PhD - Data-driven Self-Assessment for Multimodal Perception in Automated Driving
PhD - Data-driven Self-Assessment for Multimodal Perception in Automated Driving
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
Datadriven methods are ubiquitous in todays autonomous systems. An important task of environmental perception is the detection classification and tracking of relevant objects in the scene. We are particularly interested in environment perception using point cloud like data (e.g. lidar) in combination with video.
Todays perception algorithms are based on deep neural networks and usually are trained to equally weight errors for each object in a scene independent of its potential effects on the driving task. However in reality there are objects which are more and less relevant. As a result the trained network which is considered to perform best according to the metrics not necessarily is the best one to be deployed. The goal of this research is to 1) develop new ways of assessing the relevance for all parts of the scene 2) and assessing the current perception performance within these regions. In particular connecting the concepts of relevance and selfassessment to improve the correlation of training metrics and realworld performance will be the main focus.
- You develop novel machine learning approaches for object detection and tracking based on selfsupervision techniques.
- Furthermore you evaluate your algorithms on public benchmark data sets and internal realworld data sets offline and online.
- You contribute to the scientific community with publications on top machine learning and robotics conferences and journals (NIPS ICML ICLR CVPR ICCV IROS or ICRA).
- Take on responsibility and work in an agile and diverse research team with other PhD students and with exchange across several research projects.
Qualifications :
- Education: degree (Master/Diploma) in Computer Science Electrical Engineering Mathematics or related field with excellent academic achievements
- Experience and Knowledge: profound knowledge of machine learning algorithms and principles preferably deep learning and proven programming skills in Python
- Personality and Working Practice: openminded team player who is goaloriented and logical thinking
- Languages: fluent in English (written and spoken) German is a plus
Additional Information :
The PhD project will be carried out in cooperation with and under cosupervision of Dr. Holger Caesar (Assistant Professor at the Intelligent Vehicles Lab TU Delft).
Start: according to prior agreement
Please submit all relevant documents (incl. curriculum vitae motivation letter and certificates).
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 support during your application
Sarah Schneck (Human Resources)
Need further information about the job
Florian Faion (Functional Department)
49 3
Remote Work :
No
Employment Type :
Fulltime
Employment Type
Full-time
