Thesis Work:30 credits - Efficient data collection for heavy autonomous systems

30 credits – Efficient data collection for heavy autonomous systems

Introduction
Are you passionate about the cutting-edge technology driving the future of automotive safety and autonomy? This thesis project is an excellent opportunity to learn about autonomous heavy vehicles and contribute to a highly competitive, fast moving industry. 

Background
With autonomous driving technologies rapidly evolving, there is a high demand for heavy vehicle solutions for the transportation industry. Replacing a human driver with a robot that is safe in the traffic requires a lot of data, for everything from training AI models for individual functions to testing the entire system. A critical challenge is to ensure that the robot performs well in a wide range of unusual conditions: various weather conditions, various road types and conditions, various traffic conditions and behaviors of other actors in the traffic. This can be seen as a heavy tailed distribution problem. Since data collection and storage may be resource demanding and expensive, it is critical to have an efficient data collection strategy and tools which help collecting relevant data for training and testing.

Objective
Develop and evaluate a solution for automatic planning of the routes for the data collection fleet. Based on already collected data and on past evaluations of the robot, the sought solution is expected to propose where and when to focus future drives. The goal is proactively steer the distribution of case (scenarios) captured in the data, to maximize the amount of observations of seldom events and reduce the redundancy in the collected data.  

Job description
The thesis can roughly be divided into the following sub-tasks:

• Understand the different factors that may influence the training and testing of an autonomous driving robot.
• Understand the different sources of information in the system which can be used to formulate the focus of future data collection drives.
• To design a software solution which continuously monitors the needs for more data, and maps the needs to concrete proposals for future driving routes.
• The work requires interaction with people working in different domains, from developers of ML solution, to system testing and verification, and safety drivers
  
  

Qualifications

• Currently enrolled in a Master’s program in an engineering field that can be related to this thesis (e.g. Robotics, Computer Science, Mathematics
• Strong mathematical background, especially Statistics and Design of Statistical Experiments
• Strong programming skills (e.g., Python, C++, SQL, APIs)
• Excellent analytical and problem-solving skills, and the ability to work independently
• Able to work in a diverse environment and communicate effectively in English
  
  

Number of students: 1
Start date: January 2026  
Estimated time needed: 20 weeks

Contact person and supervisor
Bogdan Timus, Data Acquisition Lead: 
bogdan.timus@se.traton.com

Application
Enclose transcript of records, as well as CV and cover letter in which you highlight how you fulfill the mentioned qualifications.

A background check might be conducted for this position. We are conducting interviews continuously and may close the recruitment earlier than the day specified.