Supervisor: Univ.-Prof. Dr Elmar Rückert
Start date: 1st of July 2021

Theoretical difficulty: mid
Practical difficulty: mid

Abstract

 A central problem in robotics is the description of the movement of a robot. This task is complex, especially for robots with high degrees of freedom. In the case of complex movements, they can no longer be programmed manually. Instead, they are taught to the robot utilizing machine learning. The Motor Control Learning framework presents an easy-to-use method for generating complex trajectories. Dynamic Movement Primitives is a method for describing movements as a non-linear dynamic system. Here, the trajectories are modelled by weighted basis functions, whereby the machine learning algorithms must determine only the respective weights. Thus, it is possible for complex movements to be defined by a few parameters. As a result, two motion learning methods were implemented. When imitating motion demonstrations, the weights are determined using regression methods. A reinforcement learning algorithm is used for policy optimization to generate waypoint trajectories. For this purpose, the weights are improved iteratively through a cost function using the covariance matrix adaptation evolution strategy. The generated trajectories were evaluated in experiments. 

Thesis Document

A Motor Control Learning Framework for Cyber-Physical-Systems

Univ.-Prof. Dr. Elmar Rueckert presents in his two slots how machine learning approaches can be used in robotics. 

Link to the slides on

• Part I: Probabilistic Modelling.
• Part II: Probabilistic Time-Series Models.

Materials for the Robotics Workshop

• Go to https://jupyterlite.github.io/demo
• Download Jupyter Notebook on PTSMs and the Dataset of robot trajectories.
• Drag and drop the files inside the tree view in your browser.

Additional materials:

• Slides on the Chair of Cyber-Physical-Systems.
• Machine Learning book by Univ.-Prof. Dr. Elmar Rueckert. 
• Related Research Paper.
• PTSMs Solution File.

Student Assistant at the Montanuniversität Leoben

Short bio: Clemens Fritze, B.Sc B.Sc started at CPS in July 2022. After a short break he joined the team again in November 2023.

Clemens Fritze is a master student at the Montanuniversität Leoben. Prior to his master program he studied Mechanical Engineering at the Montanuniversität Leoben, where he passed his Bachelor defense in May 2022. In 2018, Mr. Fritze finished a Bachelor study in Business Informatics at the university of applied science in Vienna (german FH Technikum Wien).

Research Interests

• Automation
• Robotics
• IoT

Thesis

Master Thesis

Website: https://cps.unileoben.ac.at/m-sc-thesis-fritze-clemens-a-dexterous-multi-finger-robotic-manipulator-framework-for-intuitive-teleoperation-and-contact-rich-imitation-learning

Bachelor Thesis

Written Thesis: Gesture Based Mobile Robot Teleoperation for Navigation Application

Website: https://cps.unileoben.ac.at/b-sc-thesis-fritze-clemens-on-gesture-based-mobile-robot-teleoperation-for-navigation-application

Contact

Clemens Fritze, B.Sc B.Sc.
Student Assistent at the Chair of Cyber-Physical-Systems
Montanuniversität Leoben
Franz-Josef-Straße 18, 
8700 Leoben, Austria 

Email:   clemens.fritze@stud.unileoben.ac.at

Hybride Modellierung Metallurgischer Prozesse

Contact

• qoncept dx GmbH
• Peter Tunner-Straße 19, 8700 Leoben
• office@qoncept.at
• Web: https://qoncept.at/

Laufende Projekte, Bachelor- und Masterarbeiten

• Improving fundamental metallurgical modelling using data-driven approaches

Supervisor: Univ.-Prof. Dr Elmar Rückert, Qoncept GmbH
Start date: 1st of August 2022

Theoretical difficulty: mid
Practical difficulty: low

Introduction

As direct observations and permanent measurements during steelmaking processes are not possible, modelling has become a powerful tool. The technique of fundamental-based metallurgical modelling is well-established and demonstrates its capabilities in a wide range of applications in modern steelmaking. Following the general trend, data-driven approaches are increasingly used today in various areas of metallurgical modelling, in addition to these  classical fundamental approaches. Depending on the field of application, fundamental-based and data-driven models both have their own advantages and disadvantages.

The overall goal of the present thesis is to combine both models in order to leverage the strengths of  these two different methods. The first step is to apply several different data-driven models and compare them to the metallurgical model to see how they perform differently. In the second phase, various ways of combining data-driven models with the metallurgical model should be investigated. For example, this could be done via a data-driven optimization of its tuning parameters or by replacing them with data-driven models. Also, adding a data-driven residual term to the metallurgical model could be possible. Based on these findings, the third part of the thesis should focus on online learning and methods of how to avoid an off-drifting of the model. The fourth and last section of the thesis should investigate various ways of detecting errors in new data. While point one and two are the main focus of the thesis, point three and four are considered to be optional.

Tentative Work Plan

The following concrete tasks will be focused on:

• Literature research.
• Training of different data-driven models in Python.
• Performance comparison between data-driven models and the metallurgical model.
• Combination of selected data-driven models and the metallurgical model in Python.
• (Optional) Investigate different ways for online learning and live performance evaluation.
• (Optional) Anomaly detection in new data.
• Thesis writing.

Thesis Document

• Master’s Thesis: Predictive Models for Copper Content and Energy Consumption in Electric Arc Furnace Operations Subm. Oct. 2024

Supervisors: Univ.-Prof. Dr Elmar Rückert, LUPA Electronics GmbH
Start date: ASAP from June 2022

Theoretical difficulty: high
Practical difficulty: low

Abstract

Wir Menschen sind in der Lage unter widrigen Bedingungen z.B. bei eingeschränkter Sicht, oder bei Störungen komplexe Vorgänge wahrzunehmen, vorherzusagen und innerhalb von wenigen Millisekunden zusammenhängende Entscheidungen zu treffen. Mit dem zunehmenden Grad der Automatisierung steigen auch die Anforderungen an künstliche Systeme. Immer komplexere und größere Datenmengen müssen verarbeitet werden um autonome Entscheidungen zu treffen. Mit gängigen KI Ansätzen stoßen wir aufgrund der konvergierenden Miniaturisierung an Grenzen, die z.B. im Bereich des autonomen Fahrens nicht ausreichen, um ein sicheres autonomes System zu entwickeln.

Ziel dieser Forschung ist es probabilistische Vorhersagemodelle in massiv parallelisierbaren neuronalen Netzen zu implementieren und mit diesen komplexe Entscheidungen Aufgrund erlernter interner Vorhersagemodelle zu treffen. Die neuronalen Modelle verarbeiten hoch dimensionale Daten moderner und innovativer taktiler und visueller Sensoren. Wir testen die neuronalen Vorhersage und Entscheidungsmodelle in humanoiden Roboteranwendungen in dynamischen Umgebungen.

Unser Ansatz beruht auf der Theorie der probabilistischen Informationsverarbeitung in neuronalen Netzen und unterscheidet sich somit grundlegend von den gängigen Methoden tiefer neuronaler Netze. Die zugrundeliegende Theorie ermöglicht weitreichende Modelleinblicke und erlaubt neben den Vorhersagen von Mittelwerten auch Unsicherheiten und Korrelationen. Diese zusätzlichen Vorhersagen sind entscheidend für verlässliche, erklärbare und robuste künstliche Systeme und sind eines der größten offenen Probleme in der künstlichen Intelligenz Forschung.

Tentative Work Plan

To achieve our aim, the following concrete tasks will be focused on:

• Literature research on graphical model inference of motion plans.
• Toy Task implementation in Python. 
• Implementation of  GMMs, PTSMs and combinations in Python.
• Visualization and analysis of the prediction performance. Definition of suitable evaluation criteria.
• (Optional) Implementation in a realistic driving simulator.
• Analysis and evaluation of the generated data.

Sicheres Autonomes Fahren mit Probabilistischen Neuronalen Netzen

Contact

• LUPA-Electronics GmbH
• Wiebestr. 36-37, 10553, Berlin
• info@lupa-electronics.com
• Web: https://lupa-electronics.com

Wir Menschen sind in der Lage unter widrigen Bedingungen z.B. bei eingeschränkter Sicht, oder bei Störungen komplexe Vorgänge wahrzunehmen, vorherzusagen und innerhalb von wenigen Millisekunden zusammenhängende Entscheidungen zu treffen. Mit dem zunehmenden Grad der Automatisierung steigen auch die Anforderungen an künstliche Systeme. Immer komplexere und größere Datenmengen müssen verarbeitet werden um autonome Entscheidungen zu treffen. Mit gängigen KI Ansätzen stoßen wir aufgrund der konvergierenden Miniaturisierung an Grenzen, die z.B. im Bereich des autonomen Fahrens nicht ausreichen, um ein sicheres autonomes System zu entwickeln.

Ziel dieser Forschung ist es probabilistische Vorhersagemodelle in massiv parallelisierbaren neuronalen Netzen zu implementieren und mit diesen komplexe Entscheidungen Aufgrund erlernter interner Vorhersagemodelle zu treffen. Die neuronalen Modelle verarbeiten hoch dimensionale Daten moderner und innovativer taktiler und visueller Sensoren. Wir testen die neuronalen Vorhersage und Entscheidungsmodelle in humanoiden Roboteranwendungen in dynamischen Umgebungen.

Offende Projekte, Bachelor- und Masterarbeiten​

• Simultaneously predicting multiple driving strategies using probabilistic inference

KI Methoden zur Eruierung optimaler Prozessparameter der Kühllinie (Tempcore-Prozess) 

Offende Projekte, Bachelor- und Masterarbeiten

• Machine Learning for Predicting Yield Strengths.

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.

Hier finden sie den Foliensatz zum Vortrag.

Supervisors: Univ.-Prof. Dr Elmar Rückert,
Vedant Dave, M.Sc. 
Dr. Christoph Sorger und Dr. Luca Moderer
Univ.-Prof. Martin Stockinger (Chair of Metal Forming)
Start date: ASAP from June 2022

Theoretical difficulty: low
Practical difficulty: low

Abstract

In this thesis, the student has the unique opportunity to investigate supervised machine learning methods for predicting yield strengths using probabilistic regression models and deep learning approaches. The thesis is implemented with support of the MSC Software GmbH and the Stahl- und Walzwerk Marienhütte GmbH in Graz.

In the image above and below you see the production line at the Stahl- und Walzwerk Marienhütte GmbH in Graz.

To ensure the high quality standards, frequent ‘yield strength’ measurements are performed. These measurements have resulted in a large dataset which can now be analyzed and used to learn a prediction model.  First tests were promising and the thesis will be very likely a big success. 

The goal of this thesis is to analyze the data and to learn prediction models taking uncertainty estimates into account.

The models will be implemented and tested in Python.

Tentative Work Plan

To achieve our aim, the following concrete tasks will be focused on:

• Literature research on the underlying physical & chemical processes.
• Data analysis, filtering, preprocessing, visualization of the existing data. 
• Implementation of  deep neural networks (Variational Autoencoder), neural processes and GPs in Python. Baseline implementations are existing.
• Visualization and analysis of the prediction performance. An outlier detection and warning system should be implemented.
• (Optional) Implementation of neural time-series models like LSTMs.
• Analysis and evaluation of the provided data.