At a glance
- Tools mentioned
- Python
Master's thesis at Volvo Group: key facts
- Opportunity type
- Master's thesis
- Organization
- Volvo Group
- Location
- Göteborg, Sweden
- Field / discipline
- Data and Analytics
- Application deadline
- 30 Nov 2026
- Last source check
- 20 Nov 2026
About this master's thesis at Volvo Group
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.
Tuning a Car-Trained Vision-Language-Action Model to drive a Truck in a closed-loop simulation through prompting
Location: Volvo Group, Göteborg, Sweden
Time Schedule: Jan 2027 – Jun 2027
NVIDIA's open Alpamayo Vision-Language-Action (VLA) driving models are trained on passenger-car data, yet they accept natural-language navigation guidance and flexible camera inputs. This thesis asks a deliberately pragmatic question: how far can a car-trained VLA model be pushed to drive a truck using only prompting, sensor re-mounting and a light output-correction layer, evaluated in closed-loop L4 simulation (AlpaSim) on a 128 GB unified-memory (UMA) desktop.
A car and a truck navigate traffic very differently: the trailer's swept path is far wider and off-tracks through curves, braking and acceleration distances are longer, larger time gaps are needed, and reaching a mandatory exit often demands several consecutive lane changes within a fixed distance while actively cooperating with surrounding traffic (Nilsson, 2017). The students will explore how to inject this behaviour without touching the weights: (i) language / navigation prompts that instruct earlier signalling, larger gaps, earlier and wider lane changes and lower speeds; (ii) truck-viewpoint camera extrinsics and ego-geometry conditioning; and (iii) a truck kinematic / off-tracking correction layer that makes the model's proposed trajectory feasible for the articulated swept path.
The main objectives of this thesis are:
Prompt-based bootstrapping: Drive a car-trained Alpamayo VLA as-is in closed-loop simulation and design prompting / navigation-guidance strategies that induce truck-like caution (earlier signalling, larger gaps, earlier lane changes, lower speed).
Swept-path feasibility layer: Add truck-viewpoint camera extrinsics, ego-geometry conditioning and a light off-tracking correction on the model output so the car policy respects the articulated swept path.
Closed-loop L4 evaluation (car→truck gap): Evaluate on articulated highway scenarios in AlpaSim – including the multiple-lane-change-to-exit case – and quantify where prompting alone suffices versus where post-training is required.
This project is applied prompt-engineering, robotics and simulation (Python). The work will be carried out at Volvo Group Trucks Technology, Göteborg, and is recommended for two students with a strong background in machine learning and Python.
Contacts and supervision at Volvo Group
Contact persons
Elias Torstensson – Volvo GTT
tel: +46 736669283
mail: torstensson.elias@volvo.com
Leo Laine – Volvo GTT
mail: leo.laine@volvo.com
Morteza Haghir Chehreghani – Chalmers
mail: morteza.chehreghani@chalmers.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.
Trucks Technology & Industrial Division hire team players who are ready to create real customer impact. Our decentralized teams work close to our customers, with speed and autonomy, to build what they truly need.
Join us to collaborate on innovative, sustainable technologies that redefine how we design, build, and deliver value. Bring your curiosity, your expertise, and your collaborative energy, and together, we’ll turn bold ideas into tangible solutions for our customers and contribute to a more sustainable tomorrow.
Before you apply
0 of 4 readyA preparation checklist, saved in this browser on this device without an account. It does not sync across devices. The official posting determines eligibility and required documents.
How to apply
Apply via jobs.volvogroup.com. Check the original listing for required documents and submission instructions.
Source and listing information
Application source: jobs.volvogroup.com. Listing details may change; confirm them on the source site. A source check confirms page availability, not endorsement of the organization.
Report an outdated or incorrect listing