Master's thesis: Data Quality in Autonomous Vehicles

Thesis background
Autonomous vehicles require a number of different sensors to ‘understand’ what is around that vehicle. Common sensors include RGB (visible light) cameras, thermal (heat) cameras, Light Detection and Ranging (LiDAR), Radar Detection and Rangin (Radar) as well as meta information such as the vehicles’  location, time, road systems plus others.  Some information about the project at RI.SE is at https://roadview-project.eu.

In order to obtain the best object detection; other vehicles, pedestrians, cyclists and so on, the data should be of the best quality. From sensors to machine learning algorithms, using the data sources above, we need to ascertain the quality at each step and assign a value (1 poor to 10 excellent). This score or metric we call the Data Readiness Level, or DRL.

Your task
Your tasks will be to look at the data sources we have, camera, RGB and thermal, as well as LiDAR. From the data we will construct the pipelines used by autonomous vehicles to determine the data quality.  A simple example is, if an object cannot be detected, (classically a bounding box), we will look at flaws in the data, (noisy), missing data and so on. Algorithms to perform the object detection will come from the Roadview project or open source sources. Algorithms with high quality data will be implemented in the ROADVIEW vehicle, see below.

Your background
Studying at KTH you should have a good technical background, including machine learning, some mathematics and programming in at least 2 language(s). This could be Python, Java and Rust would be preferable, but other languages will be considered (C++, C). Coding knowledge will be tested on an initial face to face chat.

Terms
Scope: 30 hp
Location: You will be given an office at RISE, Kista and expected to be at this location 2-3 days per week. 6-8 hours per day working.
Benefits: You will be paid 1000 SEK per ECTS, which is tax deductible, paid on satisfactory oral + written thesis defense.
Start time: to be arranged.  

Welcome with your application
For questions and further information regarding this project opportunity contact Ian Marsh, Ph.D, Senior Researcher, ian.marsh@ri.seTel: +46707721536. Last application date: November 30, 2024.