bachelor thesis/IDP: Generating Machine Learning data with FreeRTOS and EDF schedulers for an automotive environment
Overview:
Today, hundreds of small applications run in modern cars that ensure roadworthiness with the help of sensors and control logic. These applications have special requirements with regard to real-time capability and reliability.
To ensure these two basic conditions for the software, complex mathematical calculations are performed to determine the feasibility of the tasks. In addition, the final product has to prove the scarcity of occurring errors in field tests.
Since the trend goes towards a consolidation of the software modules on only a few, but powerful, devices, a failure of these or a mutual blocking of the software modules has far-reaching consequences.
In order to counter these increasing problems, the safe and efficient execution of the individual tasks must be guaranteed.
Due to the increasing size and complexity of the code base in vehicles, this can no longer be achieved by mathematical and platform-specific approaches alone. Therefore, it is investigated whether AI-supported approaches, such as machine learning, are suitable.
Machine learning, in turn, requires a solid and reliable data set as a basis, which is the subject of this thesis.
goal of your work:
The goal of this work is to adapt the existing data generator software from the research project MaLSAMi to embedded boards with the operating system FreeRTOS. The COBRA framework is to be used for task generation and the acquired data is to be prepared in such a way that it can be integrated into existing scheduleability analyses for evaluation.
Individual work packages:
Finding suitable task parameters to cover a wide range of tasks
Creating the tasks with COBRA for FreeRTOS
Connection of the task generator software to FreeRTOS
Representation of the obtained raw data with the help of the visualization software Grafana
Preparation of the acquired data for processing in Machine Learning
Your profile:
Knowledge in C , C ++ and Python
Independent and scientifically sound work
Previous lecture knowledge:
Introduction to Computer Architecture (ERA)
Basics - Operating Systems and System Software (IN0009) /or/ Operating Systems and Hardware-related Programming for Games (IN0034)
[optional] Operating systems - L4 microkernels (IN0012, IN2106, IN4258)
Development of a Real-Time Capable Container Management System using Mobile Edge Computing (MEC) Considering Automotive Off-loading Scenarios 07/2021
Hardware-in-the-Loop Test Setup for a Generalistic Approach to Machine-Learning-Based Schedulability Analysis, Master's Thesis, 02/2021
2020:
Toolchain for Dynamic Migration Detection, Planning and Execution at Runtime Using Machine Learning Based Approaches on Embedded Hardware, Master's Thesis, 09/2020