1

190.014 Integrated CPS Projekt (3SH SE, SS & WS)

You are interested in working with modern robots or want to understand how such machines ‘learn’?

If so, this project will enable you to dig into the fascinating world of robot learning.

The course provides a structured and well motivated overview over modern techniques and tools which enable the students to define learning problems in Cyber-Physical-Systems. 

Links and Resources

Location & Time

Learning objectives / qualifications

  • Students get a practical experience in working, modeling and simulating Cyber-Physical-Systems.
  • Students understand and can apply advanced model learning and reinforcement  techniques to real world problems.
  • Students learn how to write scientific reports.

Literature

  • The Probabilistic Machine Learning book by Univ.-Prof. Dr. Elmar Rueckert. 
  • Bishop 2006. Pattern Recognition and Machine Learning, Springer. 
  • Barber 2007. Bayesian Reasoning and Machine Learning, Cambridge University Press
  • Murray, Li and Sastry 1994. A mathematical introduction to robotic manipulation, CRC Press. 
  • B. Siciliano, L. Sciavicco 2009. Robotics: Modelling,Planning and Control, Springer.
  • Kevin M. Lynch and Frank C. Park 2017. MODERN ROBOTICS, MECHANICS, PLANNING, AND CONTROL, Cambridge University Press.



190.004 CPS Research Seminar II

Univ.-Prof. Dr. Elmar Rueckert is organizing this research seminar. Topics include research in AI, machine and deep learning, robotics, cyber-physical-systems and process informatics. 

Language:
English only

Presenters are leading invited external speakers, doctoral students, senior researcher, graduates and undergraduates. 

Upcoming Talks

Location & Time

  • Location: To be decided
  • Dates: To be decided

Past Talks




190.002 Cyber-Physical Systems Lab (2SH P, WS 2022/23)


The exercise will enable the application of modern machine learning techniques and tools in robotics / cyber-physical systems. The following topics will be covered in the course:
   – Kinematics, dynamics & simulation of CPS.
   – Data representations & model learning.
   – Control techniques, priorities & torque control.
   – Planning & cognitive reasoning.
   – Reinforcement learning and black-box optimization.

The course provides a structured and well motivated overview over modern techniques and tools which enable the students to define learning problems in Cyber-Physical-Systems. 

Links and Resources

Location & Time

Learning objectives / qualifications

  • Students get a comprehensive understanding of Cyber-Physical-Systems.
  • Students learn to analyze the challenges in simulating, modeling and controlling CPS.
  • Students understand and can apply basic machine learning and control  techniques in CPS.
  • Students know how to analyze the models’ results, improve the model parameters and can interpret the model predictions and their relevance.

Programming Assignments & Simulation Tools

https://youtu.be/gBYqOBdIcaY

For simulating robotic systems, we will use the tool CoppeliaSim. The tool can be used for free for research and for teaching. 

To experiment with state of the art robot control and learning methods Python will be used. If you never used Python and are unexperienced in programming, please visit the tutorials on Python programming prior to the lecture.  

The course will also use the tool Code With Me from JetBrains. With this stool, we can develop jointly code. 

Literature

  • The Probabilistic Machine Learning book by Univ.-Prof. Dr. Elmar Rueckert. 
  • Bishop 2006. Pattern Recognition and Machine Learning, Springer. 
  • Barber 2007. Bayesian Reasoning and Machine Learning, Cambridge University Press
  • Murray, Li and Sastry 1994. A mathematical introduction to robotic manipulation, CRC Press. 
  • B. Siciliano, L. Sciavicco 2009. Robotics: Modelling,Planning and Control, Springer.
  • Kevin M. Lynch and Frank C. Park 2017. MODERN ROBOTICS, MECHANICS, PLANNING, AND CONTROL, Cambridge University Press.



M.Sc. Thesis: Rui Song on Solving Visual Navigation Tasks for Pedestrian Trajectory Generation Using Distributional Reinforcement Learning and Automatic Curriculum Learning in CARLA

Supervisors: Honghu Xue, Elmar Rückert

Finished: 22.April 2022

Abstract

In this thesis, we propose an approach that combines reinforcement learning and automatic curriculum learning to solve a visual navigation task. A pedestrian agent is expected to learn a policy from scratch in a street-crossing scenario in a realistic traffic simulator CARLA. For this, the pedestrian is restricted to its first-person perspective as sensory input. The pedestrian cannot obtain full knowledge of the environment, which raises a partial observability challenge. To achieve this, an improved version of the Distributional Soft Actor-Critic algorithm is implemented. The algorithm adopts a newly proposed 3D dilated convolutional architecture to deal with the partial observability problem. To further improve its performance, we develop an automatic curriculum learning algorithm called NavACL+ on top of NavACL. As suggested in the results and ablation studies, our approach outperforms the original NavACL by 23.1%. Additionally, the convergence speed of NavACL+ is also observed to be 37.5% quicker. Moverover, the validation results show that the trained policies of NavACL+ are much more generalizable and robust than other variants in terms of different initial starting poses. NavACL+ policies perform 28.3% better than other policies training from a fixed start.

Thesis

Solving Visual Navigation Tasks for Pedestrian Trajectory Generation Using Distributional Reinforcement Learning and Automatic Curriculum Learning in CARLA




B.Sc. or M.Sc. Project/Thesis: Mobile robot teleoperation based on human finger direction and vision

Supervisors: Univ. -Prof. Dr. Elmar Rückert  and Nwankwo Linus M.Sc.

Theoretical difficulty: mid
Practical difficulty: mid

Naturally, humans have the ability to give directions (go front, back, right, left etc) by merely pointing fingers towards the direction in question. This can be done effortlessly without saying a word. However, mimicking or training a mobile robot to understand such gestures is still today an open problem to solve.
In the context of this thesis, we propose finger-pose based mobile robot navigation to maximize natural human-robot interaction. This could be achieved by observing the human fingers’ Cartesian  pose from an

RGB-D camera and translating it to the robot’s linear and angular velocity commands. For this, we will leverage computer vision algorithms and the ROS framework to achieve the objectives.
The prerequisite for this project are basic understanding of Python or C++ programming, OpenCV and ROS.

Tentative work plan

In the course of this thesis, the following concrete tasks will be focused on:

  • study the concept of visual navigation of mobile robots
  • develop a hand detection and tracking algorithm in Python or C++
  • apply the developed algorithm to navigate a simulated mobile robot
  • real-time experimentation
  • thesis writing

References

  1. Shuang Li, Jiaxi Jiang, Philipp Ruppel, Hongzhuo Liang, Xiaojian Ma,
    Norman Hendrich, Fuchun Sun, Jianwei Zhang,  “A Mobile Robot Hand-Arm Teleoperation System by Vision and IMU“,  IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS),  October 25-29, 2020, Las Vegas, NV, USA.
  2.  



Latex Templates

CPS Latex Templates

Find below Latex templates for student reports, B.Sc. theses, M.Sc. theses and doctoral theses.

You may use these templates also for other lectures, courses, seminars or doctoral theses at other chairs at the Montanuniversität Leoben. However, do not remove the acknowledgement or copyright statement.

If you never used Latex, watch our video on an introduction to Latex.

Student Report or Assignment

We provide a professional scientific student report template using double columns.

Get the latest CPS report template from our cloud.

Student Presentation


We provide a scientific student presentation template for project and thesis reports. Get the latest CPS presentation (latex beamer) template from our cloud.

B.Sc. Thesis

We provide a thesis template using minitocs in a standard report format.

Get the latest B.Sc. template from our cloud.

The latex template also provides basic instructions on the content and the structure of a thesis.

However, every thesis is unique and may be adapted acordingly.

M.Sc. Thesis

We provide a thesis template using minitocs in a standard report format.

Get the latest M.Sc. thesis template from our cloud.

Ph.D. Thesis

We provide a Ph.D. thesis template using minitocs in a standard report format.

Get the latest Ph.D. thesis template from our cloud.

In Introduction to Latex

If you have never used Latex, you find a brief intorduction in these slides on Latex.

You may also watch a recording of the exercise by Univ.-Prof. Dr. Elmar Rueckert on Latex.




M.Sc. thesis: Benjamin Schödinger on A framework for learning Vision and Tactile correlation

Supervisor: Vedant Dave, M.Sc; Univ.-Prof. Dr Elmar Rückert
Start date: 1st May 2022

Theoretical difficulty: Mid
Practical difficulty: Mid

Abstract

Tactile perception is one of the basic senses in humans that utilize almost at every instance. We predict the touch of the object even before touching it, only through vision. If a novel object is encountered, we predict the tactile sensation even before touching. The goal of this project is to predict tactile response that would be experienced if this grasp were performed on the object. This is achieved by extracting the features of the visual data and the tactile information and then learning the mapping between those features. 

We use Intel RealSense depth camera D435i for capturing images of the objects and Seed RH8D Hand with tactile sensors to capture the tactile data in real time(15 dimensional data). The main objective is to perform well on the novel object which have some shared feature representation of the previously seen objects.

Plan

  • Literature Research
  • Architecture Development
  • Dataset Collection from Real Robot.
  • Application in Real Robot.
  • Master Thesis Writing
  • Research Paper Writing (Optional)

Related Work

[1] B. S. Zapata-Impata, P. Gil, Y. Mezouar and F. Torres, “Generation of Tactile Data From 3D Vision and Target Robotic Grasps,” in IEEE Transactions on Haptics, vol. 14, no. 1, pp. 57-67, 1 Jan.-March 2021, doi: 10.1109/TOH.2020.3011899.

[2] Z. Abderrahmane, G. Ganesh, A. Crosnier and A. Cherubini, “A Deep Learning Framework for Tactile Recognition of Known as Well as Novel Objects,” in IEEE Transactions on Industrial Informatics, vol. 16, no. 1, pp. 423-432, Jan. 2020, doi: 10.1109/TII.2019.2898264.




Innovative Research Discussion

Meeting notes on the 23rd of March 2022

Location: Chair of CPS

Date & Time: 23rd March. 2022, 12 pm to 1.00 pm

Participants: Univ.-Prof. Dr. Elmar Rueckert, Linus Nwankwo, M.Sc.

 

Agenda

  1. Discussion of the research progress
  2. Discussion of related literature for 2D Lidar-based SLAM and path planning for improved autonomous navigation

Topic 1: SLAM + Path Planning Algorithms

  1.  Compare Lidar-based SLAM with RGBD-based
  2. Select the appropriate algorithm to build the SLAM system
  3. Evaluate the performances of the chosen SLAM + path planning algorithm in terms of:
    • computational efficiency
    • collision avoidance in a dynamic environment.

Topic 2: Real-time Implementation

  1.  Compare our two mobile bases: 
  2. Implement the chosen SLAM algorithm to solve the problem of loop closure that we are currently facing.
  3.  Send the robot to a specific goal location within the laboratory
  4.  

Future Steps

Toward improved autonomous navigation in real-time with any of our mobile bases.

Next Meeting

Yet to be defined




Autonomes Industrieroboterlabor der Zukunft (AI-Robot-Lab)

Ausstattung:

  • 2 universal robotics UR3e Roboter,
  • 2 FANUC CRX10iA Roboter
  • eine Drehbank von ELMAG
  • eine industrie Bohrfräse von ELMAG und
  • ein Rollenförderband.

Die Anforderungen an Industriebetriebe im Zeitalter der Digitalisierung sind enorm gestiegen und der Bedarf an individualisierten Losungen ist groß. Kleine Stückzahlen, komplexe Bauteilegruppen und der notwendige hohe grad der Automatisierung ist mit fest vorprogrammierten Roboterprogrammen nicht mehr umsetzbar.

Projektziel

Ziel des Projektes ist es sich als starken Partner für Forschungs- und Industriebetriebe zu positionieren. Dazu soll ein begehbares, autonomes Industrieroboterlabor aufgebaut werden, in dem Robotern praxisrelevante Arbeitsablaufe durch moderne Lernmethoden der kunstliche Intelligenz beigebracht werden. Werksmitarbeiter können innerhalb weniger Sekunden, durch Vorzeigen oder durch fuhrendes Anleiten, Maschinen komplexe Bewegungsabläufe beibringen. Für die Koordination multipler autonomer Robotereinheiten und die Prozessüberwachung werden moderne Datenmodellierungsmethoden entwickelt und über Tablets bedient.

Anwendungen

Die Anwendungsszenarien umfassen Manipulations- und Sortieraufgaben  an einem Rollenforderband, die automatische visuelle Objekterkennung und Vorhersage unter realen Industriebedingungen, der Warentransport durch mobile Roboter mit Greifarmen und die Bedienung komplexer Industriemaschinen, exemplarisch vorgefuhrt an einer Bohrfräsmaschine und an einer Kleindrehbank.

Kooperationen und öffentliche Events

Das autonome Industrieroboterlabor soll nachhaltig zu Kooperationen mit nationalen und regionalen Forschungs- und Industriepartnern fuhren und die Sichtbarkeit des Lehrstuhls fur Cyber-Physical-Systems (CPS) und der Montanuniversitat Leoben im Bereich der angewandten kunstlichen Intelligenz für CPS durch jährliche öffentliche Events steigern.




Der Lehrstuhl für Cyber-Pysical Systems

Der Lehrstuhl für Cyber-Physical-Systems widmet sich anwendungsorientierter Grundlagenforschung in den Bereichen der künstlichen Intelligenz, der Digitalisierung von Industrieprozessen und der Robotik. Ein Focus liegt dabei auf der Modelierung von intelligenten menschlichen Lernprozessen mit dem Ziel effiziente Lernmethoden und Vorhersagemodelle für cyber-physikalische Systeme zu entwickeln.

Gerade diese Schnittstelle zwischen fundamentaler Grundlagenforschung in tiefen neuronalen Netzen, probabilistischer Informationsverarbeitung und komplexen industriellen Anwendungen zeichnen den Lehrstuhl für Cyber-Physical-Systems aus.

Neben der Entwicklung von Algorithmen und Methoden zur Modelierung und Verarbeitung großer Datenmengen, baut der Lehrstuhl auch komplexe Roboter- und Sensorsysteme. Eines dieser Systeme wird in naher Zukunft autonom an der Universität navigieren, Besucher empfangen und mit ihnen über ein gelerntes Dialogsystem kommunizieren. Darüber hinaus entsteht gerade ein begehbares KI Roboter Labor, dass die anwendungsorientierte Grundlagenforschung anhand von Aufgaben mit Industrieroboterarmen an einem Rollenförderband greifbar macht.