Die Fraunhofer-Gesellschaft (www.fraunhofer.de) betreibt in Deutschland derzeit 76 Institute und Forschungseinrichtungen und ist die weltweit führende Organisation für anwendungsorientierte Forschung. Rund 30 800 Mitarbeitende erarbeiten das jährliche Forschungsvolumen von 3,0 Milliarden Euro.
In the Professional Service Robots - Outdoor research group we develop autonomous mobile robots for a variety of outdoor applications, such as agriculture and forestry. The focus is on the development of an autonomous outdoor navigation solution as well as the hardware of the robots.
Environment perception is a key component for the interpretation of the surroundings of autonomous robots in outdoor areas. Camera-based solutions have been developed as an approach to visual perception. To this end, semantic segmentation has been researched and improved over the years to effectively understand the scene so that robots can reliably navigate their environment. However, semantic segmentation also brings with it a number of challenges. One major challenge is robust generalisation across multiple domains when trained on a specific source domain.
Was Sie bei uns tun
The aim of this master thesis is therefore to explore the approaches of domain adaptation or domain generalisation and to develop a robust segmentation approach that generalises well across multiple similar domains and not just the source domain on which it was trained. This helps to reduce or possibly even eliminate the need to annotate datasets for each new target domain encountered by the robot. The experiments are conducted in the context of unstructured outdoor environments characterised by uneven terrain and objects and obstacles of different shapes and sizes.
Your tasks include the implementation of robust models for environment interpretation as well as experiments with domain adaption and/or domain generalization for semantic segmentation.
Was Sie mitbringen
- Background in Computer Science, Software Engineering, Electrical Engineering, Mechatronics or similar
- Profound knowledge of C/C++ (Experience with ROS is a plus)
- Profound knowledge in deep learning
- Experience in deep learning frameworks such as Keras/Tensorflow/PyTorch
- Enthusiasm for mobile robotics
- Fluent in English or German
Was Sie erwarten können
- Cutting-edge technology in the field of outdoor mobile robotics
- Hands on with our robots on our own test fields in Stuttgart
- Take on responsibility and freedom to implement your own ideas
- Work with the best students in their discipline
- Familiar atmosphere including Cake Friday
We also offer the possibility of direct entry for excellent graduates.
Wir wertschätzen und fördern die Vielfalt der Kompetenzen unserer Mitarbeitenden und begrüßen daher alle Bewerbungen – unabhängig von Alter, Geschlecht, Nationalität, ethnischer und sozialer Herkunft, Religion, Weltanschauung, Behinderung sowie sexueller Orientierung und Identität. Schwerbehinderte Menschen werden bei gleicher Eignung bevorzugt eingestellt.
Mit ihrer Fokussierung auf zukunftsrelevante Schlüsseltechnologien sowie auf die Verwertung der Ergebnisse in Wirtschaft und Industrie spielt die Fraunhofer-Gesellschaft eine zentrale Rolle im Innovationsprozess. Als Wegweiser und Impulsgeber für innovative Entwicklungen und wissenschaftliche Exzellenz wirkt sie mit an der Gestaltung unserer Gesellschaft und unserer Zukunft.
Haben wir Ihr Interesse geweckt? Dann bewerben Sie sich jetzt online mit Ihren aussagekräftigen Bewerbungsunterlagen. Wir freuen uns darauf, Sie kennenzulernen!
If you are interested, please submit a short letter of motivation on your personal favourite topic listed above, CV, current grade transcript to kevin.bregler@ipa.fraunhofer.de
Fraunhofer-Institut für Produktionstechnik und Automatisierung IPA
Kennziffer: 71223 Bewerbungsfrist:
Stellensegment: Test Engineer, Testing, Computer Science, Electrical Engineering, Engineering, Technology, Bilingual