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



Exercises

Attention: Rules for earning bonus points have changed! See updated sheet 1.
Note: there is a FAQ (frequently asked questions) for the exercises/lab assignments.
  1. Exercise sheet 1 – Drives, Odometry, Bayes (ZIP, PDF) updated 30. April
  2. Exercise sheet 2 – Bayes Filter, Motion Models (PDF)
  3. Exercise sheet 3 – Data Explanation, Sensor Models, Discrete Filter (ZIP, PDF)
  4. Exercise sheet 4 – Particle Filter (ZIP, PDF)
  5. Exercise sheet 5 – Kalman Filter (PDF)
  6. Exercise sheet 6 – Grid Mapping, Extended Kalman Filter (ZIP, PDF)
  7. Exercise sheet 7 – Grid Mapping, SLAM (ZIP, PDF)
  8. Exercise sheet 8 – EKF Localization, Bearing-Only SLAM (PDF)
  9. Exercise sheet 9 – Path Planning, ICP (PDF)
  10. Exercise sheet 10 – Exploration (ZIP, PDF)
  11. Exercise sheet 11 – Clustering, Gaussian Process Regression (ZIP, PDF) updated 16. July
Programming assignments have to be submitted electronically. Written assignments (such as proofs, calculations, etc) have to be handed in paper form at the class on Tuesdays.



Slides (Update)

  1. Introduction PDF
  2. Paradigms PDF
  3. Locomotion PDF
  4. Sensors PDF
  5. Probabilities and Bayes PDF
  6. Probabilistic Motion Models PDF
  7. Probabilistic Sensor Models PDF
  8. Bayes Filter - Discrete Filters PDF
  9. Bayes Filter - Particle Filter and Monte Carlo Localization PDF
  10. Bayes Filter - Kalman Filter PDF
  11. Mapping with Known Poses PDF
  12. SLAM: Simultaneous Localization and Mapping PDF
  13. SLAM - Landmark-based FastSLAM PDF
  14. SLAM Grid-based FastSLAM PDF
  15. Path Planning and Collision Avoidance PDF
  16. Iterative Closest Point Algorithm PDF
  17. Place and People Recognition with Mobile Robots PDF
  18. Mapping with Elevation Maps PDF
  19. Multi-Robot Exploration PDF
  20. Improved Multi-Robot Exploration PDF
  21. Information Gain-Based Exploration PDF
  22. Gaussian Processes PDF
  23. Clustering PDF
  24. Summary PDF



Recordings

  1. Wheeled Locomotion (25.04.08)
  2. Proximity Sensors (25.04.08)
  3. Probabilistic Robotics (1) (29.04.08)
  4. Probabilistic Robotics (2) (02.05.08)
  5. Probabilistic Robotics (3) (06.05.08)
  6. Probabilistic Motion Models (1) (06.05.08)
  7. Probabilistic Motion Models (2) (09.05.08)
  8. Probabilistic Sensor Models (1) (09.05.08)
  9. Probabilistic Sensor Models (2) (20.05.08)
  10. Discrete Filters (23.05.08)
  11. Bayes Filter - Particle Filter and Monte Carlo Localization (27.05.08)
  12. Bayes Filter - Kalman Filter (1) (30.05.08)
  13. Bayes Filter - Kalman Filter (2) (03.06.08)
  14. Mapping with Known Poses (1) (03.06.08)
  15. Mapping with Known Poses (2) (06.06.08)
  16. Mapping with Known Poses (3) (10.06.08)
  17. SLAM: Simultaneous Localization and Mapping (10.06.08)
  18. SLAM - Landmark-based FastSLAM (13.06.08)
  19. SLAM Grid-based FastSLAM (17.06.08)
  20. Path Planning and Collision Avoidance (20.06.08)
  21. Iterative Closest Point Algorithm (24.06.08)
  22. Place and People Recognition with Mobile Robots (27.06.08)
  23. Mapping with Elevation Maps (01.07.08)
  24. Multi-Robot Exploration (1) (01.07.08)
  25. Multi-Robot Exploration (2) (08.07.08)
  26. Improved Multi-Robot Exploration (08.07.08)
  27. Information Gain-based Exploration (1) (08.07.08)
  28. Information Gain-based Exploration (2) (11.07.08)
  29. Gaussian Processes (15.07.08)
  30. Clustering (18.07.08)
  31. Summary (1) (22.07.08)
  32. Summary (2) (22.07.08)



Additional Material

  1. Explanation and derivation of the particle filters equations for mobile robot localization and for mapping with grid maps (PDF)
  2. Kalman Filter Tutorial by Welch and Bishop (PDF)