330.311 Robot Challenge
This course is in all assigned curricula part of the STEOP.
This course is in at least 1 assigned curriculum part of the STEOP.

2022W, VU, 2.0h, 9.0EC
TUWEL

Course evaluation

Properties

  • Semester hours: 2.0
  • Credits: 9.0
  • Type: VU Lecture and Exercise
  • Format: Hybrid

Learning outcomes

After successful completion of the course, students are able to...

  • Understand the challenges of robotics in manufacturing
  • Getting familiar with the concepts of mobile robots and safety in robotics
  • Getting to know concepts of Reinforcement learning and Transfer learning
  • Getting to know ROS and Gazebo software for simulation of robots
  • Integration and manipulation of robotics applications in the simulation environment

Subject of course

Following topics will be presented and discussed in the course:

  • Robotics in manufacturing
  • Mobile robotics
  • Assistant robots
  • Safety in Robotics
  • Machine learning (Reinforcement learning, transfer learning)
  • Innovation and entrepreneurship

Teaching methods

The course is structured in three phases that are graded separately:

  1. Lectures and exam: the course consists of ten individual lectures, which will cover the content of challenges of robotics. The lecture videos are available via TUWEL. A short exam will be conducted at the end of the semester. (25% of the grade)
  2. Individual assignments: three individual assignments will be handed, covering topics such as machine learning and mobile robotics. Code templates and detailed instructions will be provided. (15% of the grade)
  3. Group project: The group project has three phases. In the first phase, students will learn how to work with ROS and Gazebo platforms and import prepared models of robots or environments in the platform. In the second phase, students will be asked to model their own mobile robot and work on the localization and Navigation of it. The last phase is about optimizing the algorithms of navigation for the robot with machine learning methods and python programming. All the phases of project are in simulation environment and the results will compete over some evaluation criteria with other groups. (50% of the grade)

The results should also be documented in the format of a scientific report and presented during the demo day. (10% of the grade)

Mode of examination

Written

Lecturers

Institute

Course dates

DayTimeDateLocationDescription
Thu10:00 - 11:3006.10.2022 - 19.01.2023Seminarraum 107/1 Lecture
Thu10:00 - 11:3027.10.2022 onlineLecture 3
Thu10:00 - 11:3003.11.2022 onlineTutorial 1
Fri13:00 - 14:3004.11.2022Seminarraum 107/1 Lecture 4
Thu10:00 - 11:3001.12.2022 onlineTutorial 2
Tue10:00 - 11:3020.12.2022 onlineTutorial 3
Thu10:00 - 11:3009.02.2023Seminarraum 107/1 competition
Robot Challenge - Single appointments
DayDateTimeLocationDescription
Thu06.10.202210:00 - 11:30Seminarraum 107/1 Introduction
Thu13.10.202210:00 - 11:30Seminarraum 107/1 Lecture 1
Thu20.10.202210:00 - 11:30Seminarraum 107/1 Lecture 2
Thu27.10.202210:00 - 11:30 onlineLecture 3
Thu03.11.202210:00 - 11:30 onlineTutorial 1
Fri04.11.202213:00 - 14:30Seminarraum 107/1 Lecture 4
Thu10.11.202210:00 - 11:30Seminarraum 107/1 Lecture 5
Thu17.11.202210:00 - 11:30Seminarraum 107/1 Lecture 6
Thu24.11.202210:00 - 11:30Seminarraum 107/1 Lecture 7
Thu01.12.202210:00 - 11:30Seminarraum 107/1 Lecture 8
Thu01.12.202210:00 - 11:30 onlineTutorial 2
Thu15.12.202210:00 - 11:30Seminarraum 107/1 Lecture 9
Tue20.12.202210:00 - 11:30 onlineTutorial 3
Thu19.01.202310:00 - 11:30Seminarraum 107/1 Lecture 10
Thu09.02.202310:00 - 11:30Seminarraum 107/1 competition

Examination modalities

The course will be graded as follows:

  1. Exam - 25% of the grade
  2. Individual assignments – 15% of the grade
  3. Group project – 50% of the grade
  4. Documentation- 10% of the grade

Course registration

Begin End Deregistration end
01.09.2022 00:00 31.01.2023 00:00 31.01.2023 00:00

Curricula

Study CodeSemesterPrecon.Info
ALG For all Students

Literature

No lecture notes are available.

Previous knowledge

Students are expected to understand basic concepts of programming (e.g. Python or another OOP language). Previous knowledge on simulation in Robot Operating System (ROS) and Gazebo is beneficial, but not a prerequisite.

Language

English