Many manipulation systems are built from reusable primitives such as “approach,” “grasp,” and “insert,” rather than one monolithic policy. In practice, these primitives are often stitched together directly in code, which makes iteration slow and debugging difficult. In this project, you will build a lightweight graph-based interface that lets users compose such primitives into a high-level plan, execute the plan in simulation, and monitor what is happening online (e.g., which primitive is active, where transitions fail). The tool should integrate with our existing, mature codebase and support practical features such as parameterized nodes, transition conditions, simple failure/recovery logic, and clear visualization. A minimal GUI is desirable but not strictly required, the priority is a clean architecture and a tool we can keep using in future research. Req: Python engineering skills and motivation to build a maintainable tool. UI experience is a plus. No robotics expertise is needed.
| Frequency | Weekday | Time | Format / Place | Period | |
|---|---|---|---|---|---|
| by appointment | n.V. | 13.04.-24.07.2026 |
| Module | Course | Requirements | |
|---|---|---|---|
| 39-M-Inf-P Project Projekt | Projekt | Ungraded examination
|
Student information |
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.