Welcome to the Course "Mobile Robotics"! This online course goes over 8 weeks. It starts on November 14, 2022 and ends on January 29, 2023. In each week, there is something to do for you, for example, readings or watching videos, and assignments (tasks for you to accomplish). The best way to start, is to read the syllabus. It gives you an overview of the process and what to expect in the coming 8 weeks.
Location and Time: Online, access via Canvas (8 weeks)
Starts: November 14, 2022
Ends: January, 29, 2023
 |
Prof. Dr. Wolfram Burgard
Office: Ulmenstr. 52i, Nuremberg Email: wolfram.burgard@utn.de |
- Dr. Michael Krawez
- Reihaneh Mirjalili
Recommended: Thrun, Burgard & Fox (2005), "Probabilistic Robotics"
ISBN: 9780262201629
This course will introduce basic concepts and techniques used within the field of mobile robotics. The course focuses on the fundamental challenges for autonomous intelligent systems and presents the state of the art solutions. Among other topics, we will discuss:
- Kinematics
- Sensors
- Probabilistic modelling
- Robot localization
- SLAM
The course focus lies on probabilistic approaches to robot state estimation. Though the most relevant mathematical concepts are introduced within the course, the students are expected to have experience with probability theory, linear algebra, and mathematical analysis. Further, fundamental Python skills are expected for the programming assignments. The expected weekly workload in this course for a student with a B.Sc. in computer science is 10 hours.
At the end of this course, students are able to:
- provide an overview of problems and approaches in mobile robotics
- understand and model the kinematics of a wheeled robot
- apply Bayesian inference to the problem of state estimation
- model proximity sensors such as LiDAR or Sonar sensors
- probabilistically model the motion of a mobile robot
- apply the knowledge to realize an approach to estimate the position of a mobile robot given a map
The activity-based model of instruction starts from the premise that students don’t learn because the instructor does some activity, students learn through their own activity. The instructor designs activities for students, students undertake these activities (sometimes independently and sometimes in collaboration with others), and then through a combination of instructor feedback, interaction with the objects they make or encounter in the learning, or self-reflection and peer critique, students make sense of their activity and what they have learned.
- Learning Unit 1: Introduction (14. Nov. 2022 - 20. Nov. 2022)
- Learning Unit 2: Locomotion and Sensors (21. Nov. 2022 - 27. Nov. 2022)
- Learning Unit 3: Probabilistic Robotics (28. Nov. 2022 - 04. Dec. 2022)
- Learning Unit 4: Probabilistic Sensor and Motion Models (05. Dec. 2022 - 11. Dec. 2022)
- Learning Unit 5: Bayes Filters (12. Dec. 2022 - 15. Jan. 2023, includes 3 weeks of Christmas break)
- Learning Unit 6: SLAM (16. Jan. 2023 - 29. Jan. 2023)