Enhancement and Optimization of a Simulation Environment for Autonomous Driving

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

Situation:

Developments in the field of autonomous driving are progressing rapidly. The first autonomous vehicles are already driving thousands of kilometers on test tracks without major intervention by a human driver. Autonomous driving is still a long way from being ready for series production. As one of the biggest megatrends, autonomous driving is being researched with great intensity worldwide. To this end, TUM is working with several departments to develop software for its own road vehicle, which will be equipped with sensors for autonomous driving.

Project:

In this project, the current LiDAR sensor models in the simulation environment CARLA (based on Unreal Engine 4) shall be enhanced and optimized to realistically map the characteristics of the real sensor. This can include the work packages optimizing and working on the ray-tracing physics, the sensor configurations and additional topics such as integration of motion blur, point cloud fusion and point-wise timestamps.

In the first step of this project, environment and sensor modelling for autonomous vehicle simulation are reviewed. Based on the research, the current simulation suite is expanded by adding additional sensor models. The sensor models and overall integrity of the simulation is verified by the simulation of the full software stack on the simulator.

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

  • Literature research on existing sensor models and environment models in CARLA
  • Evaluation and classification of current sensor models
  • Enhancement of LiDAR models for generation of realistic point clouds in simulation
  • Creating a digital sensor twin of the research vehicle EDGAR
  • 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, CARLA
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