Theses

The DAI-Labor offers possible theses for Bachelor of Science (BSc) / Master of Science (MSc) for several of its research foci. For further information and advice on the individual topics, please contact the respective supervisor.

Print Loading print view...

Level: MA/(BA)

In the context of future mobility a testbed for development applications is necessary. Different problems such as intermodal vehicle routing, parking or speed recommendations systems have traffic as a common factor. A gym-like environment based on a popular traffic macro-simulation should be extended so that experiments with different methods and problems can be conducted. For the method reinforcement learning or other optimization approaches are possible.

Tasks:

The focus of the proposed thesis can lay in one or multiple topics such as:

  • Multi-agent reinforcement learning methods ( eg. scheduling/routing of delivery robots)
  • Regression methods ( eg. traffic or parking demand forecasting) 
  • Simulation and modeling of traffic based on SUMO and other co-simulations

Requirements:

  • Very good understanding of machine learning through experience and coursework. (at least 2 good completed courses and some practical experience with e.g. Keras/Tensorflow, pytorch, FLAX …) 
  • Practical experience in co-working on Python/C++ projects. Be able to write good documentation and using tests
  • The motivation to contribute to a scientific publication 

References:

RL Intro Book: Sutton, Richard S., and Andrew G. Barto. Reinforcement learning: An introduction. MIT press, 2018.

RL Intro Lecture: https://www.youtube.com/watch?v=2pWv7GOvuf0&list=PLqYmG7hTraZDM-OYHWgPebj2MfCFzFObQ

Traffic Marco-Simulation: https://www.eclipse.org/sumo/

Autonomous Driving Simulation: https://carla.org/

Traffic Forecasting Challenge: https://www.iarai.ac.at/traffic4cast/

Vehicle Routing Challenge: https://euro-neurips-vrp-2022.challenges.ortec.com/

Interested?

Send your application with a convincing set of documents to

Patrick Grzywok

patrick.grzywok@gt-arc.com

research area

Machine Learning
supervisor / Contact person
Patrick Grzywok
Plattform Economy and Autonomous Mobility Solutions: Data-Driven Network Effects
Emerging Technologies for Data-Driven Network Effects within Digitalized Urban Infrastructures and towards Autonomous Driving Applications
Print Loading print view...

Level: Master Thesis

Emerging Technologies for Data-Driven Network Effects within Digitalized Urban Infrastructures and towards Autonomous Driving Applications

Description

Mobility is changing. Technological innovations introduced to the market, the digitalization of infrastructures and services, or social challenges such as the COVID-19 pandemic are influencing the way we understand and experience mobility. By providing novel services like MaaS and carpooling, autonomous vehicles are set to take the centre stage for new mobility. Given this development, even more disruptive technologies and use cases will emerge. V2X connectivity and smart infrastructure leverage services in the area of multimodal transport, traffic, maps & navigation, parking, safety and payment. Those innovations create room for novel HMI solutions, new mobility solution providers and many other potential actors. 

The DAI-Lab is researching and developing solutions that could meet the requirements of an cooperative, connected and automated mobility landscape (CCAM). An essential focus is to understand the role and effects that appear from data collected in digitalized infrastructures and autonomous vehicles. These are linked to mobility services offered in these environments.

Given the concept of Platform Economy (PE), it is very interesting to investigate data-driven network effects (DDNE). DDNE occurs when a product improves significantly by shared data generated by its users, and is often enhanced by AI technologies. This thesis’ target is to conduct research on such effects in the context of PE in CCAM use cases.

Main Research Focus

  • Conduct literature research and create an overview on possible interplay of cooperative and connected autonomous mobility framework (CCAM) and platform economy (PE) approaches.
  • Choose several related use cases, identify their relevant stakeholders and visualise the interconnectivity between all instances.
  • Analyse the impact of chosen use cases in terms of data-driven network effects (DDNE) and develop a framework/tool that provides answers to the following questions:
    • What are DDNE in the context of digitalized urban infrastructures and autonomous driving? 
    • How can digitised urban infrastructure enrich the data landscape qualitatively?
    • What properties do the different actors and entities show (autonomous vehicle, pedestrians, cyclists, Road-Side-Units, etc.)?
    • Given the use cases, what data is needed, what data is helpful? How can different data be gathered and prioritized for the given use cases? 
    • What challenges occur in the context of gathering the data? How can they be solved?
    • What role does data security regulation and customer’s demand in Germany/EU play? How could developments in this domain inhibit or amplify DDNE?
  • Conclude with a discussion on benefits and disadvantages of possible future scenarios.

Prerequisites

  • General knowledge on state-of-the-art autonomous mobility solutions and the platform economy concept.
  • Preferably successfully completed university courses in the area of platform economy.
  • High motivation of discovering novel use cases within the autonomous mobility framework and DDNE.
  • Good grades in relevant fields are beneficial.

References

Curious? Get in Touch.

We are looking forward to receiving your application. Please include your current transcript of records and Curriculum vitae in tabular form; all documents in PDF format.

Contact person
Marc Guerreiro Augusto
marc.augusto@dai-labor.de
Plattform Economy and Autonomous Mobility Solutions: Effects on Urban Environment
Explaining the Effects of Autonomous Driving in Platform-based Urban Mobility on Public Space, Road Infrastructure and MaaS Solutions
Print Loading print view...

Level: Master Thesis

Explaining the Effects of Autonomous Driving in Platform-based Urban Mobility on Public Space, Road Infrastructure and MaaS Solutions

Description

In recent years, the development of cooperative and connected automated mobility solutions (CCAM) has experienced an upswing. Platform based services such as Mobility-as-a-service (MaaS), Car-as-a-service (CaaS), car pooling, ride hailing, and many more are leading to various changes on how mobility is perceived. Today, the question arises of how holistic approaches can be designed to deploy CCAM use cases into real-world environments. 

Thus, an essential focus is to understand the role and effects that appear from data collected in digitalized infrastructures and autonomous vehicles. Digital platforms acquire large amounts of data from various sources, which are aggregated and then made available for use in a wide variety of products and services. Consequently, the availability of this data shapes the success of mobility services offered in CCAM-environments. Given this foundation, several effects on the city landscape are possible. In fact, an important research topic is the effect of (steered) data on public space, road infrastructure and MaaS solutions.

Main Research Focus

  • Conduct literature research and create an overview on possible interplay of cooperative and connected autonomous mobility framework (CCAM) and platform economy (PE) approaches.
  • Contribute your own profound ideas.
  • Choose several CCAM use cases, identify relevant Stakeholders and visualise the interconnectivity between all instances.
  • Analyse the impact of chosen use cases in terms of the city landscape and develop a framework/tool that provides answers to the following questions:
    • To what extent can MaaS solutions improve efficiency for end users?
    • How do CCAM solutions impact land use? 
    • How could CCAM and MaaS alter the design of urban space?
    • How does CCAM impact CO2 emissions and km travelled per day?
    • What further parameters need to be taken into account?
  • Conclude a recommendation how to steer CCAM development towards achieving a desirable city of the future

Prerequisites

  • General knowledge on state-of-the-art autonomous mobility solutions and the platform economy concept.
  • Preferably successfully completed university courses in the area of business modelling and platform economy.
  • You show a high degree of motivation in assessing CCAM impacts on several dimensions in order to shape the desirable city of the future. 
  • Good grades in relevant fields are beneficial.

References

Curious? Get in Touch.

We are looking forward to receiving your application. Please include your current transcript of records and Curriculum vitae in tabular form; all documents in PDF format.

Contact person
Marc Guerreiro Augusto
marc.augusto@dai-labor.de
Plattform Economy and Autonomous Mobility Solutions: Business Model Development
Autonomous Mobility Data Platform: Value Proposition, Governance and Business Model within the Platform Economy Framework
Print Loading print view...

Level: Master Thesis

Autonomous Mobility Data Platform: Value Proposition, Governance and Business Model within the Platform Economy Framework

Description

Observing our changing mobility landscape, new innovative solutions within the field of autonomous driving are emerging everyday. Platform based services such as Mobility-as-a-service (MaaS), Car-as-a-service (CaaS), car pooling, ride hailing, and many more are leading to various changes on how mobility is perceived. As vehicles are often no longer seen as something to be owned, but more as a service, related platforms are getting more popular everyday. 

This leads to a new set of challenges to involved actors, such as OEMs, start ups, public transport and governments. Namely, all stakeholders active in the mobility domain have to adapt to changing needs of the end users to make the travel experience safe and pleasant. At the same time, challenges such as sustainability (e.g. carbon footprint) need to be taken into consideration. 

Given this status quo, the necessity of novel business models is a logical consequence. However, due to the large variety of important components, the partly hard-to-reform landscape and the diversity of involved stakeholders makes this an interesting challenge of research. Thus, this thesis provides the opportunity of discovering what is needed for a deployment of novel applications and services within the area of autonomous mobility.

Main Research Focus

  • Conduct literature research and create an overview on possible interplay of cooperative and connected autonomous mobility framework (CCAM) and platform economy (PE) approaches.
  • Contribute your own profound ideas.
  • Choose several PE use cases, identify relevant Stakeholders and visualise the interconnectivity between all instances.
  • Assess what each selected case’s value proposition is, and how they could be integrated into a business model, e.g. by starting with a Business Model Canvas (BMC).
  • Develop a description of the encountered landscape, and discuss possible future scenarios including its pros and cons within the most relevant fields.
  • Bonus: include concepts for data and infrastructure security.

Prerequisites

  • General knowledge on state-of-the-art autonomous mobility solutions and the platform economy concept.
  • Preferably successfully completed university courses in the area of business modelling and platform economy.
  • High motivation of discovering novel use cases within the autonomous mobility framework.
  • Good grades in relevant fields are beneficial.

References

Curious? Get in Touch.

We are looking forward to receive your application. Please include your current transcript of records and Curriculum vitae in tabular form; all documents in PDF format.

Contact person
Marc Guerreiro Augusto
marc.augusto@dai-labor.de
Plattform Economy and Autonomous Mobility Solutions: Key Characteristics
Modeling and Mapping Key Characteristics of Autonomous Mobility Solutions within the Platform Economy Framework
Print Loading print view...

Level: Master Thesis

Modeling and Mapping Key Characteristics of Autonomous Mobility Solutions within the Platform Economy Framework

Descriptions

Autonomous mobility solutions are gradually making their way to both urban and rural infrastructures, paving a new path towards innovative solutions. By providing novel services like MaaS and carpooling, autonomous vehicles are set to take the center stage for new mobility. Given this development, even more disruptive technologies and use cases will emerge. With the smart urban infrastructure consisting of a wide variety of sensors and fast interconnectivity (5G), diverse and abundant data sources will be available for research, practice and policy maker. V2X connectivity and smart infrastructure leverage services in the area of multimodal transport, traffic, maps & navigation, parking, safety and payment. Those innovations create room for novel HMI solutions, new mobility solution providers and many other potential actors. 

Thus, connecting those diverse stakeholders involved in those mobility solutions will also play an important role for a successful transformation. Namely. it will be vital for platform-based mobility solution providers to understand the needs of not only the end user, but also those of other similar providers. A mapping of different platform solution providers may create new paradigms and solutions within mobility. 

In order to demonstrate the practicability of such approaches, a systematic review encapsulating different emerging disruptive technologies is desired, including use cases and regulations that emerge with cooperative, connected and automated mobility (CCAM). Analyzing key features and modeling processes of selected use cases such as vehicle on demand, smart parking or GLOSA services, by including their functioning within respective stakeholders involved will be a key to develop and embed autonomous mobility solutions in our everyday lives.

Main Research Focus

  • Conduct literature research and create an overview on possible interplay of cooperative and connected  autonomous mobility framework (CCAM) and platform economy (PE) approaches
  • Contribute your own profound ideas
  • Choose several use cases and identify relevant Stakeholders
  • Create component-, process- and data landscape, assess their interconnectivity and relate them to important actors
  • Visualize how the platform economy principles (network externalities, platform, services, etc.) are mapped to the selected use cases, e.g. via BPMN process landscaping
  • Conclude with a recommendation on how the status quo can be used and transformed towards deploying the selected use cases

Prerequisites

  • Successfully completed university courses on state-of-the-art autonomous mobility solutions, data platforms and the platform economy concept
  • High degree of motivation regarding the discovery of novel use cases within the autonomous mobility framework
  • Knowledge in process development is beneficial
  • Very good grades in relevant fields are desired

References

Curious? Get in Touch.

We are looking forward to receiving your application. Please include your current transcript of records and Curriculum vitae in tabular form; all documents in PDF format.

Contact person
Marc Guerreiro Augusto
marc.augusto@dai-labor.de
Plattform Economy and Autonomous Mobility Solutions: Data Manifesto
Conception of a Data Manifesto for AI-driven Autonomous Mobility Platforms in the Platform Economy Framework
Print Loading print view...

Level: Master Thesis

Conception of a Data Manifesto for AI-driven Autonomous Mobility Platforms in the Platform Economy Framework

Description

With the rise of new digital mobility platforms, innovative services will be introduced. Platform-based services such as Mobility-as-a-service (MaaS), Car-as-a-service (CaaS), carpooling, ride-hailing, autonomous driving applications and many more are leading to various changes in how mobility is perceived. These mobility solutions are data-driven. Requirements for data acquisition, processing and use thus need to be understood and described in accordance with data laws which in turn may allow or limit the use of methods and models, respectively.

When building such solutions, it is important to deeply think about how to use data offered on platforms. This connects to detailing what kind of data is created and used, as well as explicitly not used. Addressing questions such as network effects produced with these platforms and describing the intertwining of provided data, models and services are key aspects for creating a data manifesto. 

This research focuses on building an understanding of a data manifesto for a data mobility platform in the realm of autonomous mobility. The work aims to shed light on the state-of-the-art described in the literature, restrictions other platforms self-impose, discussion on the virtues of certain self-imposed restrictions for a platform that is based in EU or Germany based on today's social discourse, and proposes a data manifesto which considers elaborated properties for allowing autonomous and platform-driven mobility solutions to unfold.

Main Research Focus

  • Conduct Research on Platform Economy fundamentals, such as Digital Platforms, Network-Effects, Multi-sided markets, etc.
  • Transfer the theory to the context of autonomous mobility by assessing the concepts of Mobility as a Service and others Use Cases.
  • Also look at data protections laws and developments in the relevant areas.
  • Conclude a manifesto that clarifies the target of data acquisition and processing

Prerequisites

  • Strong motivation to conduct research on a interdisciplinary level between Platform Economy and Autonomous Mobility
  • High interest in digital platforms, data regulation and in that context the impact of data organization on different stakeholders
  • Successfully completed university courses on state-of-the-art autonomous mobility solutions are a plus
  • Very good grades in relevant fields are desired

References

Curious? Get in touch.

We are looking forward to receive your application. Please include your current transcript of records and Curriculum vitae in tabular form; all documents in PDF format.

Contact person
Marc Guerreiro Augusto
marc.augusto@dai-labor.de
Print Loading print view...

Time Series such as sensor signals, speech or stock prices generally vary in length and speed. To cope with such temporal variations, warping distances such as Dynamic Time Warping (DTW) are often used. In recent years, the problem of finding an average of time series under DTW has been faced and many properties such as the existence, uniqueness, complexity, exact solutions and heuristic solutions have been studied. In practice, a DTW average may not 'look like' an averagely shaped curve of the sample time series. This is reasoned in the nature of the DTW distance itself. Therefore, several alternative warping distances have been proposed. However, as of today, they have rarely been used for computing average curves. The goal of this thesis it to explore the behavior of different warping distances for time series averaging. One challenge is to evaluate such averages quantitatively and qualitatively.

Prerequisites

  • Good programming skills (Python, Matlab or Java)
  • Solid basics in Analysis and Linear Algebra, ideally experience with gradient descent optimizers
  • Interest in theoretically oriented research

Literature

  • Schultz, D., & Jain, B. (2018). Nonsmooth analysis and subgradient methods for averaging in dynamic time warping spaces. Pattern Recognition74, 340-358.
  • Petitjean, F., Ketterlin, A., & Gançarski, P. (2011). A global averaging method for dynamic time warping, with applications to clustering. Pattern recognition44(3), 678-693.
  • Zhao, J., & Itti, L. (2018). shapedtw: Shape dynamic time warping. Pattern Recognition74, 171-184.
  • Keogh, E. J., & Pazzani, M. J. (2001, April). Derivative dynamic time warping. In Proceedings of the 2001 SIAM international conference on data mining (pp. 1-11). Society for Industrial and Applied Mathematics.
  • Cuturi, M., & Blondel, M. (2017, July). Soft-dtw: a differentiable loss function for time-series. In International Conference on Machine Learning (pp. 894-903). PMLR.
  • Marteau, P. F. (2008). Time warp edit distance with stiffness adjustment for time series matching. IEEE transactions on pattern analysis and machine intelligence31(2), 306-318.
  • And own literature research
supervisor / Contact person
M.Sc. David Schultz
david.schultz@dai-labor.de
Print Loading print view...

Geodesically convex optimization has recently attracted attention from the machine learning community due to the realization that some important problems that appear to be non-convex at first glance, are geodesically convex, if we introduce a suitable differential structure and a metric. In this thesis, the student is expected to conduct an empirical study on the performance of geodesic convex optimization methods for applications in machine learning, compared to the state-of-the-art non-convex optimization techniques.

Prerequisites

  • English language
  • successfully completed courses Machine Learning I and II
  • Programming skills in Python
  • Knowledge in Differential Geometry and Convex Optimisation
supervisor / Contact person
Print Loading print view...

The Electrical Grid plays an important role in our everyday life. As to bring the new technologies in place and facilitate the energy transition, Simulations have been conducted to assess the feasibility of new developments. Today we do not only talk about the stability, reliability and efficiency of the grid but also its resilience or the ability to Anticipate, React, Adapt, and Recover. Therefore, to increase the resilience of today’s power grid, simulation and software assessments are needed to couple the multidomain inter-dependencies of the Cyber-Physical Human Systems (CPHS). Extreme weather events have been occurring more frequently around the world. These events demonstrated how vulnerable the distribution grid is.

Well-placed and coordinated enhancements, such as system hardening and redundancy, orchestrated microgrids, and advanced fault detection, can reduce the number of outages that could occur due to High Impact Low Probability (HILP) events. We offer a Bachelor / Master Thesis in the field of Power Grid Simulation and integration of Distributed Energy Resources. The thesis will encapsulated the different stages from Model Development to Vulnerability Assessment, and Power Flow Optimization related to Distributed Energy Resources in Power Networks.

Requirements

  • Studies in the fields of technical informatics, control engineering, automation, electrical engineering, energy engineering, or similar
  • Good knowledge and practical experience in python, co-simulation paradigms, ArcGIS, Simulink or Power Factory
  • Teamwork and Goal Oriented
  • Interest in Renewable Energy Topics and Automation Technology
  • Task Oriented and Independent Learning

research area

Energy Data Analytics
supervisor / Contact person
M.Sc. Izgh Hadachi
izgh.hadachi@dai-labor.de