Deep Learning-supported Scalable Mapping of Urban Environments for Autonomous Vehicles

Institut
Lehrstuhl für Fahrzeugtechnik
Typ
Bachelorarbeit / Semesterarbeit / Masterarbeit /
Inhalt
experimentell / theoretisch /  
Beschreibung

EDGAR, the new research vehicle for autonomous driving at TUM, is currently under construction. At the same time, an overall software stack is being developed that will enable fully autonomous driving in urban environments.

Within the scope of this thesis, a concept for a scalable mapping pipeline is to be developed. Current mapping concepts depend on expensive mapping vehicles that drive around cities and create HD-maps. In this thesis, we want to leverage data from different sources such as vehicle data (LiDAR, camera), satellite images (Open Street Maps, Google Maps, etc.) or available lane-level data (Vermessungsamt) to generate a scalable pipeline for mapping of urban environments.

The developed toolchain is to be integrated into the overall EDGAR workflow based on Autoware.Auto and ROS2.

The following work packages are included in the study work to be assigned:

  • Literature research on existing concepts in research and industry
  • Evaluation and classification of open source apporaches
  • Researching available data sources
  • Development of a toolchain to fuse multiple data sources for map generation
  • Integration of the developed software into the overall software
  • Documentation and visualization of the results

What we offer:

  • A highly motivated team of research associates and students pursuing the common goal of full-stack autonomous driving
  • Work with state-of-the-art hardware: HiL simulator, research vehicle EDDIE, cloud compute power, machine learning, etc.
  • Work with state-of-the-art software tooling: ROS2, Docker, CI/CD, Carla, Unreal Engine, etc.
  • Build industry-relevant knowledge and software engineering skills

 

Voraussetzungen
  • Highly motivated teamplayer
  • Motivation to familiarize yourself with new topics
  • Ideally experience with game engines
  • Ideally programming experience (Python, C++, Git, ROS2)
  • Ideally previous knowledge in the field of autonomous driving or sensor technology
Verwendete Technologien
Git, C++, Python, ROS2, Docker, Autoware
Tags
FTM Studienarbeit, FTM AV, FTM AV Perception, FTM Sauerbeck, FTM Informatik
Möglicher Beginn
sofort
Kontakt
Florian Sauerbeck, M.Sc.
Raum: MW 3508
Tel.: +49 89 289 15342
sauerbeckftm.mw.tum.de
Ausschreibung