LiDAR Simulation, Fusion and Processing for Autonomous Vehicles
- Lehrstuhl für Fahrzeugtechnik
- Bachelorarbeit Semesterarbeit Masterarbeit
- experimentell theoretisch
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.
This thesis focuses on the LiDAR pipeline. To be able to generate point clouds in simulation, existing open-source LiDAR models are to be extended to the fetures of the EDGAR LiDARs. Different physical effects are to be evaluated and implemented if feasible. Motion blur coming from the time difference between single scans while the ego vehicle is moving is to be implemented.
In the second step, a pipeline for de-skewing (removing the motion blur) and fusion of the LiDARs is to be conceptualized, implemented and evaluated. Spatial calibration is to be taken into account as well as temporal time differences and compensations. The goal of the pipeline is a single point cloud with data from all LiDARs and without inconsistencies.
The final sofware is to be evaluated with real-world data.
Open source algorithms will be evaluated, assessed and compared. Subsequently, a toolchain will be developed and implemented to enable the best possible simulation and fusion of the LiDAR sensors that are being mounted on EDGAR.
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 algorithms for simulation, de-skewing and fusion
- Implementation of LiDAR models for generation of realistic point clouds in simulation
- Implementation of a point cloud de-skewing and fusion pipeline
- 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
- Highly motivated teamplayer
- Motivation to familiarize yourself with new topics
- 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
- FTM Studienarbeit, FTM AV, FTM AV Perception, FTM Sauerbeck, FTM Informatik
- Möglicher Beginn
Florian Sauerbeck, M.Sc.
Raum: MW 3508
Tel.: +49 89 289 15342