1. Theses & HiWi Jobs
    2.  

Autonomy 2.0: Deep End-to-End Machine Learning for Autonomous Vehicles (MA)

Institute
Professur für autonome Fahrzeugsysteme
Type
Master's Thesis /
Content
experimental / theoretical / constructive /  
Description

End-to-End Learning

Welcome to the AVS (Autonomous Vehicle Systems) lab!

In our lab, we focus on autonomous driving, specifically on developing 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 hand-crafted “Perception, Planning and Control” modules towards "End-to-End Learning." End-to-End Learning for autonomous vehicles entails the vehicle's ability to learn how to navigate safely and efficiently directly from sensor data using a single neural network or multiple modules. This approach enables the vehicle to convert raw sensor data into control signals without needing hand-coded rules or manual feature extraction.

F1TENTH vehicles are decked out with top-notch components, including LIDAR, cameras, and advanced onboard computing capabilities, making them perfect for autonomous racing and a wide range of other research applications. These vehicles provide a flexible and open-source platform for researchers to test and implement new algorithms in real-world scenarios. The combination of F1TENTH vehicles and End-to-End Learning is compelling. It allows for thorough simulation and real-world testing, ensuring the models developed are robust, efficient, helpful for research, and ready to race.

Currently, we are looking for students to join us in the following areas:

  • Implementation and benchmarking of various preexisting End-to-End algorithms
  • Designing and/ or implementing novel End-to-End approaches
  • Exploring the usability of reinforcement and imitation learning for F1TENTH vehicles
  • Performance evaluation and improvement of End-to-End frameworks
  • Implementation of different algorithms from the planning and control area into an End-to-End learning framework
Requirements

Requirements:

  • 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

Your Benefits:

  • 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.

Tags
AVS Jahncke
Possible start
sofort
Contact
Felix Jahncke
Phone: +49-89-28910429
felix.jahncketum.de