CEVT is an innovation and development company at the forefront of mobility. Modular development, ground-breaking virtual engineering, software development and continuous innovation enable us to deliver world-class technology. Today we deliver to different automotive brands in the Geely family such as Geely Auto, Volvo Cars, and Lynk & Co and are based at Lindholmen in Gothenburg.
Master Thesis Project
Title: Learning-Based Optimal Control for Trajectory Tracking
The goal of this thesis is to develop and evaluate a learning-based optimal control strategy to control a vehicle's motion to track a trajectory. Figure 1 gives an overview of the control strategy. The motion controller shall receive a motion trajectory as input and determine the control setpoints for the vehicle to track a given trajectory. A learning strategy shall be developed to improve the vehicle model by considering the unmodeled vehicle dynamics and environmental noise.
Figure 1: Overview of the control strategy
The developed control strategy shall be verified in a simulation environment. The developed learning-based optimal control strategy shall be benchmarked against a traditional optimal control strategy without the learning element to evaluate the performance, computation, and robustness of the developed full control solution.
The overall aim of the thesis work is to:
- Investigate different machine learning strategies that can be integrated into the optimal control problem formulation for improving system model accuracy and/or cost function.
- Implement and verify one (or few) chosen control strategy in a simulation environment.
- Benchmark the developed control strategy with a traditional optimal control strategy with respect to performance, computation load, and robustness.
- Possibility to test the developed solution in a HIL environment.
- Master student in Mechatronics/Control/Automotive engineering or similar.
- Knowledge in Modelling, Simulation, Machine Learning and Optimal Control techniques.
- Basic knowledge in MATLAB and Simulink.
- Basic knowledge in C/C++ and Python programming.
- Ability to take own initiatives and work independently.
Number of students: 2, please apply with CV and cover letter.
Starting date: January 2022. The duration of the thesis work is 20 weeks
For more information please contact:
Teodor Husmark, Software Function Developer, +46738621757, firstname.lastname@example.org
Last application date: 2021-10-29
Apply today. We will perform ongoing selection during the application period. We look forward to hearing from you!
Please note that due to GDPR regulations we can only accept applications sent through the recruitment system, not via email or other channels.