Introduction to Mobile Robotics - SS 2012
Introduction to Mobile Robotics (engl.) - Autonomous Mobile Systems
This course will introduce basic concepts and techniques used within the field of mobile robotics. We analyze the fundamental challenges for autonomous intelligent systems and present the state of the art solutions. Among other topics, we will discuss:- Sensors,
- Kinematics,
- Path planning,
- Vehicle localization,
- Map building,
- SLAM,
- Exploration of unknown terrain
- Lecturers: Prof. Dr. Wolfram Burgard, PD Dr. Cyrill Stachniss, Juniorprof. Dr. Maren Bennewitz, Juniorprof. Dr. Kai Arras
- Co-organizers: Benjamin Suger, Jonas Rist
- Lectures: Wednesday 14-16, Friday 12-13, Room: Geb. 101 - SR 01-009/13
- Exercises: Friday 13-14, Room: Geb. 101 - SR 01-009/13
Exercises
Solving and submitting the exercise sheets is recommended but not mandatory to be admitted to the final exam. There are no bonus points.
The exercises should be solved in groups of two students. In general, assignments will be published on Wednesday and have to be submitted the following Wednesday before class. Submit programming exercises via email to mobilerobotics@informatik.uni-freiburg.de.
- Exercise sheet 1 – Setup (PDF)
- Exercise sheet 2 – Linear Algebra, Locomotion, and Sensing (updated 2.05., 5.10pm) (PDF, laserscan.dat)
- Exercise sheet 3 – Locomotion, Bayes Rule, Bayes Filter (PDF)
- Exercise sheet 4 – Sampling, Motion Model, Bayes Filter (PDF)
- Exercise sheet 5 – Probability Distributions, Velocity-Based Motion Model (PDF)
- Exercise sheet 6 – Sensor Model, Particle Filter (PDF, files)
- Exercise sheet 7 – Particle Filter (PDF, pf_framework)
- Exercise sheet 8 – Kalman Filter (PDF, ekf_framework)
- Exercise sheet 9 – Mapping with Known Poses (PDF)
- Exercise sheet 10 – SLAM Basics (PDF)
- Exercise sheet 11 – ICP (PDF, icp_framework)
- Exercise sheet 12 – Motion Planning (PDF, dijkstra_framework)
Slides
- Introduction PDF
- Robot Control Paradigms PDF
- Wheeled Locomotion PDF
- Sensors PDF
- Probabilities and Bayes PDF
- Probabilistic Motion Models PDF
- Probabilistic Sensor Models PDF
- Discrete Filters PDF
- Particle Filter, MCL PDF
- Kalman Filter PDF
- Extended Kalman Filter PDF
- Mapping with Known Poses PDF
- Techniques for 3D Mapping PDF
- SLAM: Simultaneous Localization and Mapping PDF
- SLAM: Landmark-based FastSLAM PDF
- SLAM: Grid-based FastSLAM PDF
- Iterative Closest Points Algorithm PDF
- Path Planning and Collision Avoidance PDF
- Multi-Robot Exploration PDF
- Information-Driven Exploration PDF
- Summary PDF
Recordings
In case of missing recording in SS12, please consult the 2009 recordings.(For downloading, you might have to right-click and choose "Save link as...")
- Introduction (no recordings)
- Paradigms (no recordings)
- Locomotion (no recordings)
- Sensors
- Probabilities and Bayes - Part 1
- Probabilities and Bayes - Part 2
- Motion Models - Part 1
- Motion Models - Part 2
- Motion Models - Part 3
- Sensor Models - Part 1
- Particle Filter - Part 1
- Particle Filter - Part 2
- Kalman Filter
- Extended Kalman Filter
- Mapping with Known Poses - Part 1
- Mapping with Known Poses - Part 2
- Techniques for 3D Mapping
- SLAM/EKF SLAM - Part 1
- SLAM/EKF SLAM - Part 2
- FastSLAM - Part 1
- ICP
- Path Planning and Collision Avoidance - Part 1
- Path Planning and Collision Avoidance - Part 2
- Multi-Robot Exploration
- Information-Driven Exploration - Part 1
- Information-Driven Exploration - Part 2
- Summary
Additional Material
- Octave cheat sheet
- Linear Algebra
- Bayes' Rule Example PDF
- Basic Probabilities Rules PDF
- Presence Exercise on Bayes Filter PDF Solution
- Kalman Filter Tutorial by Welch and Bishop PDF
- Explanation and derivation of the particle filters equations for mobile robot localization and for mapping with grid maps (PDF)