Ongoing PhD-projects
Context-aware deployment of collaborative robots
The project’s objective is to empower robot end-users by easing the deployment of automation solutions. It investigates active 3D sensing, actionable semantic world models, and Augmented Reality. The project is carried out in collaboration with Universal Robots.
PhD student: Krzysztof Zielinski (Industrial PhD in cooperation with Universal Robots)
Project period: 2022-2024
Supervisor: Mikkel Baun Kjærgaard
Data-driven Assessment of Reliability for Cyber-Physical Production systems (CPPS)
The goal of this doctoral project is to design and develop tools and methodology that learn reliability models from data that is generated in CPPS. The project will incorporate development of Fault Detection and Diagnosis capabilities, along with methodology for learning causal fault models. Simulation methods will be developed and utilized to analyze reliability and availability of CPPS. Developed models and simulations will be utilized as decision support for preventive maintenance scheduling and optimization of CPPS configuration.
PhD student: Jonas Freiderich
Project period: 2020-2023
Principal supervisor: Sanja Lazarova-Molnar
Data-driven agent-based simulation for decision support in parallel trading of pharmaceuticals
The project’s main objective is to develop agent-based modelling and simulation software for predicting parallel trading of pharmaceuticals in EU. Orifarm will use the software to simulate and support complex business decisions on buying and selling pharmaceutical products. Orifarm has operated within parallel trading since 1994 and has collected data on price fluctuations, competing products, originator products, generic products, customer behaviour, marketing authorisations, sourcing countries, sales countries, product in stock, product expiry dates, etc. Orifarm wants to make these complex and essential business decisions in a more digitalized and more data-driven manner, leading to faster, less risky, less subjective (person dependent), and more sound decisions.
PhD student: Ruhollah Jamali
Project period: 2021-2024
Principal supervisor: Sanja Lazarova-Molnar
Software Architecture for Industry 4.0
This doctoral project aims to investigate non-functional requirements within software architecture for production systems in relation to lndustry 4.0. This is done, to some extent, by working with end users and/or technology and/or solution providers in the project. The research will include architecture prototyping, architecture evaluation, functional and non-functional requirements for infrastructure platforms that support smart manufacturing systems as well as implementing an evaluating actual middleware for the systems.
PhD student: Sune Chung Jepsen
Supervisors: Kasper Hallenborg and Torben Worm
Software Engineering of Machine-Learning-based Analytics for IoT Data
The goal of this doctoral project is to design and develop scalable systems for machine-learning-based analytics of IoT data. This project will incorporate developing software technologies based on novel software architectures and semantic technology to enable scalable machine-learning based analytics of IoT data. The technologies will be developed and evaluated for the analysis of IoT data for buildings.
PhD student: Henrik Dyrberg Egemose.
Supervisor: Mikkel Baun Kjærgaard
Tools for Data-driven Analytics of Operation Data from Industrial Cobots
The goal of this doctoral project is to design and develop interactive software tools for data-driven analytics of operation data from collaborative robots. The project will incorporate the development of interactive tools for data exploration and operator feedback based on ubiquitous computing principles and technologies (e.g. augmented reality). The interactive tools will incorporate data-driven models to relate operation data to operator objectives including speed of operation, reliability and energy-efficiency.
PhD Student: Juan Esteban Heredia Mena.
Completed Ph.D.-projects
Framework for verification and evaluation of building energy performance
For more information, please contact:
PhD student: Elena Markoska
Supervisor: Sanja Lazarova-Molnar
Machine Learning-based Modeling for Sensor Data on Occupant Behavior
The goal of this doctoral project is to design and develop machine learning models for sensor data on occupant behavior. The machine learning models will enable estimation and prediction of relevant properties about occupant behavior from the sensor data.
For more information, contact Anooshmita Das.
Privacy Risk Assessment and Mitigation for Sensing Data
The goal of this doctoral project is to design and develop methods and tools for handling the privacy challenges when collecting sensing data about human behavior. In particular the project will consider how to identify the risks and mitigate them. The project will consider a wide-range of sensor data and consider the utility of tools and methods in case studies with a focus on open data.
For more information, contact Jens Hjort Schwee.
Safe Multi-Sensor Software Architecture for Autonomous Vehicles
This project is an Industrial Ph.D.-project in cooperation with CLAAS E-Systems. The project aims to design and develop hard- and software adhering to international safety standards and, in particular, the development of a method for automatically integrating sensor data and automatic program generation to ease the integration and verification of sensors and software. One aspect of particular interest is the detection, handling and assessment of obstacles.
PhD student: Johann Thor Ingibergsson Mogensen
Supervisor: Ulrik Pagh Schultz
Towards a Generic Software Platform for Agricultural Robotics based on Autopoietic Separation of Safety and Functionality
This project is an Industrial Ph.D.-project in cooperation with Conpleks ApS and Kongskilde. The project aims to isolate the core safety-critical parts of the controller into a safety kernel, and to generate the implementation of this safety kernel automatically from a high-level safety specification written in a domain-specific language (DSL) specially designed for the safety experts.
PhD student: Marian Sorin Adams
Supervisor: Ulrik Pagh Schultz
Click here to read more about the project.
Trustworthy Cyber-Physical Systems and Internet of Things within Industry 4.0
This doctoral project aims to provide a model-based design and formal analysis technology for the development of trustworthy Cyber-Physical Systems with advanced IoT features. This project will focus on developing tool-supported methodologies to integrate various verification & validation techniques for modeling safety & security-critical CPS/IoT applications and supporting trusted automation with I4.0.
PhD student: Reza Soltani
Supervisor: Eun-Young Kang