Thesis Work 30 hp - Build a Fast Closed-Loop Simulator on GPU for Autonomous Driving

Introduction: Thesis work is an excellent way to get closer to Scania and build relationships for the future. Many of today's employees began their Scania career with their degree project.

Background: Recent research has shown that GPU-accelerated simulators enable much faster training of driving agents compared to traditional CPU-based methods. Open-source simulators exist, but they may not be mature enough or easy to adapt to our data. We therefore propose building a lightweight but extensible in-house tool, focused on object-level closed-loop simulation, as a foundation for future work.

**Objective: **The thesis project will design and implement a fast closed-loop simulator running on GPU, capable of:

• Efficiently simulating simple object interactions (vehicles, obstacles, etc.).
• Integrating with our data format.
• Providing a clean interface for agent training.

The focus is on creating a minimal, well-engineered prototype that can later be extended.

Potential research questions:

• What level of abstraction is sufficient to achieve both speed and training utility?
• How can GPU execution be structured for scalability and extensibility?
• What trade-offs exist between simulator fidelity and throughput?

Work description

The project will include:

• Surveying existing GPU-based simulators.
• Defining a minimal input/output structure for scenarios.
• Implementing a GPU-first simulator core.
• Evaluating performance and comparing against a CPU baseline.
• Documenting the design and providing guidelines for extensions.

Candidate profile

Master’s student in Computer Science, Engineering Physics, Robotics, or similar, with:

• Solid programming skills (C++ and/or GPU programming experience desirable).
• Interest in simulation, parallel computing, and autonomous systems.

Number of students: 1-2

Start date for the thesis work: January 2026

Estimated time required: 20 weeks (full-time)

Contact persons and supervisors:

oscar.palfelt@scania.com, +46 7 293 784 46

Application: Your application must include a CV, personal letter and transcript of grades

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