.
Indicated by the black dotted line, the resulting bimodal posterior reaches its maximum distance between the modes at \SI{13.4}{\second}.
@@ -205,10 +223,10 @@ Only with new measurements coming from the hallway or other parts of the buildin
\label{fig:realWorldTime}
\end{figure}
As already mentioned in our previous work \cite{}.
A KDE-based approach for estimation is able to resolve multimodalities.
It does not always provide the lowest error, since it depends more on an accurate sensor model then a weighted-average approach, but is very suitable as a good indicator about the real performance of a sensor fusion system.
At the end, in the here shown examples we only searched for a global maxima, even though this approach approach opens a wide range of other possibilities for finding a best estimate.
This lead to the conclusion, that a weighted average approach provides a more smooth representation of the estimated locations and thus a higher robustness.
In contrast, a KDE-based approach for estimation is able to resolve multimodalities.
It does not always provide the lowest error, since it depends more on an accurate sensor model then a weighted average approach, but is very suitable as a good indicator about the real performance of a sensor fusion system.
At the end, in the here shown examples we only searched for a global maxima, even though this approach opens a wide range of other possibilities for finding a best estimate.
%wie in bulli paper.