Master Thesis Student - Machine Learning Driver Model
Göteborg, SE, 417 15
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
Are you ready to kickstart your career with one of the most innovative and renowned automotive companies in the world? We are thrilled to announce an incredible Master thesis opportunity at Volvo GTT starting in the beginning of year 2026.
Transport solutions are a vital part of the modern lifestyle we live in today. At Volvo Group we are committed to driving prosperity by improving our technologies. The future of autonomous and driver-assist systems hinges on their ability to operate safely, efficiently, and comfortably behaving in ways that are intuitive and human-like. For heavy-duty trucks, this challenge is magnified by complex dynamics, significant variations in mass, and the high impact of driving style on fuel consumption.
Our department Customer Features Verification focuses on various features, including vehicle fuel/energy economy, CO₂ emission, performance and drivability. We are hands-on when conducting physical tests, performing cutting-edge data analysis and complete vehicle simulations to evaluate these features.
About the thesis work
This project aims to develop a sophisticated, two-tier intelligent driver model that leverages machine learning to learn complex vehicle behavior from data and emulate nuanced, human-like driving strategies. The project builds upon an existing validated longitudinal vehicle dynamics model in Simulink, replacing the current physics-based controller with an advanced machine learning approach.
The driver model will consist of:
- Driver Intent Model (Behavioral Layer): A high-level module that learns human-like driving decisions, mapping driving context (speed error, distance to stop, lead vehicle behavior, road grade preview) to smooth, realistic acceleration profiles using imitation learning techniques.
- Pedal Mapper (Control Layer): A low-level module acting as a learned inverse model of the truck’s powertrain and brake dynamics, translating desired acceleration into precise pedal commands. This will be implemented using MLP-based (Multi-Layer Perceptron) neural networks with online adaptation capability through Recursive Least Squares (RLS).
- Safety & Comfort Supervisor: A supervisory layer enforcing critical constraints including jerk limits, pedal rate limits, and Time-to-Collision (TTC) guards.
By utilizing imitation learning, neural networks, and online system identification techniques, this intelligent driver model will improve vehicle control performance, enhance human-like driving behavior, and contribute to safer autonomous driving solutions.
A critical component of this thesis is the full integration and comprehensive validation of the developed driver model into the existing Simulink vehicle dynamics environment. You will systematically evaluate the model’s performance against a comprehensive set of KPIs, including control performance (RMSE of acceleration tracking, stop position accuracy), human-likeness (jerk profiles, headway distribution vs. human data), safety & plausibility (pedal command overlap, TTC violations in car-following scenarios), and efficiency metrics (proxy for energy consumption). This integration and validation work will ensure the model’s readiness for real-world deployment in autonomous and driver-assist systems.
The MSc. thesis proposal has a scope of 30 ECTS credits (suitable for one student).
Project start: January/February 2025.
Physical location: Volvo GTT (Group Truck Technology), Lundby, Göteborg
About you
We expect that you are finishing your studies in Automotive Engineering, Control Systems, Mechanical Engineering or similar. You should have excellent proficiency in MATLAB & Simulink and be familiar with Python. A solid theoretical foundation in Control Theory (e.g., PID, state-space models), and good understanding of fundamental Machine Learning concepts (Supervised Learning, Neural Networks) are required.
Background in vehicle dynamics, system identification (e.g., RLS), or reinforcement learning is a plus. You should be comfortable implementing algorithms from first principles in code.
Ready for the next move?
If you want to make a real impact in your future career, the transportation business is where you want to be. We look forward to meeting you.
Renan Sasahara Hernandes (Industrial Supervisor), Volvo Group Trucks Technology (GTT),
Staffan Luong (Industrial Supervisor), Volvo Group Trucks Technology (GTT),
Email: renan.hernandes@volvo.com, staffan.luong@volvo.com
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 Technology are seeking talents to help design sustainable transportation solutions for the future. As part of our team, you’ll help us by engineering exciting next-gen technologies and contribute to projects that determine new, sustainable solutions. Bring your love of developing systems, working collaboratively, and your advanced skills to a place where you can make an impact. Join our design shift that leaves society in good shape for the next generation.