Master Thesis in Conditional Prediction for Autonomous Driving

Company Description

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference.

The Robert Bosch GmbH is looking forward to your application!

Job Description

Trajectory prediction is one of the key elements of the autonomous driving stack. Despite a strong research and industry focus, there are many problems to be solved, such as understanding complex social interactions between different agents, efficiently incorporating rich topological information, predicting multimodal trajectories, and achieving reliable long-term predictions. In addressing these challenges, Deep Learning (DL) algorithms have shown promising results over classical robotics approaches, especially for the urban driving use case. Within DL-based trajectory prediction, an important issue is the ability to explicitly condition a model on ground truth information. This can range from incorporating prior knowledge such as traffic rules or driveable areas, to conditioning outputs on known destinations of other road users. In this context, the future actions of traffic participants are influenced by the actions of the ego (autonomous vehicle). Thus, a trajectory predictor should be able to condition its outputs on known ego goals without causing overconfidence in the downstream planner.

• This thesis deals with the topic of vehicle trajectory prediction with a focus on conditional prediction. During your Master thesis, you will develop a general solution for conditional prediction based on existing trajectory prediction solutions.
• You will develop and evaluate the conditional predictor with a view to downstream planner integration.
• Last but not least, you will carry out the practical implementation in Python and PyTorch.

Qualifications

• Education: Master studies in the field of Computer Science, Electrical Engineering or comparable with a focus on robotics or machine learning and very good grades during studies
• Experience and Knowledge: experience of reading research papers and of coding for machine learning applications, in Python with PyTorch, TensorFlow or JAX
• Personality and Working Practice: eager to learn and contribute to research
• Enthusiasm: ready to dive into a topic at the forefront of machine learning research and autonomous driving applications
• Languages: fluent in English

Additional Information

Start: according to prior agreement
Duration: 9 months

Requirement for this thesis is the enrollment at university. Please attach your CV, transcript of records, examination regulations and if indicated a valid work and residence permit.

Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore, we welcome all applications, regardless of gender, age, disability, religion, ethnic origin or sexual identity.

Need further information about the job?
Faris Janjos (Functional Department)
+49 711 811 49109

#LI-DNI