In the AVS lab, we focus on pushing the boundaries of autonomous driving by developing advanced software modules, ensuring ethical behavior in autonomous systems, and testing algorithms in real-world scenarios using real vehicles. We work with autonomous vehicles ranging from 1/10th scale race cars to full-scale autonomous road vehicles, providing a unique and hands-on research environment.
This thesis focuses on developing a differentiable motion planner for F1TENTH autonomous race cars. Currently, our vehicles follow a predefined raceline without considering feasibility checks or potential collisions. The new motion planner will sample feasible trajectories, evaluate them based on a cost function that considers factors like collision risk, control effort, and driving speed, and select the optimal trajectory for safe and efficient driving.
Differentiable motion planners are unique because they allow gradient-based optimization, integrating the motion planning process with machine learning algorithms. This enables real-time optimization, resulting in more adaptive and efficient driving strategies compared to traditional methods. In this thesis, you will apply these state-of-the-art techniques to autonomous racing, bridging the gap between theoretical algorithms and practical application.
Key Work Packages:
Requirements:
Your Benefits:
The thesis can be started immediately. Please send your resume, recent grade report, and a brief description of your fields of interest and why you are the perfect fit for this thesis to felix.jahncketum.de.
I am always on the lookout for motivated and committed students and look forward to receiving your application so we can work together on the mobility of tomorrow.