Thesis description
The main objective of the thesis will be to optimize the process of generating digital environments by applying automatic machine learning technologies. For example, the concepts of target tracking, object detection and unsupervised learning for automatically annotating and positioning roads, road signs, or obstacles for model generation could be of interest.
AstaZero will provide sensor data from the scanning rig, as well as the opportunity to partake in the day-to-day business of building the digital environments. AstaZero will provide necessary guidance in collaboration with RISE AI department. The tasks of the master thesis student will be:
- Study state-of-the-art methodologies used by OEMs, sensor providers and HD-map creators, as well as get an understanding of the AstaZero sensor platform
- Design and implement algorithms for automatic annotation and 3D object detection and positioning
- Generate 3D objects of roads, traffic signs and other traffic furniture to be included in digital representations of the test track
- Evaluate algorithm performance and compare with manual-driven concepts
- Document the activities and results as a thesis report
The thesis will be conducted at AstaZero R&D in Gothenburg during the spring of 2024 with a start in January. The compensation will be 30,000 SEK upon completion of a high-quality thesis.
Student profile
We are looking for two MSc students with backgrounds in computer science, technical physics, or technical mathematics with knowledge/experience from working with machine learning. Programming skills are a must, preferably in Python with relevant machine learning frameworks, such as PyTorch and/or Tensorflow. Experience with sensor fusion or computer vision is a plus.
Applications should include a brief personal statement, a CV and a list of grades. In the application, make sure to mention previous activities or other projects that you consider relevant for the position.
Suitable applicants will be interviewed as applications are received.