Author: Elmar Rueckert

image_pdfimage_print

Dr. Nils Rottmann

Elmar Rueckert people_alumni

Ph.D. Student at the University of Luebeck

Short bio: With January 2018, Nils Rottmann is a PhD student and research scientist at the Institute for Robotics and Cognitive Systems at the University of Luebeck. In his doctoral study, with the title “Smart Sensor, Navigation and Learning Strategies for low-cost lawn care Systems”, he develops low-cost sensor systems and investigates probabilistic learning and modeling approaches. His research addresses the challenges of learning adaptive control strategies from few and sparse data and to predict and plan complex motions in dynamical systems.

He holds a master’s degree in Theoretical Mechanical Engineering from the Hamburg University of Technology, Germany. Nils Rottmann graduated with honors in December 2017 with a thesis entitled „Geometric Control and Stochastic Trajectory Planning for Underwater Robotic Systems“.

Research Interests

  • Robotics: Mobile Robotics, Sensor Development, Robot-Operating-System (ROS), Mobile Navigation, Path Planning, Complete Coverage Path Planning, Probabilistic Robotics.
  • Machine Learning: Non-Linear Regression, Graphical Models, Probabilistic Inference, Variational Inference, Gaussian Processes, Bayesian Optimization.

Contact & Quick Links

M.Sc. Nils Rottmann
Doctoral Student supervised by Univ.-Prof. Dr. Elmar Rueckert since March 2018.
Ratzeburger Allee 160,
23562 Lübeck,
Deutschland

Phone:  +49 451 3101 – 5222 
Email:   rottmann@rob.uni-luebeck.de
Web:  https://nrottmann.github.io

CV of M.Sc. Nils Rottmann
DBLP
Frontiers Network
GitHub
Google Citations
LinkedIn
ORCID
Research Gate

Publcations

2021

Rottmann, N.; Denz, R.; Bruder, R.; Rueckert, E.

Probabilistic Approach for Complete Coverage Path Planning with low-cost Systems Proceedings Article

In: European Conference on Mobile Robots (ECMR 2021), 2021.

Links | BibTeX

Probabilistic Approach for Complete Coverage Path Planning with low-cost Systems

Cansev, Mehmet Ege; Xue, Honghu; Rottmann, Nils; Bliek, Adna; Miller, Luke E.; Rueckert, Elmar; Beckerle, Philipp

Interactive Human-Robot Skill Transfer: A Review of Learning Methods and User Experience Journal Article

In: Advanced Intelligent Systems, pp. 1–28, 2021.

Links | BibTeX

Interactive Human-Robot Skill Transfer: A Review of Learning Methods and User Experience

2020

Rottmann, N.; Bruder, R.; Schweikard, A.; Rueckert, E.

Exploiting Chlorophyll Fluorescense for Building Robust low-Cost Mowing Area Detectors Proceedings Article

In: IEEE SENSORS , pp. 1–4, 2020.

Links | BibTeX

Exploiting Chlorophyll Fluorescense for Building Robust low-Cost Mowing Area Detectors

Rottmann, N.; Kunavar, T.; Babič, J.; Peters, J.; Rueckert, E.

Learning Hierarchical Acquisition Functions for Bayesian Optimization Proceedings Article

In: International Conference on Intelligent Robots and Systems (IROS’ 2020), 2020.

Links | BibTeX

Learning Hierarchical Acquisition Functions for Bayesian Optimization

Rottmann, N.; Bruder, R.; Xue, H.; Schweikard, A.; Rueckert, E.

Parameter Optimization for Loop Closure Detection in Closed Environments Proceedings Article

In: Workshop Paper at the International Conference on Intelligent Robots and Systems (IROS), pp. 1–8, 2020.

Links | BibTeX

Parameter Optimization for Loop Closure Detection in Closed Environments

Rottmann, N.; Bruder, R.; Schweikard, A.; Rueckert, E.

A novel Chlorophyll Fluorescence based approach for Mowing Area Classification Journal Article

In: IEEE Sensors Journal, 2020.

Links | BibTeX

A novel Chlorophyll Fluorescence based approach for Mowing Area Classification

Xue, H.; Boettger, S.; Rottmann, N.; Pandya, H.; Bruder, R.; Neumann, G.; Schweikard, A.; Rueckert, E.

Sample-Efficient Covariance Matrix Adaptation Evolutional Strategy via Simulated Rollouts in Neural Networks Proceedings Article

In: International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI’ 2020), 2020.

Links | BibTeX

Sample-Efficient Covariance Matrix Adaptation Evolutional Strategy via Simulated Rollouts in Neural Networks

2019

Rottmann, N.; Bruder, R.; Schweikard, A.; Rueckert, E.

Loop Closure Detection in Closed Environments Proceedings Article

In: European Conference on Mobile Robots (ECMR 2019), 2019, ISBN: 978-1-7281-3605-9.

Links | BibTeX

Loop Closure Detection in Closed Environments

Rottmann, N.; Bruder, R.; Schweikard, A.; Rueckert, E.

Cataglyphis ant navigation strategies solve the global localization problem in robots with binary sensors Proceedings Article

In: Proceedings of International Conference on Bio-inspired Systems and Signal Processing (BIOSIGNALS), Prague, Czech Republic , 2019, ( February 22-24, 2019).

Links | BibTeX

Cataglyphis ant navigation strategies solve the global localization problem in robots with binary sensors

Mrs. Mag. Elenka Orszova

Elmar Rueckert people_alumni

Secretrary

Short bio: Mrs. Mag. B.Sc. Elenka Orszova  started in August 2021 at the chair of CPS. 

She studied Anthropology and Cognitive Science at the Comenius University in Bratislava, Slovakia. 

Research Interests

  • Cyber-Physical-Systems 
  • Modern Technologies 
  • Learning Machines and Robotics

Contact

Mrs. Mag. Elenka Orszova
Sekretariat des Lehrstuhls für Cyber-Physical-Systems
Montanuniversität Leoben
Franz-Josef-Straße 18, 
8700 Leoben, Austria 

Phone:  +43 3842 402 – 1901
Email:   elenka.orszova@unileoben.ac.at 
Web:  https://cps.unileoben.ac.at

Integrated CPS Project or B.Sc./M.Sc. Thesis: Learning to Walk through Reinforcement Learning

Elmar Rueckert teaching_openprojecttopics, teaching_openthesestopics

Supervisor: 

Start date: ASAP, e.g., 1st of October 2022

Qualifications

  • Interest in controlling and simulating legged robots
  • Interest in Programming in Python and ROS or ROS2
 
Keywords: locomotion, robot control, robot operating system (ROS), ESP32

Introduction

For humans, walking and running are effortless provided good health conditions are satisfied. However, training bipedal or quadrupedal robots to do the same is still today a challenging problem for roboticists and researchers. Quadrupedal robots are known to exhibit complex nonlinear dynamics which makes it near impossible for control engineers to design an effective controller for its locomotion or task-specific actions. 

Reinforcement learning in recent years has shown the most exciting and state-of-the-art artificial intelligence approaches to solving the above-mentioned problem. Although, other challenges, such as learning effective locomotion skills from scratch, transversing rough terrains, walking on a narrow balance beam [3], etc remains. Several researchers in their respective work have proved the possibilities of training quadrupedal robots to walk (fast or slow) or run (fast or slow) through reinforcement learning. Nevertheless, how efficient and effective these walking and running skills are achieved with real-time systems in comparison to humans or quadrupedal animals is still a task to solve.

In the context of this thesis, we propose to study the concept of reinforcement learning and subsequently apply it to train our 3D printed quadrupedal robot in the figure above to walk and run. For this, we will leverage on the work of [1, 2] to explore the robots’ capabilities in generating very dynamic motions or task-specific locomotive actions through reinforcement learning.

Tentative Work Plan

The following concrete tasks will be focused on:

  • study the concept of reinforcement learning as well as its application in quadruped robots for testing control and learning algorithms.
  • apply reinforcement learning algorithms to train the robot to perform skill-specific tasks such as walking, running, etc.
  • real-time experimentation, simulation (MATLAB, ROS & Gazebo, Rviz, C/C++, Python, etc) and validation.

References

[1]        Felix Grimminger, Avadesh Meduri, Majid Khadiv, Julian Viereck, Manuel Wuthrich Maximilien Naveau, Vincent Berenz, Steve Heim, Felix Widmaier, Thomas Flayols Jonathan Fiene, Alexander Badri-Sprowitz and Ludovic Righetti, “An Open Torque-Controlled Modular Robot Architecture for Legged Locomotion Research”, arXiv:1910.00093v2 [cs.RO] 23 Feb 2020.

[2]        Tuomas Haarnoja, Sehoon Ha, Aurick Zhou, Jie Tan, George Tucker and Sergey Levine, Learning to Walk via Deep Reinforcement Learning, arXiv:1812.11103v3 [cs.LG] 19 Jun 2019.

[3]        Haojie Shi1, Bo Zhou2, Hongsheng Zeng2, Fan Wang2y, Yueqiang Dong2, Jiangyong Li2, Kang Wang2, Hao Tian2, Max Q.-H. Meng, “Reinforcement Learning with Evolutionary Trajectory Generator: A General Approach for Quadrupedal Locomotion”, arXiv: 2109.0 6 4 09v1  [cs.RO]  14 Sep 2021.

Link: zur Folie

Robert-Bosch-Stiftung LEGO Robotic 07/2019-10/2021

Elmar Rueckert projects_research_past

Neuartige Robotertechnologien und künstliche Lernmethoden können Schlüsseltechnologien sein, um  unsere Umwelt zu schützen. Prof. Dr. Elmar Rückert und Herr Ole Pein haben diese Seite ins Leben gerufen, um diese Thematik gemeinsam mit Schülerinnen und Schülern des Carl-Jacob-Burckhardt-Gymnasium in Lübeck zu untersuchen.

Das Projekt wird innerhalb des Wahlpflichtunterrichts am Carl-Jacob-Burckhardt-Gymnasium  in der 8. und 9. Klassenstufe verwirklicht. In der 8. Klasse lernen die Schülerinnen und Schüler Lego-Mindstorms-EV3-Roboter zu konstruieren und zu programmieren. 

Das Projekt basiert auf unserer frei verfügbaren Python Software für LEGO EV3s. Es wird kontinuierlich von einem Team der Universität Lübeck weiterentwickelt und an die Bedürfnisse und Fragestellungen der Schülerinnen und Schüler angepasst.

Das Projekt mit dem Titel „Autonome Elektrofahrzeuge als urbane Lieferanten“ wird im Rahmen des Programms „Our Common Future“ von der Robert Bosch Stiftung gefördert.

Link: https://future.ai-lab.science

1 Secretary – July 1st 2021, RefID: 2106APC

Elmar Rueckert pastjob

1 Stelle für eine/n halbbeschäftigte/n Sekretär/in am Department Product Engineering – Lehrstuhl Cyber
Physical Systems an der Montanuniversität Leoben ab ehest möglichem Termin in einem unbefristeten
Arbeitsverhältnis Verw.Gr. IIb nach Uni-KV, monatl. Mindestentgelt exkl. Szlg.: 2.023,50 € für 40 Wochenstunden (14xjährlich), tatsächliche Einstufung erfolgt lt. anrechenbarer tätigkeitsspezifischer Vorerfahrung).

Aufgabenbereich

Korrespondenz; Buchhaltungs- und Verrechnungsaufgaben; Tätigkeiten im Zusammenhang mit MU_online und PURE betreffend den Lehrstuhl; Studentenbetreuung; Parteienverkehr; Allgemeine Büro- und Verwaltungstätigkeiten; Büromaterialverwaltung, eigenverantwortliche Führung der Lehrstuhlbibliothek.

Voraussetzungen

Abgeschlossene kaufmännische Ausbildung (Handelsschule oder ähnliches).

Erwünschte Qualifikation

Ausgezeichnete Korrespondenz in deutscher und englischer Sprache; sehr gute EDV-Kenntnisse (MS Office); SAP-Kenntnisse; MUonline-Kenntnisse; Kenntnisse im Bereich der Buchhaltung und des Rechnungswesens, Homepage-Kenntnisse, Selbständiges und genaues Arbeitensowie Einsatzfreude und Organisationsgeschick.

Männliche Bewerber nur nach abgeschlossenem Präsenz-/Zivildienst.

Bewerbung und Unterlagen

Application deadline: June 30th, 2021

Online Bewerbung auf: Montanuniversität Leoben Homepage (unter dem Kürzel 2106APC)

Die Montanuniversität Leoben strebt eine Erhöhung des Frauenanteiles an und fordert deshalb qualifizierte Frauen ausdrücklich zur Bewerbung auf. Frauen werden bei gleicher Qualifikation wie der bestgeeignete Mitbewerber vorrangig aufgenommen.

2 PhD Positions – December 1st 2021, DFG-Train-Project

Elmar Rueckert pastjob

We offer two positions for fully employed Doctoral Students at the Chair of Cyber-Physical-Systems starting as soon as possible. The contract is initially limited till 30.06.2023 with the option of extension by another 30 months. Salary Group B1 to Uni-KV, monthly minimum charge excl. SZ.: € 2.971,50 for 40 hours per week (14 times a year), actual classification takes place according to accountable activity-specific previous experience.

Job Description

Within the research project TRAIN we are looking for  highly motivated students with experience in one of the fields robotics, reinforcement learning, machine learning or computational neuroscience.
The students will investigate novel transfer learning strategies of robot manipulation tasks that can be learned from human demonstrations and corrections. The methods include probabilistic deep learning, stochastic neural networks and probabilisitic inference approaches. The target evaluation platform is a compliant robot arm FRANKA EMIKA equipped with a five finger hand and tactile sensors.

The positions provide the possibility of gaining a PhD degree.

What we offer

The opportunity to work on research ideas of exciting modern topics in artificial intelligence and robotics, to develop your own ideas, to be part of a young and newly formed team, to go on international research trips, and to receive targeted career guidance for a successful scientific career.

Requirements

Completed master’s degree in computer science, physics, telematics, statistics, mathematics, electrical engineering, mechanics, robotics or an equivalent education in the sense of the desired qualification. Willingness and ability for scientific work in research including publications with the possibility to write a dissertation.

Desired additional qualifications

Programming experience in one of the languages C, C++, C#, JAVA, Matlab, Python or similar is beneficial. Experience with Linux or ROS is advantageous. Good English skills and willingness to travel for research and to give technical presentations.

Application & Materials

A complete application includes a (1) detailed curriculum vitae, (2) a letter of motivation, (3) the master’s thesis as PDF file or link, (4) all relevant certificates of prior education for bachelor’s and master’s studies. The following documents will be considered in favor of the candidate. They are however not mandatory. (5) letter(s) of recommendation(s), (6) name, email and phone number of additional references to contact, (7) previous publications as PDFs or links (e.g. from M.Sc. studies).

Application deadline: Open until the position is filled.

Online Application via Email: Please send your application files to cps@unileoben.ac.at

The Montanuniversität Leoben intends to increase the number of women on its faculty and therefore specifically invites applications by women. Among equally qualified applicants women will receive preferential consideration.

1 Lab Technician – June 30th 2021, RefID: 2108APA

Elmar Rueckert pastjob

1 position for a fully employed Lab Technician at the Chair of Cyber-Physical-Systems on the Department of Product Engineering at the earliest possible date or beginning on 15th of June. in a 1-year term of employment with the option of extension in a permanent position. Salary Group 3A to Uni-KV, monthly minimum charge excl. SZ.: € 2.147,30 for 40 hours per week (14 times a year).

Job Description

The tasks include setting up PCs, installing and maintaining operating systems, maintaining GitHub repositories and our webpage and content management systems. Installing robotic hardware (e.g., FRANKA Emika robot arms), recording and editing robotic videos, working with the modern robotic and machine learning tools.

What we offer

Being part of a young research team, helping creating a new lab environment. Versatile tasks including working with modern or self-build robotic and machine learning systems. Full time position with the option of an open-ended contract.

Requirements

Completed technical high school with an university entrance qualification or equivalent education (in german: HTL Absolvent mit Maturaabschluß).
We require self-motivation, independence, problem solving oriented thinking, technical interests in computer science topics, reliability and sociability or the ability to work in a team.

Application & Materials

Details to the application process will be published soon.

Application deadline: September 30th, 2021

Online Application via: Montanuniversität Leoben Webpage (search for 2108APA)

The Montanuniversitaet Leoben intends to increase the number of women on its faculty and therefore specifically invites applications by women. Among equally qualified applicants women will receive preferential consideration.

1 Research Group Leader / Senior Researcher, 2302WPD

Elmar Rueckert pastjob

One vacant position for a full-time senior scientist (m/f/d) at the Chair of Cyber-Physical-Systems, in the Department Product Engineering – Start at the earliest possible date in an employment contract limited to three years with the option of extension in a permanent employment relationship. Salary Group B1 according to the Uni-KV, monthly minimum salary excl. Szlg.: € 4.351,90 for 40 hours per week
(14 x).

Job Description

The research topics of the group are autonomous systems, machine and deep learning, embedded smart sensing systems, and computational models. The Senior Scientist will work on one of these topics (or combinations thereof), with a focus developed collaboratively based on the candidate’s prior experience. The researcher will additionally be involved in teaching (e.g., student mentoring), project management, and grant applications

What we offer

We offer a research position in fascinating fields with the opportunity to develop your own ideas and implement them independently. In addition, the researcher is part of a young and newly formed team, learns and assumes leadership responsibility with coaching sessions, and receives targeted career counseling for a successful scientific career.

Requirements

Degree in computer science, computer engineering, physics, telematics, electrical engineering, mechanics, robotics, or equivalent related to machine learning or robotics with PhD. Experience in at least one of the topics related to machine learning, image processing, neural networks, robot learning or learning sensor systems, demonstrated by publications in international conferences (e.g., RSS, ICRA, IROS or ICML, IJCAI, AAAI, NIPS, AISTATS) and journals (e.g., AURO, TRo, IJRR or JMLR, MLJ, Neural Computation). Ability to work in a team, sociability, self-motivation, interest in group leadership, very good English skills and reliability are expected.

Desired additional qualifications

Experience in soliciting external funding or industry collaboration experience is a plus.

Application & Materials

An application includes a detailed curriculum vitae with a list of all publications.

Application deadline: 07.06.2023

Online Application via: Email (cps@unileoben.ac.at) and via the Job portal of the university (2305WPB).

The Montanuniversitaet Leoben intends to increase the number of women on its faculty and therefore specifically invites applications by women. Among equally qualified applicants women will receive preferential consideration. Scientific experience demonstrated through publications in international conferences and journals on machine learning, neural networks, robotics, or embedded systems. Good team-leading skills and the ambition to supervise doctoral students. Experience in obtaining external funding and in collaborating with industrial partners is advantageous but not a requirement. Excellent English skills and willingness to travel for research and to give technical presentations are required.

3 PhD Positions – June 30th 2021, RefID: 2103WPW

Elmar Rueckert pastjob

3 positions for fully employed University Assistant’s at the Chair of Cyber-Physical-Systems on the Department of Product Engineering at the earliest possible date or beginning on 15th of June in a 4-year term of employment. Salary Group B1 to Uni-KV, monthly minimum charge excl. SZ.: € 2.971,50 for 40 hours per week (14 times a year), actual classification takes place according to accountable activity-specific previous experience.

The following doctoral theses are available:

Fundamentals of learning methods for autonomous systems.

The goal is to make autonomous learning systems such as industrial robot arms, humanoid or mobile robots suitable for everyday use. To achieve this, large amounts of data must be processed in a few milliseconds (Big Data for Control) and efficient learning methods must be developed. In addition, safe human-machine interaction must be ensured when dealing with the autonomous systems. For this purpose, novel stochastic motion learning methods and model representations for compliant humanoid robots will be developed.

Fundamentals of stochastic neural networks.

Modern deep neural networks can process large amounts of data and calculate complex predictions. These methods are also increasingly used in autonomous systems. A major challenge here is to integrate measurement and model uncertainties in the calculations and predictions. For this purpose, novel neural networks will be developed that are based on stochastic computations that enrich predictions with uncertainty estimations. The neural networks will be used in learning tasks with robotic arms.

Robot learning with embedded systems.

Modern robot systems are equipped with complex sensors and actuators. However, they lack the necessary control and learning methods to solve versatile tasks. The goal of this thesis is to develop novel AI-based sensor systems and to integrate them into autonomous systems. The developed algorithms will be applied in mobile computers and tested on realistic industrial applications with robotic arms.

What we offer

The opportunity to work on research ideas of exciting modern topics in artificial intelligence and robotics, to develop your own ideas, to be part of a young and newly formed team, to go on international research trips, and to receive targeted career guidance for a successful scientific career.

Job requirements

Completed master’s degree in computer science, physics, telematics, statistics, mathematics, electrical engineering, mechanics, robotics or an equivalent education in the sense of the desired qualification. Willingness and ability for scientific work in research including publications with the possibility to write a dissertation.

Desired additional qualifications

Programming experience in one of the languages C, C++, C#, JAVA, Matlab, Python or similar. Experience with Linux or ROS is advantageous. Good English skills and willingness to travel for research and to give technical presentations.

Application

Application deadline: June 30th, 2021

Online Application via: Montanuniversität Leoben Webpage

The Montanuniversitaet Leoben intends to increase the number of women on its faculty and therefore specifically invites applications by women. Among equally qualified applicants women will receive preferential consideration.

How to build a professional low-cost lightboard for teaching

Elmar Rueckert wiki_hard_software

Making Virtual Lectures Interactive

Giving virtual lectures can be exciting. Inspired by numerous blog posts of colleagues all over the world (e.g., [1], [2]), I decided to turned an ordinary glass desk into a light board. The total costs were less than 100 EUR.

Below you can see some snapshots of the individual steps.

Details to the Lightboard Construction

The light board construction is based on

  • A glas pane, 8mm thick. Hint: do not use acrylic glass or glas panes thinner than 8mm. I got an used glass/metal desk for 20EUR.
  • LED stripes from YUNBO 4mm width, e.g. from [4] for 13EUR. Hint: Larger LED strips, which you can typically get at DIY markets have width of 10mm. These strips do not fit into the transparent u profile.
  • Glass clamps for 8mm glass, e.g., from onpira-sales [5] for 12EUR.
  • Transparent U profiles from a DIY store, e.g., the 4005011040225 from HORNBACH [6] for 14EUR.
  • 4 castor wheels with breaks, e.g. from HORNBACH no. 4002350510587 for 21EUR.

Details to the Markers, the Background and the Lighting

Some remarks are given below on the background, the lighting and the markers.

  • I got well suited flourescent markers, e.g., from [6] for 12EUR. Hint: Compared to liquid chalk, these markers do not produce any noise during the writing and are far more visible.
  • The background blind is of major importance. I used an old white roller blind from [7] and turned it into a black blind using 0.5l of black paint. Hint: In the future, I will use a larger blind with a width of 3m. A larger background blind is required to build larger lightboards (mine is 140x70mm). Additionally, the distance between the glass pane and the blind could be increased (in my current setting I have a distance of 55cm).
  • Lighting is important to illuminate the presenter. I currently use two small LED spots. However, in the future I will use professional LED studio panels with blinds, e.g. [8]. Hint: The blinds are important to prevent illuminating the black background.
  • The LED stripes run at 12Volts. However, my old glass pane had many scratches, which become fully visible at the maximum power. To avoid these distracting effects, I found an optimal setting with 8Volts worked best for my old glass pane.

Details to the Software and to the Microphone

At the University, we are using CISCO’s tool WEBEX for our virtual lectures. The tool is suboptimal for interactive lightboard lectures, however, with some additional tools, I converged to a working solution.

  • Camera streaming app, e.g., EPOCCAM for the iphones or IRIUN for android phones. Hint: the smartphone is mounted on a tripod using a smartphone mount.
  • On the client side, a driver software is required. Details can be found when running the smartphone app.
  • On my mac, I am running the app Quick Camera to get a real time view of the recording. The viewer is shown in a screen mounted to the ceiling. Hint: The screen has to be placed such that no reflections are shown in the recordings.
  • In the WEBEX application, I select the IRIUN (virtual) webcam as source and share the screen with the quick camera viewer app.
  • To ensure an undamped audio signal, I am using a lavalier microphone like that one [9].
  • For offline recordings, apple’s quicktime does a decent job. Video and audio sources can be selected correctly. Hint: I also tested VLC, however, the lag of 2-3 seconds was perceived suboptimal by the students (a workaround with proper command line arguments was not tested).

An Example Lecture

And that’s how it looks …