Level: Master Thesis
The main focus of this thesis is the support of evaluation of sensor placement proposals as they arise in selecting a suitable configuration of one or more camera, lidar or radar sensors, with a focus on a stationary (infrastructure) setting in the context of Connected and Automated Mobility (CAM). A suitable simulation environment (like SVL or CARLA) should be used to generate sample data for different sensor configurations that allow for a reasonable evaluation of its effectiveness.
The overall goal is to find well suited positions (and orientation) for a sensor such as a camera, lidar or radar, based on the physical layout of its environment and the sensor’s characteristics, such as FoV or resolution.
Main Research Focus
- Literature research on similar work and related performance metric
- Selection or development of suitable metrics for fitness evaluation of individual sensor placement proposals
- Application and evaluation of those metrics in a sample scenario
- Basic programming skills (for manipulating simulation scenarios and possibly extending sensor implementation)
- Experience with simulations in general beneficial
- Any background in computer vision, with specific sensor data (lidar, radar, cameras) or their mathematical models would be helpful
- SVL (open-source, development suspended in Jan. 2022. https://www.svlsimulator.com/ | https://github.com/lgsvl/simulator)
- CARLA (open-source, https://carla.org/ | https://github.com/carla-simulator)
- GAZEBO (open-source, http://gazebosim.org/ | https://github.com/osrf/gazebo)
- MORSE (open-source, discontinued. http://morse-simulator.github.io/ | https://github.com/morse-simulator/morse | https://www.openrobots.org/morse/)
Curious? Get in touch.
We are looking forward to receiving your application. Please include your current transcript of records and Curriculum vitae in tabular form; all documents in PDF format.