Master thesis - Efficient World Representations for End-to-End Autonomous Driving
Scania GroupRekommenderat
Sammanfattning
This Master's thesis opportunity at TRATON Group R&D focuses on developing efficient world representations for end-to-end autonomous driving, specifically for heavy-duty vehicles. The project, part of the EGoPT initiative, aims to enhance real-time trajectory planning by compressing multimodal sensor data while preserving critical information. The work will involve literature review, model implementation, and performance analysis, with a start date in January 2027 and a duration of 20 weeks. TheJobbet i korthet
Arbetstid
heltid/deltid
Det här erbjuder vi
Opportunity to work closely with TRATON Group R&D and build future relationships.Gain hands-on experience in a cutting-edge research project.Access to public datasets and emerging truck-focused resources.
Ansök senast: Öppet tillsvidare
Publicerad: 2026-10-30
Beskrivning
30 hp - Efficient World Representations for End-to-End Autonomous Driving
Introduction
A Master's thesis is an excellent way to get closer to TRATON Group R&D and build relationships for the future. In this thesis, you will contribute to EGoPT, a new industrial research project on World Models for Autonomous Driving.
Background
Modern autonomous vehicles generate large amounts of sensor data from cameras, lidar, radar, and vehicle-state signals. Processing all this information at full resolution and over long temporal histories can exceed the computational budget available for real-time planning. Compressing it too aggressively, however, may remove information that is important for planning or safety.
The VINNOVA-FFI EGoPT project investigates how compact, task-aligned representations of multimodal sensor data can support real-time trajectory planning for autonomous heavy-duty vehicles. Current end-to-end driving methods and evaluation tools are mainly developed for passenger cars, while trucks introduce additional constraints related to vehicle size, articulation, load-dependent dynamics, braking distance, and computational resources.
The thesis will primarily use public datasets, open-source models, simulation, and planning benchmarks and emerging truck-focused resources.
Objective
The thesis will investigate an initial research question within EGoPT. Possible directions include:
Job description
During the thesis period, you will:
The expected outcome is a reproducible model baseline, evaluation method, or experimental framework that can support future research within EGoPT.
Education/program/focus
You are pursuing a Master's degree in computer science, machine learning, robotics, engineering physics, electrical engineering, or a related technical field.
A suitable candidate should have strong programming skills, preferably in Python and PyTorch; knowledge of machine learning and deep learning; an interest in autonomous driving, computer vision, transformers, representation learning, or simulation; and motivation to combine scientific investigation with practical implementation.
Number of students: 1
Start date for the thesis work: January 2027
Estimated time required: 20 weeks, full-time (30 hp)
Location: TRATON Group R&D, Södertälje
Contact persons and supervisors
Industrial supervisors: Rafael Valencia Carreño, rafael.valencia.carreno@scania.com
Thomas Gustafsson, thomas.gustafsson@scania.com
Hiring managers: Maria Linnarsson, maria.linnarsson@scania.com, Magnus Granström, magnus.granstrom@scania.com
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.
Publication date:
1.10.2026 - 30.11.2026 (applications evaluated continuously)
Requisition ID: 33765
Number of Openings: 1.0
Part-time / Full-time: Full-time
Permanent / Temporary: Temporary
Country / Region: SE
Location(s):
Södertälje, SE, 151 38
Required Travel: 0%
Workplace: Hybrid
Introduction
A Master's thesis is an excellent way to get closer to TRATON Group R&D and build relationships for the future. In this thesis, you will contribute to EGoPT, a new industrial research project on World Models for Autonomous Driving.
Background
Modern autonomous vehicles generate large amounts of sensor data from cameras, lidar, radar, and vehicle-state signals. Processing all this information at full resolution and over long temporal histories can exceed the computational budget available for real-time planning. Compressing it too aggressively, however, may remove information that is important for planning or safety.
The VINNOVA-FFI EGoPT project investigates how compact, task-aligned representations of multimodal sensor data can support real-time trajectory planning for autonomous heavy-duty vehicles. Current end-to-end driving methods and evaluation tools are mainly developed for passenger cars, while trucks introduce additional constraints related to vehicle size, articulation, load-dependent dynamics, braking distance, and computational resources.
The thesis will primarily use public datasets, open-source models, simulation, and planning benchmarks and emerging truck-focused resources.
Objective
The thesis will investigate an initial research question within EGoPT. Possible directions include:
- Efficient spatial or temporal representations: compress sensor observations or scene history while preserving information needed for planning.
- Adaptive representations: allocate a limited token or compute budget to the cameras, regions, or information most relevant to the current driving situation.
- Safety-aware compression: evaluate whether compact representations preserve safety-critical information.
- Heavy-duty vehicle generalization and evaluation: adapt learned planners to different vehicle configurations, or evaluate and extend public benchmarks with articulated or configuration-dependent constraints.
Job description
During the thesis period, you will:
- Review relevant literature and help define a focused research question.
- Set up or reproduce an open-source autonomous-driving model, simulator, or benchmark.
- Implement and evaluate a method, benchmark extension, or experimental framework.
- Analyze relevant trade-offs in planning performance, safety, generalization, latency, memory, or computational cost.
- Document the work, present the results, and write the final thesis report.
The expected outcome is a reproducible model baseline, evaluation method, or experimental framework that can support future research within EGoPT.
Education/program/focus
You are pursuing a Master's degree in computer science, machine learning, robotics, engineering physics, electrical engineering, or a related technical field.
A suitable candidate should have strong programming skills, preferably in Python and PyTorch; knowledge of machine learning and deep learning; an interest in autonomous driving, computer vision, transformers, representation learning, or simulation; and motivation to combine scientific investigation with practical implementation.
Number of students: 1
Start date for the thesis work: January 2027
Estimated time required: 20 weeks, full-time (30 hp)
Location: TRATON Group R&D, Södertälje
Contact persons and supervisors
Industrial supervisors: Rafael Valencia Carreño, rafael.valencia.carreno@scania.com
Thomas Gustafsson, thomas.gustafsson@scania.com
Hiring managers: Maria Linnarsson, maria.linnarsson@scania.com, Magnus Granström, magnus.granstrom@scania.com
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.
Publication date:
1.10.2026 - 30.11.2026 (applications evaluated continuously)
Requisition ID: 33765
Number of Openings: 1.0
Part-time / Full-time: Full-time
Permanent / Temporary: Temporary
Country / Region: SE
Location(s):
Södertälje, SE, 151 38
Required Travel: 0%
Workplace: Hybrid
Ansök till tjänsten
Master thesis - Efficient World Representations for End-to-End Autonomous Driving
Rekommenderat
OM FÖRETAGET
Scania Group
