Martin Feick

Doctoral Researcher

Loading...

Research Interests

Virtual RealityMixed realityFabricationTangible User Interfaces3D User InterfacesRobotics
 

Open Thesis Topics

The student will develop a robotic system that navigates through a retail store and takes pictures of the shelves in order to send them to our existing Intelligent Agent. Based on these pictures, a classification will be made. If something is wrong, a Transfer of Control (ToC) will be triggered and the "Remote Expert" will receive a notification. Together with the student, we will decide how this will be implemented. For instance, it could be a dashboard, smartwatch/tablet/smartphone or even a VR/AR interface. Based on the information provided, the expert can now decide whether it is an actual error (which needs to be fixed) or if it was a false alarm -> i.e., s/he gives feedback to the system, so that it learns and improves over time (learning aspect is not part of this thesis). Overall, such a system is called Hybrid Intelligence.

 

Focus

The focus of this thesis lies on the conceptualization and implementation of a robotic framework to support retail robots. Additionally, a small evaluation of the system is expected. 

 

Prerequisites

  • You should have (very) good programming skills.
  • Before applying, please read and understand the concept of Hybrid Intelligence (see page 7/27 [1])
  • Last but not least, be enthusiastic about robots =)! 

 

How to apply

Please send an application to Martin Feick and/or Niko Kleer containing the following information. (if you do not answer every point, your application will not be considered):

  • When you plan to start the thesis
  • When you plan to finish the thesis
  • A short motivational statement (max 0.5 pages) why this topic is interesting for you
  • Your transcript of records and your CV

Many traditional deep learning approaches assume a considerable amount of training data to be available for the initial training of a prediction model. However, there exist cases where the initial model can only be trained using a limited amount of data and is continuously improved over time (e.g. due to the unavailability of data or uncertainty about the total number of classes). As a result, it is necessary to choose a sensible training methodology and model architecture that is able to continuously improve based on the provided feedback.

In this thesis, a deep learning model dedicated towards detecting concrete objects in a retail store (e.g. tennis ball, sprite bottle, apple...) is supposed to be implemented, investigated using multiple approaches, and improved utilizing such feedback.

 

Focus

The focus of this thesis lies in the implementation of a continuously improving deep learning approach for the detection of concrete objects commonly appearing in a retail store. This includes feedback about already considered and unknown classes. The implemented model is supposed to be embedded into a hybrid artificial intelligence-based system that stores basic rules about the spatial arrangement of the products.

 

Prerequisites

  • Make yourself familiar with the following papers: [1], [2], [3]

  • Experience in implementing deep learning models
  • You should have a strong interest in the investigation and fine-tuning of deep learning models
  • Familiarity with object detection models is a plus

 

How to apply

Please send an application to Martin Feick AND Niko Kleer containing the following information. (if you do not answer every point, your application will not be considered):

  • When you plan to start the thesis
  • When you plan to finish the thesis
  • A short motivational statement (max 0.5 pages) why this topic is interesting for you
  • Your transcript of records and your CV
 

Open B.Sc. / M.Sc. Thesis Topics

If you are interested in doing a Bachelor's or Master's thesis in my area of interest, feel free to contact me. Please check the open topics at the top of this page beforehand (if there are any).

 

Projects

CAMELOT

TRACTAT

 

 

Academic Services

Reviewer: TEI'22 WiP, CHI 2022 Full Papers, CSCW 2021 Full papers, CHI 2021 Full Papers, CSCW 2020 Full papers, CHI 2020 Late-Breaking-Reports, INTERACT 2019 Full papers, DIS 2019 Work-In-Progress, CHI 2019 Late-Breaking-Reports, ISS 2018 Posters, SUI 2018 Full papers, CSCW 2018 Posters, HRI 2018 Late-Breaking-Reports

PC: TEI'21 WiP


Publications ()

Loading...