In this project, you will work on integrating a LiDAR-based 3D Person Detection in the context of ATO (Automatic Train Operation). An important component of ATO is an autonomous door operation that controls the safe exchange of passengers without the need for additional staff at the train platform. To facilitate a robust door control that can operate under conditions where camera based system will fail, a purely LiDAR-based person detection system should be implemented and adapted to the ATO domain.
Your tasks will be to:
- Explore the 3D point cloud data of reenacted scenarios at the train platform
- Integrate state-of-the-art 3D object detection models and examine their applicability for an autonomous door operation
- Extend these models to detect domain specific utilities (e.g. luggage, bikes, mobility aids, etc.)
| Frequency | Weekday | Time | Format / Place | Period |
|---|
The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.