The Institute of Robotics and Mechatronics develops robots that enable people to interact with the environment more efficiently, effectively and safely. The robots are designed to work in environments that are inaccessible or dangerous for humans, but also to support and relieve people at work and in everyday life.
What to expect
The Cognitive Robotics department is closely linked to the topic of artificial intelligence (AI). After all, robots are built to do something - and in order for them to know what to do and how, they need a certain amount of intelligence. Every robot we work with should solve its tasks as efficiently and purposefully as possible. To this end, the department is working on various key AI topics.
Your tasks
- Compile an overview of machine learning methods suitable for learning from 3D mesh and point cloud data
- Familiarise yourself with the existing geometry/trajectory generator and the dataset, as well as the underlying problem
- Pre-processing and, where necessary, extending a generator or the dataset comprising meshes and planning solutions
- Designing and implementing a training pipeline that maps geometry to processing strategies
- Training, evaluating and comparing the trained models with existing planning solutions
Your profil
- Good programming skills in Python
- Experience with a deep learning framework (e.g. PyTorch or TensorFlow)
- A basic understanding of machine learning/deep learning, as well as some experience with 3D data (point clouds, mesh models)
- Familiarity with triangulated mesh models (STL, OBJ) for working with a dataset
- Ability to work independently and strong problem-solving skills
Remuneration is based on qualifications and pay band, up to pay band 5 of the TVöD.
We look forward to getting to know you!
If you have any questions about this position (Vacancy-ID 5901) please contact:
Dr. Freek Stulp
Tel.: +49 8153 28 1848
