Master- / Bachelor-Thesis: Formal Verification of Automatically Generated Code in Automotive Systems
18.07.2024, Diplomarbeiten, Bachelor- und Masterarbeiten
The Chair of Robotics, Artificial Intelligence and Real-Time Systems offers thesis positions in the area of Large Language Models in the automotive context.
Background | |
As part of the CeCaS research project, a group has been formed to develop a new system architecture for future vehicles, with a focus on autonomous driving. The development of new autonomous vehicles requires a rethinking of systems, software and software engineering to keep up with the growing complexity and implementation of the latest technologies, such as AI-based functions in automotive engineering. To this end, the software we develop is first integrated on an HPC system and then tested on real vehicles. | |
Description | |
A key challenge in developing a centralized system architecture for vehicles is the increasing complexity of software development. Due to the enormous variety of requirements, such as safety requirements like ISO 26262, tools such as automated code generation will have to be used in the future. The emergence of large language models provides an opportunity to implement this theory. General purpose models such as GPT4 or Llama 3 are not yet able to implement the requirements. As a result, there are many open research questions before these approaches can be used in industry. These include, but are not limited to:
| |
Your Tasks | Requirements |
|
|
Kontakt: sven.kirchner@tum.de
More Information
thesis_description |
formal verification of automated code generation,
(Type: application/pdf,
Size: 143.5 kB)
Save attachment
|