this is for holding javascript data
Volker Strobel edited chapter_Conclusion_label_chap_conclusion__.tex
over 7 years ago
Commit id: d701dbf249cbf44734345f9364ec4cc2d1b11005
deletions | additions
diff --git a/chapter_Conclusion_label_chap_conclusion__.tex b/chapter_Conclusion_label_chap_conclusion__.tex
index 8d183b8..4a5191d 100644
--- a/chapter_Conclusion_label_chap_conclusion__.tex
+++ b/chapter_Conclusion_label_chap_conclusion__.tex
...
\chapter{Conclusion}
\label{chap:conclusion}
This thesis presented a novel approach for
fast and accurate lightweight indoor
localization of MAVs. We pursued an onboard design without the need of
an additional ground station to foster flexibility and autonomy. The
conducted on-ground and in-flight experiments underline the real-world
applicability of the system. Promising results were obtained for
waypoint navigation, accurate landing, position estimates and
stable hovering accurate landing in the indoor environment.
The
used approach is based on three
pillars.\\ pillars that we identified for indoor
localization for MAVs. The first pillar shifts computational effort
from the flight phase to an offline preprocessing step. This
allows for using provides
the advantages of sophisticated algorithms, without affecting
performance during flight. The second pillar states that during flight
the MAV lightweight
algorithms should run with low-performing processors. These
algorithms should be
able to used that can trade off speed with accuracy. This
allows
to their use
them on a wide range of models, from pico-drones to MAVs
with a wing-span of over one meter. Examples of these adaptable
algorithms are the
particle filter texton-based approach and the
texton-based approach. particle filter. The
third pillar is
the a known---and possibly---modifiable environment. This
knowledge and
flexibilty flexibility allows
to predict for predicting and improving the
quality of the
used approach.
In %In contrast to
SLAM \textsc{slam} frameworks, in
which %which the task is to simultaneous mapping and localization, the
proposed %presented approach is intended for various repetitive indoor
activities. %activities.