Thesis Work: 30 credits - Accurate auto-labeling of 3D objects for autonomous driving

Introduction
This thesis will be carried out at the Autonomous Solutions department at Traton, where we develop cutting-edge research solutions for scene perception, prediction and planning for autonomous driving.

A thesis project at Traton is an excellent way of making contacts for your future working life. Many of our current employees began their careers with a thesis project. Furthermore, some theses may lead to publications in computer vision or robotics conferences, which would be a plus for the successful thesis candidate.

Background
Autonomous driving technologies are rapidly evolving and are expected to transform the transportation industry. These technologies often rely on deep learning, for which accurate ground truth labels are essential. Traditionally, these labels have been generated by humans, involving a time-consuming and labor-intensive annotation process; while not necessarily being accurate enough. More recently, several automatic labeling methods have been developed; but the accuracy of these generally remains below that of the human annotation processes.

Objective
Develop and evaluate an auto-labeling method for 3D objects, which produces more accurate 3D boxes than those from typical state-of-the-art autonomous driving datasets and auto-labeling methods.

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

• Understand 3D sensor data (mainly, rotating LiDAR) and relevant autonomous driving datasets (e.g. Argoverse 2 and our proprietary datasets)
• Revisit prior approaches for auto-labeling of 3D objects
• Develop a custom auto-labeling method for 3D objects
• Evaluate quality of the auto-labeling method(s)
    

Qualifications

• Currently enrolled in a Master’s program in an engineering field that can be related to this thesis (e.g. computer vision, robotics, or others)
• Basic understanding of computer vision, machine learning and rotating LiDAR sensors
• Comfortable in programming languages such as Python and/or C++
• Able to work in a diverse environment and communicate effectively in English
• Excellent problem-solving skills and the ability to work independently

Number of students: 1-2
Start date: January or February 2026  
Estimated time needed: 20 weeks

Contact person and supervisor
Alexandre Justo Miro, Industrial PhD Candidate on Perception for Autonomous Driving: 
alexandre.justo.miro@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 date specified.