Master thesis: Automated LiDAR-based city-scale map calibration

Join our Team
About this opportunity:
City-scale 2.5/3D maps are a key component in radio propagation modelling. These maps give a coarse model of the physical reality in formats like USDC, glTF and Mitsuba XML, that primarily represent urban structures like buildings and streets. Maps are often outdated, miss details, and contain errors, especially regarding complex structures and vertical dimensions of the buildings.
These inaccuracies impact radio propagation modeling, which prevents their use for the task at hand. Automated calibration of city-scale maps is a challenging multi-disciplinary research topic. Purpose of this thesis project is to bring automation in city-scale maps based on existing LiDAR data. The selected students will perform research on top of existing Ericsson Research solutions.
What you will do:
Develop and evaluate automated methods for calibrating city-scale 2.5D/3D maps using existing LiDAR data.
Identify and characterize differences between map geometry and observed data, including missing or inaccurate buildings, building heights, complex structures and street layouts.
Build prototypes that align LiDAR-derived evidence with map geometry and assess the accuracy, robustness and limitations of the resulting maps.
Work with 3D city-map representations and formats such as USDC, glTF and Mitsuba XML, and consider how improved maps support radio-propagation modelling.
Explore relevant computer-vision, machine-learning and geometric approaches; design experimental solutions, analyse results and share findings with the research team.
Extend existing Ericsson Research solutions, documenting your implementation and recommendations for further development.
The skills you bring:
You are pursuing a Master's degree (or equivalent) in computer science, electrical engineering, geomatics, robotics, computer vision or a related field, and are looking for a thesis project.
You can turn research ideas into working software and code independently.
You are comfortable with Python and at least one additional programming language, such as C++, JavaScript or another relevant language.
You can work with data, design experiments, evaluate results and explain technical decisions clearly.
You are comfortable using modern AI-assisted research and programming tools thoughtfully, while being able to understand, debug, validate and take ownership of the code you produce.Experience with 2D or 3D map formats, geometric registration, machine learning or radio-propagation modelling is an advantage.
Familiarity with at least one relevant area, such as computer vision, LiDAR or point-cloud processing, satellite imagery or remote sensing, geospatial data, 3D graphics, rendering or 3D modelling is an advantage.
Why join Ericsson?At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply? Click Here to find all you need to know about what our typical hiring process looks like.Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.
Primary country and city: Sweden (SE) || Stockholm
Req ID: 791815