This website is no longer updated.

As of 1.10.2022, the Faculty of Physics has been merged into the TUM School of Natural Sciences with the website https://www.nat.tum.de/. For more information read Conversion of Websites.

de | en

Masterpraktikum - Software Engineering in Robotics (IN2106, IN4252)

Course 0000005305 in WS 2019/20

General Data

Course Type practical training
Semester Weekly Hours 6 SWS
Organisational Unit Informatics 6 - Chair of Robotics, Artificial Intelligence and Real-time Systems (Prof. Knoll)
Lecturers Mahmoud Younes Mahmoud Akl
Alexander Lenz
Florian Walter
Responsible/Coordination: Alois Christian Knoll
Dates

Assignment to Modules

Further Information

Courses are together with exams the building blocks for modules. Please keep in mind that information on the contents, learning outcomes and, especially examination conditions are given on the module level only – see section "Assignment to Modules" above.

additional remarks PLEASE NOTE: Prospective participants must have the required previous knowledge stated below and apply for the course as explained in "Course Criteria & Registration". Modern robots are among the most complex devices built to date. Data from dozens of sensors ranging from simple position sensors to depth cameras need to collected, processed and transformed into corresponding control commands in real-time. So far, data processing is mostly carried out on dedicated controllers with vendor-specific software infrastructures. However, the requirement for transparent data access, new applications in service robotics and currents trends in machine learning and cloud robotics require new flexible software architectures and transparent interfaces. The goal of this practical course is to implement scalable cloud services for robotics. Participants will analyze common software components and use cases in robotics (perception, path planning, machine learning etc.) and make them available through easy-to-use APIs using state-of-the art tools and infrastructure. The final system will let prospective users easily instantiate new robot controller systems on demand, evaluate them on a cloud-based robot simulator and seamlessly deploy them to the physical robot.
Links E-Learning course (e. g. Moodle)
TUMonline entry

Equivalent Courses (e. g. in other semesters)

Top of page