Session
Computer Science and Communication Engineering
Description
This paper presents a comprehensive exploration of the evolving landscape of autonomous vehicle technologies, focusing on both modular and end-to-end learning paradigms, with an emphasis on the significant role of deep learning. Through a combined approach of qualitative analysis and comparative review, the study draws on numerous sources, including research papers, industry documentation and real-world case studies, to assess the impact of deep learning on these paradigms. The initial findings highlight substantial advancements in autonomous vehicle development due to deep learning, particularly in areas like perception, decision making and system adaptability. However, these areas operating independently within modular paradigm systems have their limitations, including issues related to maintenance, interpretation and incomplete information.
Keywords:
deep learning, autonomous, vehicle evolution.
Proceedings Editor
Edmond Hajrizi
ISBN
978-9951-550-95-6
Location
UBT Lipjan, Kosovo
Start Date
28-10-2023 8:00 AM
End Date
29-10-2023 6:00 PM
DOI
10.33107/ubt-ic.2023.270
Recommended Citation
Berisha, Endrit; Kabashi, Faton; Shkurti, Lamir; Sofiu, Vehbi; and Selimaj, Mirlinda, "Deep learning’s impact on autonomous vehicle evolution" (2023). UBT International Conference. 5.
https://knowledgecenter.ubt-uni.net/conference/IC/CS/5
Deep learning’s impact on autonomous vehicle evolution
UBT Lipjan, Kosovo
This paper presents a comprehensive exploration of the evolving landscape of autonomous vehicle technologies, focusing on both modular and end-to-end learning paradigms, with an emphasis on the significant role of deep learning. Through a combined approach of qualitative analysis and comparative review, the study draws on numerous sources, including research papers, industry documentation and real-world case studies, to assess the impact of deep learning on these paradigms. The initial findings highlight substantial advancements in autonomous vehicle development due to deep learning, particularly in areas like perception, decision making and system adaptability. However, these areas operating independently within modular paradigm systems have their limitations, including issues related to maintenance, interpretation and incomplete information.