THESIS WORKER - OPTIMAL SUSPENSION TARGETS

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! About this opportunity – Background Are you interested in training AI engineer that can tune the suspension system? Here is an opportunity for you to train your own AI engineer.
We have prepared a learning framework that combines Reinforcement learning and VI-Carrealtime simulation environment.
We want the RL to interact with the simulation result to learn the suspension tuning methodologies.
You will also have the opportunity test your AI engineer by driving the auto-tuned suspension in Real-time simulator.
Scope of the thesis work The suspension target is used to guide the construction of the suspension system.
We focus on kinematic properties such as toe and camber behaviours.
However, how suspension kinematics influence the overall vehicle behaviours, such as cornering stability is sometimes challenging to understand.
Without sufficient knowledge, suspension tuning can be difficult.
You might meet some requirements but fail to meet others, especially in high-dimensional cases.
Envisioned solution RL algorithms are one way to accumulate tuning knowledge by interacting with a simulation environment.
You can use popular RL frameworks such as Q-learning, actor-critic methods, or even your own customized algorithm.
We have prepared a template for you! We also have an algorithm that generates a drivable suspension property file from given suspension targets.
This allows you to test your RL algorithm not only by examining training curves but also by driving the vehicle yourself! Objective •    Test different RL learning algorithms •    Hyper parameter tuning •    Improve the training efficiency •    Optional looking into the possibility involved subjective driving experience into learning algorithm Deliverables •    The best learning algorithm you can find (we have a baseline that you need to outperform) Limitations The topic focus on suspension only.
Other subsystems like tire, steering system assume unchanged.
Suspension kinematics is the prior concern, and suspension compliance is an option.
What you´ll bring •    Strong Python skills •    Experience with reinforcement learning (familiarity with popular frameworks is needed) •    Knowledge of suspension kinematics is a plus •    Experience with VI-CarRealTime product is a plus •    From Volvo Car corporation, you will receive copilot license to enhance your coding! Duration •    The work will start in to be discussed •    The duration for this thesis work is 20 weeks.
•    30 ECTS (academic credits) if in agreement with your Thesis Advisor in University •    This thesis is to be conducted by 2 Students working in pair.
Be part of the change – apply today! Applications should include  your CV and a brief personal letter stating your interests within the given area and your thoughts and credentials.
We are continuously screening applications and will fill the position as soon as we find a good match.
So do not hesitate to send in your application.
Apply as soon as possible but no later than    Please note that due to GDPR applications via email will not be accepted.
If you want more information about the project or simply learn a bit more about the team, please reach out to.
Manager, Jenny Berglund at Supervisor, Yansong Huang at Volvo Cars - Driving change together Volvo Cars’ success is the result of a collaborative, diverse, and inclusive working environment.
Today, we are one of the most well-known and respected car brands, with around employees across the globe.
At Volvo Cars, your career is designed around your skills and aspirations, allowing you to reach your fullest potential.