The project in five facts.
Challenge, approach and results.
The diploma thesis compares the effectiveness of two popular simulation platforms, CARLA and Udacity, with emphasis on beginners in this field, with the aim of training artificial intelligence models for autonomous vehicle applications. The usability of Jupyter Notebook and Google Colab, two well-known programming environments, for creating and testing autonomous driving algorithms is also evaluated. The main objectives of the thesis are to determine which development environments and simulation tools are best for inexperienced developers and how to optimise self-learning algorithms to improve the efficiency and accuracy of artificial intelligence models in autonomous driving conditions. The research results show that the more realistic but more demanding CARLA simulator is more suitable for experienced users and thorough simulations, whilst the beginner-friendly Udacity simulator is more accessible due to its simpler interface and lower processing requirements.
Problem
The diploma thesis compares the effectiveness of two popular simulation platforms, CARLA and Udacity, with emphasis on beginners in this field, with the aim of training artificial intelligence models for autonomous vehicle applications.
Solution and Method
The usability of Jupyter Notebook and Google Colab, two well-known programming environments, for creating and testing autonomous driving algorithms is also evaluated.
Results
The main objectives of the thesis are to determine which development environments and simulation tools are best for inexperienced developers and how to optimise self-learning algorithms to improve the efficiency and accuracy of artificial intelligence models in autonomous driving conditions. The research results show that the more realistic but more demanding CARLA simulator is more suitable for experienced users and thorough simulations, whilst the beginner-friendly Udacity simulator is more accessible due to its simpler interface and lower processing requirements.
Similarly, Google Colab offers new users an environment that is easy to use and resource-efficient, as it provides reliable computing resources using cloud infrastructure without the need to install high-performance hardware locally. On the other hand, Jupyter Notebook is considered more useful for experienced developers who require more freedom and control in setting up their development environment. Furthermore, the research confirms that increasing the number of iterations in the self-learning algorithm cycle improves the efficiency of artificial intelligence models to a certain extent.
However, beyond this point, further iterations lead to diminishing returns, as they increase resource consumption without bringing significant improvement in learning outcomes. These observations enhance understanding of the trade-off between learning efficiency and computational efficiency during the training of AV models. Taking all of the above into account, the diploma thesis offers insightful and useful advice that will help both beginners and experienced users in selecting the best tools and development procedures for audiovisual content.
In addition, it provides suggestions for future studies aimed at improving the efficiency and robustness of artificial intelligence models in autonomous driving.
Module, programme and stories.
Your diploma project for a real company.
A diploma thesis at Academia solves a challenge from a company – often the one where you do your 800 hours of placement. Read about the Programsko inženirstvo module or book a consultation.