Thesis work 30hp - Identification of incorrect speed limits in large-scale data sets

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 
With the introduction of the legislation for Intelligent Speed Assistance (speed limit detection systems), all vehicles now need to have a system for determining what the speed limit is where the vehicle is driving. At Scania, this system uses camera information and offboard map data to determine the speed limit for the current road.

In order to improve the functionality, it is important to be able to evaluate the function performance on a large scale to see trends and find existing issues, but this is difficult due to the absence of ground truth data for speed limits, and manual analysis is not feasible for larger datasets.

Objective

The objective for this project is to determine some set of conditions which, when fulfilled, can help indicate that the speed limit displayed by the system is likely incorrect. The goal is to be able to automatically identify scenarios where the speed limit is likely incorrect in the display, in order to narrow down the amount of data which has to be verified manually.

Job description

The work will involve identifying criteria which can be used to suggest the actual speed limit differs from what is shown to the driver, and evaluating these using re-simulations (e.g. in MATLAB/Simulink) of existing datasets to tune these conditions to real-world situations and find how they can be applied in practice.

If time allows, the check for these conditions can then be run on a real data-set, and an estimate of the accuracy can be performed using spot-checking of a subset of the marked locations where the system might be incorrect.

Examples of conditions which might be considered are:

• Comparison of camera and map information
• Own vehicle speed compared to speed limit (if sign says 30km/h but driver is driving 60km/h)
• Speed of surrounding vehicles
• Driver behavior before and after speed limit changes (pressing accelerator/brake pedal)
• Driver reaction to overspeed warnings (i.e. slowing down when acoustic warning plays)
  
  

Education/program/focus

Indicate education, program or focus: Data Science, Behavioural science or similar, with  understanding of statistical concepts. Experience with programming (MATLAB, Python, R) is advantageous.

Number of students: 1

Start date for the thesis work: January 2026

Estimated time required: 6 months

Contact persons and supervisors
Niklas Isaksson, Supervisor, 070-081 48 64, niklas.isaksson@scania.com
Anders Sundström, Hiring manager, 08-5538 61 44, anders.x.sundstrom@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.