Master Thesis Student - Traffic sign and lane fusion in autonomous driving

30 hp - Traffic sign and lane fusion in autonomous driving: From data to practical implementation

Introduction

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

Background

Modern vehicles use information from cameras and other sensors to understand the surrounding road environment and support Advanced Driver Assistance Systems (ADAS). Reliable information on detected objects such as traffic sign needs to be associated with surrounding lanes and ego vehicles' path. Detections from front looking camera provides objects such as traffic signs, road lanes, and road edges. These objects are provided with various attributes such as positions, curvature rates, and etc. However, currently there are no sufficient models to associate traffic sign with surrounding lanes. A possible solution is to predict the position and geometry of the lanes based on the vehicle's ego-motion, such as yaw-rate, steering-wheel angle, speed, and acceleration. The detected traffic signs can then be associated with the predicted lanes using an algorithmic or probabilistic association method.

Objective
The scope of the thesis is therefore to develop and evaluate a method for associating traffic signs with the correct lanes using only data from the camera.

The thesis shall include:

• analysing the available camera data and defining the requirements for the solution,

• developing or further developing a model for representing and predicting road/lane geometry,

• developing an association method that connects traffic signs to the predicted lanes,

• implementing the solution in C++ or similar programming languages,

• evaluating the accuracy, robustness and limitations of the proposed method using relevant vehicle data.

The input to the solution shall consist exclusively of information from the camera, including traffic signs, lane markings and road edges. The output shall consist of traffic signs associated with the corresponding lanes.

The technical approach is intentionally open. Depending on the initial analysis, the thesis may focus on developing a new road/lane model, further developing an existing solution in road and lane fusion. The work may also include investigating how agentic frameworks can support algorithm development, system design, testing or evaluation. The final choice of approach shall be based on the available data, technical requirements and expected performance.

Thesis description

• Formulating the research questions and planning the thesis work.

• Conducting review/pre-study of the state of the art. This is to find out how traffic signs are associated with lanes in autonomous driving. This stage sets out an early indication of how the rest of the project will continue.

• Develop a model that constructs a lane model where sign traffic signs may be associated with. The model shall be able to predict the ego lane and surrounding lanes based on the available information from the camera and ego-motion.

• Communicate with the project in a bi-weekly meeting with supervisors; one mid-term and final presentation together with the final report is expected.

Education/program/focus

We are looking for a master's student in Engineering physics, Electrical engineering Control and Robotics, Vehicle Engineering, or a related field.

Number of students: 1

Start date for the thesis work: [To be agreed]

Estimated time required: 20 weeks, full time (30 credits)

Contact persons and supervisors

Khashayar Shahrezaei khashayar.shahrezaei@scania.com
Håkan Lidman hakan.x.lidman@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 from - to.

2026-10-13 to 2026-11-23

Requisition ID: 34031

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