Thesis in Controllable High-Definition Map Generation for Traffic Scenario Simulation
Thesis in Controllable High-Definition Map Generation for Traffic Scenario Simulation
Employer Active
Job Alert
You will be updated with latest job alerts via email
Share
Job Alert
You will be updated with latest job alerts via email
Job Description
Generation of synthetic traffic scenarios is an important part of scaling simulationbased verification of safetycritical components in selfdriving vehicles like planner software. This field has seen a multitude of publications within the past 12 years. However most of these methods require a highdefinition 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 stateoftheart language conditioning for diffusion models and apply these techniques to map generation.
Qualifications :
- Education: Master 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 4
#LIDNI
Remote Work :
No
Employment Type :
Fulltime
Employment Type
Full-time
