Creating a Dataset for F1TENTH Autonomous Racecars (BA/SA/MA/IDP)
- Institute
- Professur für autonome Fahrzeugsysteme
- Type
- Bachelor's Thesis Semester Thesis Master's Thesis
- Content
- experimental theoretical
- Description
Welcome to the AVS (Autonomous Vehicle Systems) lab!
In our lab, we focus on autonomous driving, specifically on the development of software modules for autonomous vehicles, ethical behavior, and the practical application of algorithms in real-world scenarios using real vehicles. To achieve these goals, we have access to autonomous racing cars in 1/10 scale, full-scale autonomous racing cars, and autonomous vehicles for on-road traffic.
In my personal research, I primarily work with the 1/10 scale racing vehicles. One of my main areas of research is the transformation of the typical architecture of an autonomous vehicle with “Perception, Planning and Control” modules towards "End-to-End Learning." End-to-End Learning for autonomous vehicles refers to the vehicle learning directly from sensor data, using a neural network, how to drive safely and efficiently.
Datasets play a crucial role in effectively working with algorithms and testing them out. They provide the foundational data needed for training and evaluating machine learning models. A prime example of such a dataset is KITTI, which is structured to support the development of autonomous driving systems. It includes data from various sensors like cameras and LiDAR, annotated with information about the environment, such as the location of other vehicles, pedestrians, and the drivable road surface. The advantages of datasets like KITTI include their comprehensive nature, allowing researchers to test algorithms on a wide range of scenarios, and their structured format, which facilitates the development and benchmarking of autonomous driving technologies.
Given the importance of specialized datasets in advancing autonomous vehicle research, we aim to create a similar resource for our F1TENTH autonomous racecars. The task involves evaluating existing datasets, conceptualizing a dataset structure that fits the unique needs of F1TENTH vehicles, and then implementing this concept for our real F1Tenth racecars, on our own racetrack with a high-fidelity motion capture system.
- Requirements
The following section provides a list of skills that are helpful or necessary to perform the work. You do not need to possess each of the following skills, as they can all be learned during the thesis process. However, please keep in mind that obtaining them will require additional time-invest.
- Coding experience (Python, C++)
- Framework experience (ROS 1/2, Git)
- Knowledge in Automotive Engineering and Autonomous Driving
- Curious mindset
- Independent and organized work attitude
- Open-minded team player
In return for your time and dedication, we offer you multiple benefits for your academic, professional, and personal journey.
- Fascinating, future-oriented field of research
- Young and dynamic team
- Academic and professional support beyond the thesis
- Organized and structured thesis project
- If suitable, publication as a scientific paper
- Thesis project in German or English
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.
- Possible start
- sofort
- Contact
- Felix Jahncke