Robotics

Das Ziel dieser Arbeit ist es, die nichtlinearen Methode der kleinsten Quadrate als Optimierungsverfahren für die Lokalisierung mithilfe von Distanzsensoren innerhalb von Mesh Karten zu testen. Die nichtlineare Methode der kleinsten Quadrate bietet die Möglichkeit, Datenausreißer mithilfe von Verlustfunktionen zu filtern. Dadurch stellt sich die Frage, ob diese Methode besser für reale Daten geeignet ist als andere. Um dies zu testen wurde die nichtlineare Methode der kleinsten Quadrate innerhalb von MICP-L (Mesh ICP Lokalisierung) umgesetzt, um sie mit dem dort verwendeten Kabsch-Umeyama-Algorithmus zu vergleichen.

Robot navigation is a contemporary field of research in which the optimal path a robot could take has to be computed with decreased computational costs. The robot should then move as enduringly and efficiently as possible by taking the area’s different costs into consideration. The present bachelor thesis analyzes the performance of Move Base Flex and the ROS Navigation Stack into which the Grid Map library was integrated. Grid Map is a library for 2.

Mobile robots shall help and accompany us in the future in our everyday life. To do so, a robot has to navigate to specific locations, not always defined by its position but also by what one can find there. In this thesis, a possible approach to include semantic maps into navigational planning is Osnabrück was implemented. Normally, semantic maps are build using an ontology as a reasoning base. In this thesis, a database is connected with a topological graph to include semantic information in a map.