Solutions to assignments of Robot Mapping Course WS 2013/14 by Dr.Cyrill Stachniss at University of Freiburg Framework Credits: Dr.Cyrill Stachniss
This repository contains the solutions to the assignments posted in the course website http://ais.informatik.uni-freiburg.de/teaching/ws13/mapping/index_en.php
Simultaneous Localization And Mapping is considered a fundamental problem for any autonomously navigating system. Such a system - mostly, a robot - will need to perceive the environment around it (mapping) and at the same time, answer the question "Where am I in my map?" (localization). Hence, SLAM has become an integral part of robotics.
The Mathematics behind the heart of SLAM algorithms include Probability theory and Bayesian and Markov methods. Depending on the specifics of the SLAM algorithm, knowledge of several other techniques may also be required - for example, the GraphSLAM (or LeastSquares SLAM) requires knowledge of graph theory.
Robot Mapping by Dr.Cyrill Stachniss introduces several SLAM Algorithms in sufficient detail so as to facilitate implementation. The primary textbook for the course is "Probabilistic Robotics" by Thrun et.al.
Octave on Ubuntu was used to code the SLAM algorithms. The code should be compatible with MATLAB also. However, it has not been tested.
The video / plot results are in the 'plots' folder in each corresponding algorithm folder.
[1] Dr.Cyrill Stachniss, Robot Mapping course, University of Freiburg. https://www.youtube.com/watch?v=3Yl2aq28LFQ&index=15&list=PLgnQpQtFTOGQrZ4O5QzbIHgl3b1JHimN_
[2] Thrun et.al., Probabilistic Robotics
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent