FHWS/Fusion2016
Archived
3
0
Fork 0
Code Issues 1 Pull Requests Releases Wiki Activity

added conclusion

Browse Source
This commit is contained in:
Toni
2016-02-14 17:58:13 +01:00
parent 6e5de8e5ec
commit 03f0606d0d
2 changed files with 16 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
tex/chapters/conclusion.tex
View File

@@ -1,10 +1,19 @@
\section{Conclusion} \section{Conclusion}
We presented a novel approach for integrating prior navigation knowledge by using realistic human walking paths.
Based on a weighted graph, two different models for walking in a more targeted and natural manner were introduced.
It could be shown that adding this additional knowledge causes an overall improvement of the localisation results, while maintaining flexible for uncertain behaviour.
Furthermore, our approach is able to provide accurate and robust position estimations, even when (normally) necessary calibration processes are ignored.
However, providing this calibration knowledge can further improve the results. In order to reduce the effort of locating the \docAP{}s and calibrating them, a numerical optimization based on predefined walks could be considered. Additionally, the graph allows for storing pre-computed signal strengths and thus enables more complex prediction models incorporating floor and wall information into the signal strength estimation.
As seen, multimodal distributions lead to faulty position estimations and therefore a rising error. One possible method to resolve this issue would be a more suiting location estimation method. Another promising way is smoothing. By deploying a fixed-lag smoother the system would still be perceived as real-time application, but is able to estimate the (delayed) estimation using future measurements up to the latest timestep.
\commentByFrank{balance zwischen den einzelnen wahrscheinlichkeiten ist oft ein schmaler grad. wieviel turn erlauben, wieviel auf den pfad zwingen. das verbesern}
\commentByFrank{position der APs wissen ist viel arbeit. vereinfachen durch test-walks auf vorgegebenen pfaden -> numerisch optimieren wo APs sind} %\commentByFrank{balance zwischen den einzelnen wahrscheinlichkeiten ist oft ein schmaler grad. wieviel turn erlauben, wieviel auf den pfad zwingen. das verbesern}
\commentByToni{quadtress. stellen die groesse der zellen variable ein. je nach bedarf.} %\commentByFrank{position der APs wissen ist viel arbeit. vereinfachen durch test-walks auf vorgegebenen pfaden -> numerisch optimieren wo APs sind}
\commentByFrank{multimodalitaeten (z.B. treppenhaeuser). fixen durch andere estimations} %\commentByToni{quadtress. stellen die groesse der zellen variable ein. je nach bedarf.}
\commentByToni{oder durch smoothing} %\commentByFrank{multimodalitaeten (z.B. treppenhaeuser). fixen durch andere estimations}
\commentByToni{Aufzuege hinzufuegen. Vertical Acceleration benutzen.} %\commentByToni{oder durch smoothing}
%\commentByToni{Aufzuege hinzufuegen. Vertical Acceleration benutzen.}

2
tex/chapters/system.tex
View File

@@ -18,7 +18,7 @@
The hidden state $\mStateVec$ is given by The hidden state $\mStateVec$ is given by
\begin{equation} \begin{equation}
\mStateVec = (x, y, z, \mObsHeading, \mStatePressure),\enskip \mStateVec = (x, y, z, \mObsHeading, \mStatePressure),\enskip
x, y, z, \mObsHeading \mStatePressure \in \R \enspace, x, y, z, \mObsHeading, \mStatePressure \in \R \enspace,
\end{equation} \end{equation}
% %
where $x, y, z$ represent the position in 3D space, $\mObsHeading$ the user's heading and $\mStatePressure$ the where $x, y, z$ represent the position in 3D space, $\mObsHeading$ the user's heading and $\mStatePressure$ the