Thesis in Controllable High-Definition Map Generation for Traffic Scenario Simulation

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 GmbHis looking forward to your application!

Job Description

Generation of synthetic traffic scenarios is an important part of scaling simulation-based verification of safety-critical components in self-driving vehicles like planner software. This field has seen a multitude of publications within the past 1-2 years. However, most of these methods require a high-definition map (HD map) as input and generate the scenario by placing traffic agents on the provided map. This is a disadvantage since HD maps are expensive and have limited coverage. A few papers have investigated combined map and scenario generation. However, none of these methods have focused on controllability of the generation process.

• During your assignment you will extend HD map generation such that they can be conditioned on external input including natural language.
• You will understand and use state-of-the-art language conditioning for diffusion models and apply these techniques to map generation.

Qualifications

• Education: Bachelor studies in the field of Computer Science, Machine Learning or comparable
• Experience and Knowledge: with Python and deep learning frameworks (PyTorch); experience in autonomous driving research, with diffusion models and using pretrained model repositories (e.g.: hugging face) is a plus
• Personality and Working Practice: you work effectively in interdisciplinary teams, contribute ideas and can communicate complex technical concepts clearly and convincingly, furthermore you can analyse complex data quickly
• Languages: fluent in English

Additional Information

Start: according to prior agreement
Duration: 6 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?
Yu Yao (Functional Department)
+49 711 811 55164

#LI-DNI

Summary

• Type: Full-time
• Function: Research