Open AccessSelf-Driving Vehicles Using End to End Deep Imitation Learning
Author(s) -
Ashraf Nabil,
Abdel Meguid Kassem
Publication year - 2021
Publication title -
transactions on machine learning and artificial intelligence
Language(s) - English
Resource type - Journals
ISSN - 2054-7390
DOI - 10.14738/tmlai.95.10795
Subject(s) - computer science , automotive industry , end to end principle , artificial intelligence , deep learning , action (physics) , field (mathematics) , artificial neural network , imitation , simulation , human–computer interaction , engineering , psychology , social psychology , physics , mathematics , quantum mechanics , pure mathematics , aerospace engineering
Autonomous Driving is one of the difficult problems faced the automotive applications. Nowadays, it is restricted due to the presence of some laws that prevent cars from being fully autonomous for the fear of accidents occurrence. Researchers try to improve the accuracy and safety of their models with the aim of having a strong push against these restricted Laws.
Autonomous driving is a sought-after solution which isn’t easily solved by classical approaches. Deep Learning is considered as a strong Artificial Intelligence paradigm which can teach machines how to behave in difficult situations. It proved its success in many differ domains, but it still has sometime in the automotive applications.
The presented work will use the end-to-end deep machine learning field in order to reach to our goal of having Full Autonomous Driving Vehicle that can behave correctly in different scenarios. CARLA simulator will be used to learn and test the deep neural networks. Results will show not only performance on CARLA’s simulator as an end-to-end solution for autonomous driving, but also how the same approach can be used on one of the most popular real datasets of automotive that includes camera images with the corresponding driver’s control action.