[Back]


Diploma and Master Theses (authored and supervised):

S. Brugger:
"Integrating probabilistic information of dynamic environment into maps for enhanced action planning";
Supervisor: R. Grosu, O. Höftberger; Institut für Technische Informatik, 2014; final examination: 2014-03-26.



English abstract:
Action planning of robots and autonomous vehicles is typically based on maps of their environment.
These maps often only contain information about the static environment and ignore
dynamic entities. Information about dynamic entities, like moving objects, in the environment
can help to improve action planning in robotics.
The basics of autonomous navigation such as localisation, mapping and tracking are covered.
State of the art algorithms for mapping such as particle filtering and Simultaneous Localization
and Mapping (SLAM) are evaluated. An approach to gather probabilistic and dynamic information
about the dynamic environment is introduced within this thesis. All entities within a map
are probabilistic, containing a value about the probability of their existence and a change rate.
Dynamic behaviour at certain locations will cause dynamic areas to be created. In addition these
new information need to be saved somehow within the map. A technique to save this information,
as well as to reuse existing maps and extend them, is presented. This thesis is all about
gathering information, evaluating this information regarding its dynamic aspect, generating dynamic
areas and store probabilistic and dynamic information in maps.
A software module, which is designed to gather and process change rates about the dynamic
environment, was developed. This module in cooperation with other modules and a robotic software
framework is able to perform dynamic mapping while autonomously driving to a certain
destination. A small robot, equipped with a laser scanner which provides information about
the environment, was used to experimentally examine the behaviour of the dynamic mapping
software module. These experiments are evaluated and demonstrate the approach of generating
maps with information about the dynamic environment.


Electronic version of the publication:
http://publik.tuwien.ac.at/files/PubDat_233063.pdf


Created from the Publication Database of the Vienna University of Technology.