Unitree GO1

The video shows our Unitree GO1 robot at its first steps at CPS. This quadruped robot can locomote in rough terrain, autonomously avoids obstacles like stones or blocking barriers, and provides a large number of sensors for navigation and mapping research projects. 



  • Research videos using the robot will be presented here. 


  • Publications about the robot as well as related topics will be found here.

Zoll / Imports / Exports

Für Exporte u. Importe aus dem Nicht-EU Ausland

  • Zollvorschriften:
  • HAM. Code check:

Importe / Exporte über die DHL

Hier sollen alle Daten vorab auf MyDHL+online eingetragen werden.

Hilfe gibte es hier


Ansprechperson MUL

Finanzbuchhaltung: Nadja Schulhofer (

Vacations and Work from Home

General Workflows and Agreements

Find below some general descriptions of workflows and agreements for working at our chair.

For any further question, you can always ask the whole CPS team.

Vacation Application Process

Please follow the instructions below, when you apply for any vacation days. 
  1. Request my permission via email
    • Please always send me an email first, where you ask for my ok for your vacation plan. Otherwise, I will ignore any notifications from the SAP system.
    • Add Regina cc to the email

  2. Apply for vacations in the online SAP portal (
    • I will receive an automatic email notification and will approve your application.
    • Without my approval, your application is not granted.

  3. Add your vacation days to our “CPS Events” Calendar
    • All of you have write access to add your vacation days.  

Working from at Home

According to your work contract, you have to come to the office for work.

Exceptions based on eventually valid covid regulations will be communicated via emails from the president of the university.

Understanding the basics of privacy

Important Articles

Companies like Google collect and process your data

Google collects your data from many different sources. Here are some examples:

  • Gmail: Google can read and store information from every email you write and receive, including in the spam, draft, and trash folders.
  • Google Maps: Google saves every location you search, in addition to all the places you physically visit with your devices, even if you aren’t logged in. Are you using Waze instead? Google owns that too. The ubiquity of phones and our constant use of them makes them almost like tracking devices we carry around willingly.
  • Android devices: Because Android phones and tablets run on an operating system built by Google, the company can track which ads you’re shown while using your phone. Google also knows what time, down to the second, you open each app.
  • Google apps: The Google Play store records all your searches and downloads, as well as any rewards cards used. Google also tracks which articles you’ve read through Google News.
  • YouTube: Google acquired YouTube back in 2006. When you’re using YouTube, Google tracks your search history, your watch history, how long you spend watching videos, and all your comments and likes or dislikes.
  • Google Assistant: Every request you make and every question you pose is recorded — you can even listen to the audio playback.
  • G Suite: Your calendar shows where you’ll be and when, and Google Hangouts saves all of your conversations.

If you are interessted in which data Google has collected about you, test Google Takeout.

Recommendations: Browser, Search Engine & Online Docs

In our digital age, we have to be aware of the data collection strategies of all services that we use. However, often, alternatives  developed by the open-source community exist. Here are some recommendations:


Recommendations: Messenger & Repositories

  • I personally recommend: Nextcloud’s Talk App.
  • Setup your own repo server using, e.g., Gitea or Gitey.

Final remarks: Stay sensitive to what happens to your data. Nothing is for free.

Digital Competencies – Data Safety, Privacy and Content Search on the net

Getting started with Pytorch using Cuda acceleration

This tutorial gives an instruction on installing Cuda and enabling Cuda acceleration using Pytorch in Win10. Installation in Linux or Mac systems are all possible. An additional .py file will verify whether the current computer configuration uses the Cuda or not. The following instruction assumes that you have already installed Python IDE, e.g., Anaconda, Pycharm, Visual Studio…

Step 1: Check which Cuda version is supported by your current GPUs under this website. From the left figure, we can see that A100 supports Cuda 11.0. It is also reported from other blogs/ forums that A100 can support Cuda 11.1. In this post, we install Cuda 11.1.

Step 2: Download Nvidia Cuda Toolkit 11.1 (the same version as Cuda in Step 1) from the website. In Win10, for instance, we follow up the choice as shown right. The size of exe(local) is around 3.1GB. After downloading, run the .exe and perform installation. It may take some minutes to complete installation.

Step 3: On the homepage of Pytorch, choose the appropriate options as shown in the left figure. IMPORTANT: The cuda version must be the same as in Step 1. It is also recommended to use Stable version. After finishing the , copy the command into Anaconda Powershell Prompt or other command prompt where you install packages for Python. Waiting for the installation, which may require larger than 1GB disk space and takes some minutes for installation. You could also find historical version of Pytorch in that homepage.

Verify your installation with .py file

You could download a file and run it. If the result shows ‘cuda’, then you can enjoy the Cuda acceleration for training neural networks!

Using Multiple GPUs for further acceleration

Running Pytorch with Multiple GPUs can further increase the efficiency. We have 8 GPU cards and can be used parallely for training. Please refer to (1) (2) (3) for details. 

150.000 MINT – Digital competencies (0.66SH P, WS)

This entry course discusses major competences all students should have to study at the MUL.
The Chair of CPS provides tutorials on
  • Data Safety, Privacy and Content Search on the net.
  • Learning Python using online tools.
  • Learning to develop 3D-CAD models using online tools.
  • Using powerful online team working tools including shared documents.
  • Using data repositories and creating your personal webpage.

Links and Resources

Location & Time

  • See the MUOnline link. 
  • CPS Presentations are on the: 17.10.2022 at 11.00 in the HS1 Studierendenzentrum.

Posts on Digital Competencies

Integrated CPS Project or B.Sc. Thesis: Mobile Navigation via micro-ROS


Start date: October 2022



  • Interest in controlling and simulating mobile robotics
  • Interest in Programming in Python and ROS or ROS2
Keywords: Mobile robot control, robot operating system (ROS), ESP32


The goal of this project or thesis is to develop a control and sensing interface for our mobile robot “RMP220“. The RMP220 has two powerful brush-less motors equipped with two magnetic encoders.

Learn in this project how to read the sensor values and how to control the motors via micro-ros on a ESP32 controller.



Note: This project is also offered as Internship position.

Single Person Project or Team Work

You may work on the project alone or in teams of up to 4 persons.

For a team work task, the goals will be extended to control the robot via ROS 2 and to simulate it in Gazebo or RViz.


If this project sounds like fun to you, please contact Linus Nwankwo or Elmar Rueckert or simple visit us at our chair in the Metallurgie building, 1st floor.

190.006 Seminar for Doctoral Students (4SH, WS)

Univ.-Prof. Dr. Elmar Rueckert is organizing this doctoral seminar.

The goals of this course are

  • Instruction in the scientific treatment of problems in machine learning,
    robotics and cyber-physical systems.
  • Presentation and defense of own hypotheses in the field of the respective dissertation.
  • Guidelines for writing scientific papers at an international level.
  • Discussion of the content and structure of a doctoral thesis.
  • Discussion of CVs with examples of Ph.Ds., Postdocs, early career stage professors and of full professors.
  • Discussion on potential career paths and differences in the individual systems.

English only

You are a doctoral student and would like to learn how AI achievements are presented, defended, and discussed?

This course will give you the opportunity to discuss all aspects of a doctoral thesis and of potential career paths in AI. Univ.-Prof. Dr. Elmar Rueckert will discuss best practices in publishing, presenting and how to get the ideal future job.


    • 07.10.22 13:15 Univ.-Prof. Dr. Elmar Rueckert gives an Introduction to the content of the doctoral seminar. Also online via:
    • 14.10.22 13:15 – 17:30
    • 21.10.22 13:15 – 17:30
    • 28.10.22 13:15 – 17:30
    • 04.11.22 13:15 – 17:30
    • 11.11.22 13:15 – 17:30
    • 18.11.22 13:15 – 17:30
    • 25.11.22 13:15 – 17:30
    • 02.12.22 13:15 – 17:30
    • 09.12.22 13:15 – 17:30
    • 16.12.22 13:15 – 17:30
    • 13.01.23 13:15 – 17:30
    • 20.01.23 13:15 – 17:30
    • 27.01.23 13:15 – 17:30

Location & Time

Links and Resources

560.002 Do-it Lab Mechanical Engineering (1SH P, WS )

You have no prior experience with robots but would like to work with them?

If so, this hands-on project will enable you to build and control your own robot.

You will use Python to program intelligent navigation or even learning strategies. 

At the end of the practical project, we discuss your achievements and what you have learnt.

You can work on your own or build a team of up to three people at most. We provide a student lab with all-in-one-pcs prepared to code in Python on an ubuntu os.

The project is based on code examples, wiki pages and video tutorials for non-experts.

Links and Resources

Location & Time

Learning objectives / qualifications

  • Students get a practical experience in working, programming and understanding autonomous robots in navigation and obstacle avoidance tasks.
  • Students understand and can apply classical robot path planning and navigation algorithms.
  • Students learn how to present their implementation, assumptions and achievements.

Universal Robot UR3e

Picture Source: [visited at 20.07.2022]

The UR3e from Universal Robots is an ultra-light, compact, collaborative table-top robot that can effortlessly perform high-precision assembly and screwdriving tasks, for example. It has a reach of 500 mm and can carry up to 3 kg of weight.


  • For more information about the Universal Robots company and the robots they build, visit their website at:


  • Research videos using the robot will be presented here. 


  • Publications about the robot as well as related topics will be found here.