Master thesis: Synthetic Data Generation for Camera-Based Perception in AMRs

Transport is at the core of modern society. Imagine using your expertise to shape sustainable transport and infrastructure solutions for the future. If you seek to make a difference on a global scale, working with next-gen technologies and the sharpest collaborative teams, then we could be a perfect match. 

Background of thesis project
At Volvo Trucks’ final assembly plants, battery-electric, internal combustion, and hydrogen-powered trucks are built on a single production line handling roughly 25,000 unique parts. Since it is infeasible to store all components directly at the line, a flexible internal logistics system is used to deliver materials just in time. To manage this, Volvo employs autonomous mobile robots (AMRs) coordinated by a centralized, cloud-based control system. These robots operate in dynamic, human-shared environments and rely on ceiling-mounted cameras for perception. Using machine learning models for semantic segmentation, the system identifies obstacles to enable collision-free navigation. However, the performance of such models depends on access to large, labeled datasets, which are expensive and time-consuming to collect in real-world conditions.

This thesis will investigate simulation as a scalable alternative to real-world data for training perception models for camera-based AMRs. The work will explore the use of recent advancements in 3D scene reconstruction, such as Gaussian Splatting, combined with modern simulation engines (e.g., Unreal Engine or Unity) to generate realistic environments from which image data and ground-truth labels can be extracted. A key challenge is the sim-to-real gap, which hinders the transfer of models trained in simulation to real-world deployments. To mitigate this, the project is conducted in collaboration with Repli5, a Gothenburg-based startup specialized in generating high-fidelity synthetic data for computer vision.

Suitable background
We are looking for MSc students with a background in one of the following programmes (or similar):
•    Systems, Control and Mechatronics
•    Complex Adaptive Systems
•    Data Science and AI
•    Other related engineering or computer science disciplines

Required Skills: Proficiency in machine learning and Python programming

Meriting Experience: Familiarity with computer vision and/or simulation environments (e.g., Unreal Engine, Unity, Gazebo, CARLA, etc.)

Thesis project tasks
-    Integrate 3D Gaussian Splatting with modern simulation engines (e.g., Unreal or Unity)
-    Generate synthetic datasets (images and labels) from the simulated scenes
-    Train ML models for semantic segmentation and/or object detection using the synthetic data
-    Evaluate the trained models on real-world data from Volvo’s factory
-    Formulate design guidelines for synthetic dataset construction tailored to perception in AMR logistics environments.

Thesis Level
Master

Language
Thesis is to be written in English.

Starting date
Latest 19th of January 2026 (possibility to be at Volvo, partly)

Number of students
Two (2)

Last day to apply: 2025-11-09

Tutor
Knut Åkesson, Chalmers,  knut.akesson@chalmers.se  (Supervisor)
Erik Brorsson, Volvo GTO, Manufacturing Solutions erik.brorsson@volvo.com

Contact
Kristofer Bengtsson, Volvo Group Trucks Operations kristofer.bengtsson@volvo.com

References
AMR system at Volvo: https://www.youtube.com/watch?v=DA7lKiCdkCc

We value your data privacy and therefore do not accept applications via mail. 

Who we are and what we believe in 
We are committed to shaping the future landscape of efficient, safe, and sustainable transport solutions. Fulfilling our mission creates countless career opportunities for talents across the group’s leading brands and entities.

Applying to this job offers you the opportunity to join Volvo Group. Every day, you will be working with some of the sharpest and most creative brains in our field to be able to leave our society in better shape for the next generation. ​We are passionate about what we do, and we thrive on teamwork. ​We are almost 100,000 people united around the world by a culture of care, inclusiveness, and empowerment. 

Group Trucks Operations encompasses all production of the Group’s manufacturing of Volvo, Renault and Mack trucks, as well as engines and transmissions. We also orchestrate the spare parts distribution for Volvo Group’s customers globally and design, operate and optimize logistics and supply chains for all brands. We count 30,000 employees at 30 plants and 50 distribution centers across the globe. Our global footprint offers an opportunity for an international career in a state-of-the-art industrial environment, where continuous improvement is the foundation. As our planet is facing great challenges, we - one of the largest industrial organizations in the world - stand at the forefront of innovation. We are ready to rise to the challenge. Would you like to join us?