Thesis Work 15hp-30hp - Automated optimized testing of vehicle software

A thesis project at Scania is an excellent way of making contacts for your future working life. Many of our current employees started their career with a thesis project.

Background:
To verify and validate new or updated software quickly and often, we need to use a combination of verification approaches such as vehicle testing, hardware-in-the-loop, and virtualization (also called software-in-the-loop). Regardless of the approach, testing of physical systems or in simulation is cost intensive. Thus, to make the verification as efficient as possible, we need firstly, to automate as much as possible, and secondly, to ensure that the test object is as minimal as possible. 

Target:
This project aims at developing new methods for selection of test object and test data. This means, for example, that we need to select: an optimal set of configurations to fully cover all possible configurations; a minimal set of test cases and input data to cover all possible behaviour; minimal set of software parts (i.e. test objects) to cover the whole software. An important aim is to perform testing by using as minimal amount of computational resources as possible.
   Since testing in physical vehicles is very expensive, an important new approach is virtualized testing. This means we run vehicles in computer simulations where roads and its environment are also simulated. The roads are built up by road segments aiming to cover as many driving scenarios as possible.
   A variety of approaches should be investigated. It is, for example, interesting to study formal methods, generative AI, and data-driven approaches. The thesis project should preferably implement the proposed methods in prototype tools.

 
 Example of assignments:

- Automatic detection of Vehicle Function variability in a centralized system architecture.
- A tool to automatically select a vehicle configuration to maximize variant coverage.
- Variant independent Vehicle Function Tests.
- Vehicle Function test coverage based on testing on multiple architectural levels.
- Automatic generation and maintenance of Vehicle Function Test scripts using AI.
- Automated testing of Vehicle Function degradation based on machine learning.
- Automated verification of Vehicle Functions during driving scenarios in virtual or real vehicles.
- Automated detection of issues during driving scenarios in virtual or real vehicles.
- Data-driven approach for test planning and coverage analysis.  
- Verification of autonomous vehicles.
- How to reduce fault analysis time in test data from CAN-networks.
- Optimize testing by only testing the minimal part of the software needed for sufficient coverage.

Education:
Type of project: MSc or BSc
Education: computer science, electrical engineering, engineering physics or similar.

Contact persons:
Jonas Westman, Senior researcher, Scania, jonas.westman@scania.com
Mattias Nyberg, Adj. prof, KTH / Research Manager, Scania,  mattias.nyberg@scania.com

Number of students: 2-5
Time:10 or 20 weeks, full time 40 hours per week
Start: Jan 2025
Credits: 15hp and 30hp
 
Application:
Enclose 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.