City:  Erlangen
Date:  Sep 24, 2022

Master Thesis - Deep Learning based TOA Error Regression with Uncertainty Estimation

The Fraunhofer-Gesellschaft (www.fraunhofer.com) currently operates 76 institutes and research institutions throughout Germany and is the world’s leading applied research organization. Around 30 000 employees work with an annual research budget of 2.9 billion euros. 

Background. Time of arrival (TOA) based radio systems are widely used for indoor localization, achieving accuracies in the centimeter range. However, their positioning performance is restricted due to bandwidth limitations and challenging propagation conditions. Complex environments like production lines can deteriorate the positioning performance dramatically: Absorptions, reflections, and scattering cause wrong TOA estimations, which lead to localization errors. Therefore neural network based approaches have been investigated to mitigate the TOA estimation errors considering environment-specific properties. Often, the channel impulse response (CIR) is used, as the CIR contains rich spatial information which help localization algorithms to improve the positioning accuracy e.g. by none-line-of-sight (NLOS) identification, error mitigation, or TOA estimation.

 

Challenges. However, data-driven methods often have a poor generalization towards data-distribution shifts (in our case changed or new environments), which cause model violations and thus wrong predictions. Also, ambiguities in the data, caused, e.g., due to bandwidth limitations and NLOS cause a high uncertainty, which is often not considered in neural networks. To enable a reliable and robust localization performance, the uncertainty estimation of data-driven algorithms is therefore an important step.

 

Goals. The main goal of the work is to implement a TOA error mitigation approach employing channel impulse responses of radio systems. You will investigate and implement state of the art uncertainty estimation approaches like Monte Carlo dropout, deep ensembles or Bayesian neural networks to evaluate the reliability of the estimated errors.

 

What you will do

The proposed work consists of the following parts:

•    Generation of synthetic channel impulse responses using QUADRIGA simulator.
•    Implementation of TOA error regression model using state of the art neural network architectures.
•    Investigation and Implementation of methods for uncertainty quantification in neural networks.
•    Benchmarking and reporting of error regression and uncertainty quantification for different radio propagation condition.

 

What you bring to the table

•    You are currently studying Computer Science, Information and Communication technology or related disciplines.
•    You are interested in Deep learning, Uncertainty Estimation and Localization.
•    You have knowledge in Machine Learning, Deep Learning as well as in deep learning frameworks like Pytorch, Keras. Knowledge in communication technologies is a plus.

 

What you can expect

•    Flexible working hours
•    Open and friendly team work
•    Varied tasks with room for creativity
•    Exciting seminars and events 
•    Networking with scientists
•    Active contribution in applied research
•    Interesting an innovative projects

The thesis will be assigned and carried out in accordance with the rules of your university. For this reason, please discuss the thesis with a professor who can advise you over the course of the project.

 

We value and promote the diversity of our employees' skills and therefore welcome all applications - regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity. 

 

With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process. As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future. 

 

Interested? Apply online now (cover letter, CV, transcripts). We look forward to getting to know you!

 

Fraunhofer Institute for Integrated Circuits IIS 

www.iis.fraunhofer.de 

 

Requisition Number: 13766                Application Deadline: none              Location: Nuremberg

 


Job Segment: Computer Science, Training, Learning, Technology, Research, Education, Human Resources