Thesis Worker - Autonomous Drive & ADAS

Thesis Worker at Volvo Cars

Welcome to explore the world of Volvo Cars by writing your thesis with us! As a thesis worker in our organization you are supported by a supervisor who follows you during your project. All thesis projects are arranged in business critical areas and therefore you will be able to contribute to our company purpose – providing freedom to move in a safe, sustainable and personal way – from day one!

Background

In the organization Autonomous Drive & Active Safety Functions we design and ensure the best behavior of our functions for our customers. We design, integrate and verify the complete vehicle solution for autonomous cars and active safety functions. We collaborate with some of the most innovative industry partners to reach our future visions of safety, convenience and mobility. We develop functions such as Collision Avoidance, Automatic Parking and Autonomous Driving. 

Our department will lead several master thesis projects starting in the beginning of 2025 and we are now looking for students that are eager to help us explore new ideas in a state-of-the-art platform that will enable delivery of autonomous drive features powered by Artificial Intelligence. We have different topics for master thesis projects in several different areas ranging from systems engineering to machine learning.

With us, you will have a unique chance to make an impact in solving the “engineering problem of the century” of autonomous driving.

Master Thesis projects

The master thesis projects we plan to run during spring 2025 are:
1.    Data-driven analysis of Adaptive Cruise Control (ACC) car-following time gaps for different driving contexts
•    The effectiveness of ACC is significantly influenced by the car-following time gap, which must be carefully calibrated to avoid risks like rear-end collisions or driver dissatisfaction. This study aims to explore various contextual factors affecting this time gap, conducting a thorough literature review and data analysis to recommend optimal ACC settings for different driving scenarios.
 

2.    User-based-insurance; Can we detect dangerous behaviours in e.g overtaking situations
•    Create a model that identifies behavior/situations that triggers accidents, so that an ADAS function can support driver and potentially avoid accidents. By looking at data from accidents, describe the situation ahead of the accident, parametrization of the situation and find the triggering facts that leads to an accident in the scenarios.
 

3.    Create virtual scenarios from field data recordings with low fidelity data with sensor errors. 
•    From selected scenarios derived from customer data create a corresponding virtual scenario that can be used for testing of ADAS/AD functions
 

4.    Robustness of an Autonomous Bike aimed for physical testing at test track
•    Bike target will enable unique test capability of real-life scenarios, from e.g. customer fleet data and accident databases. Part of the FFI project Self driving Bike III, focusing on robustness studies of the target. Collaboration between ASTA and Volvo Cars and Chalmers.
 

5.    User interaction analysis for Acceleration Control Pedal Error and Prevent Acceleration
•    Analyze real driver behavior before and after the Acceleration Control Pedal Error and Prevent Acceleration functions intervenes and develop the HMI interface towards the driver and how it shall interact accordingly. The purpose is to base this new user interaction/HMI for these functions based on real life behavior of the driver and present the optimal user interaction between AD/ADAS system and the driver.
 

6.    Adaptive AI for Low-Speed Collision Avoidance based on driving behavior and environment
•    Develop an adaptive AI that learns from both environmental factors and individual driving behavior to fine-tune collision avoidance responses. For example, the system could adjust sensitivity based on the driver's habits and weather conditions etc.
 

7.    Synthetic Data Generation for vision and lidar based object detection
•    To design and implement a pipeline for Synthetic Data Generation using simulations environments (e.g., Esmini, or Unity), or GenAI tools such as GPT, and evaluate the prototype w.r.t. the available open datasets.
 

8.    Multi Agent Large Language Model as AD/ADAS System Engineer
•    To design and implement system engineering process (e.g., System Theoretic Process) pipeline, to design architecture and specify requirements for a Software Intensive System of Systems (SISoS) such as AD/ADAS.
 

9.    AD/ADAS Scenario Generation by fine-tuning open source Large Language Model
•    To design and implement a multi-agent LLM pipeline using fine tuning techniques and comparing the performance of it w.r.t. the same pipeline using general purpose LLMs.
 

10.    Avoid scratching my rims by steering assistance using onboard vehicle sensors
•    Low speed parking scenarios especially closer to curbs or in parallel parking scenarios is a main challenge for large vehicles. A consequence is that it leads to scratching of rims (being a very expensive part)
•    To leverage the current sensor set and the Park assist camera views for presenting the best use of visual aid and indication of proximity to the drivers. Also, explore the possibility for an actuator assistance (steering assistance) for ensuring the curb hits are curtailed as much as possible.

11.    Automatically activate child lock in tight parking situations
•    Door openings have been a predicted issue during tight situations of parking especially when children inside the vehicle are prone to be excited to have reached their destination and tend to fiddle with the door to open. 
•    To leverage the current sensor set and the Park assist camera views for presenting the best use of visual aid and indication of proximity to the drivers and also to ensure that the door opening alert is issued. The work on this thesis could also entail possibilities of ensuring the conditions that the vehicle doors are in check so as to not let a child be able to fiddle with the door.

In your application make sure to point out what projects you find the most interesting. 

What you´ll bring

You are a highly motivated, self-driven student in a master’s program. You have a genuine interest and curiosity in the subject matter with good analytical skills. You have excellent communication skills, both verbal and written English, and you are a collaborative team player with a preference to do your thesis in a pair. Your academic field is in areas such as Computer Science, Computer Engineering, Data Science, Electrical Engineering or Systems, control and mechatronics.

Duration

•    The work will start in January 2025 (can be discussed).
•    The duration for this thesis work is 20 weeks.
•    30 ECTS (academic credits) if in agreement with your Thesis Advisor in University.
•    Each thesis is to be conducted by 2 students working in pair. If you apply as a pair, make sure both of you submit your applications.

The thesis projects will be conducted on site in our offices in Torslanda, Göteborg.

Be part of the change – apply today!

We’d love to receive and review your application. Selection will be ongoing during the application period, so do not hesitate to send in your application. Attach your CV and personal letter stating your interests within the given area and your thoughts and credentials.

Apply as soon as possible but no later than 2024-10-31.

Please note that applications via email will not be accepted.

If you want more information about the projects or simply learn a bit more about the teams, please reach out to:
Sofia Sköld - Engineering Manager – sofia.skold@volvocars.com

Who are we?

Everything we do starts with people. Our purpose is to provide freedom to move, in a personal, sustainable and safe way. We are committed to simplifying our customers’ lives by offering better technology solutions that improve their impact on the world and bringing the most advanced mobility innovations to protect them, their loved ones and the people around them.

Volvo Cars’ continued success is the result of a collaborative, diverse, and inclusive working environment. The people of Volvo Cars are committed to making a difference in our world. Today, we are one of the most well-known and respected car brands, with over 40,000 employees across the globe. We believe in bringing out the best in each other and harnessing the true power of people. At Volvo Cars your career is designed around your talents and aspirations so you can reach your full potential. Join us on a journey of a lifetime as we create safety, autonomous driving and electrification technologies of tomorrow