back to search

TurtleBot: Reinforcement Learning on a Real System

ED110251Aerospace Lab Courses4 ECTSEnglishwinter semesterProfessur für Raumfahrzeugkontrolle (Prof. Kochdumper)
AI-edited module sheet. Based on the TUMonline module description, edited for readability.Original in TUMonline

What it is about

You will learn how mobile robots determine their position, map their surroundings, and move autonomously. To do this, you will work with measurement data, model the dynamics of a TurtleBot, and implement control and Reinforcement Learning in ROS. At the end, you will develop and evaluate, as a team, a Reinforcement Learning agent for autonomous driving on a race track.

What you will be able to do

  • Explain the basic principles of localization, system dynamics, control, and Reinforcement Learning
  • Apply localization and mapping methods to estimate the state of a mobile robot
  • Determine and analyze dynamic models of robotic systems based on experimental data
  • Design and implement control algorithms and robot software with ROS
  • Develop, train, and evaluate Reinforcement Learning agents for autonomous navigation
  • Integrate perception, control, and learning into an autonomous robotic system
  • Clearly communicate technical results in reports and collaborative project work

What the module consists of

  • PreparationYou prepare the material independently before each session using the resources provided.
  • ExercisesIn the first three course units, you deepen your understanding of the theoretical material and prepare for the laboratory exercises and final project.
  • Practical group workIn groups of no more than four people, you work on and discuss tasks related to the course topics.
  • Laboratory exercisesIn the first three course units, you apply the material in practical exercises using the TurtleBot.
  • Final projectAs a team, you develop, implement, and evaluate a Reinforcement Learning solution for the autonomous navigation of a TurtleBot.

Teaching method

  • Independent preparationYou study the material for each session using the resources provided.
  • Individual exercisesYou consolidate theoretical concepts and practice the skills you need for the laboratory and final project.
  • Practical work in small groupsYou work on tasks together with no more than three other students and discuss the results.
  • Team project with report and source codeYou develop and evaluate, together with your team, a Reinforcement Learning agent for autonomous navigation.

Dates

Lab courseTurtleBot: Reinforcement Learning on a Real System3 groups to choose from

  • Tue09:00–10:00Externer Ort (siehe Anmerkung)once on 20.10.
  • Gruppe 1Tue09:00–11:30Externer Ort (siehe Anmerkung)
    6× · 03.11.–26.01.
    • 03.11.
    • 17.11.
    • 01.12.
    • 15.12.
    • 12.01.
    • 26.01.
  • Gruppe 2Tue12:00–14:30Externer Ort (siehe Anmerkung)
    6× · 03.11.–26.01.
    • 03.11.
    • 17.11.
    • 01.12.
    • 15.12.
    • 12.01.
    • 26.01.
  • Gruppe 3Tue15:00–17:30Externer Ort (siehe Anmerkung)
    6× · 03.11.–26.01.
    • 03.11.
    • 17.11.
    • 01.12.
    • 15.12.
    • 12.01.
    • 26.01.

From the current semester, not binding. You attend one of several groups; the timetable automatically suggests the one with the fewest clashes.

Module ratings

No ratings for this module yet.

Rate this module

Only fill in the categories you can judge – for each one, either stars and text together or nothing at all.

Lecture
Tutorial
Exam

Reviews are automatically checked before they are published.

Official page in TUMonline · Details are not binding.