RT Journal Article
T1 Deep Learning for Safe Autonomous Driving: 												Current Challenges and Future Directions
A1 Muhammad, Khan
A1 Ullah, Amin
A1 Lloret, Jaime
A1 Ser, Javier Del
A1 De Albuquerque, Victor Hugo C.
AB Advances in information and signal processing technologies have a significant impact on autonomous driving (AD), improving driving safety while minimizing the efforts of human drivers with the help of advanced artificial intelligence (AI) techniques. Recently, deep learning (DL) approaches have solved several real-world problems of complex nature. However, their strengths in terms of control processes for AD have not been deeply investigated and highlighted yet. This survey highlights the power of DL architectures in terms of reliability and efficient real-time performance and overviews state-of-the-art strategies for safe AD, with their major achievements and limitations. Furthermore, it covers major embodiments of DL along the AD pipeline including measurement, analysis, and execution, with a focus on road, lane, vehicle, pedestrian, drowsiness detection, collision avoidance, and traffic sign detection through sensing and vision-based DL methods. In addition, we discuss on the performance of several reviewed methods by using different evaluation metrics, with critics on their pros and cons. Finally, this survey highlights the current issues of safe DL-based AD with a prospect of recommendations for future research, rounding up a reference material for newcomers and researchers willing to join this vibrant area of Intelligent Transportation Systems.
SN 1524-9050
YR 2021
FD 2021-07
LA eng
NO Muhammad , K , Ullah , A , Lloret , J , Ser , J D & De Albuquerque , V H C 2021 , ' Deep Learning for Safe Autonomous Driving : Current Challenges and Future Directions ' , IEEE Transactions on Intelligent Transportation Systems , vol. 22 , no. 7 , 9284628 , pp. 4316-4336 . https://doi.org/10.1109/TITS.2020.3032227
NO Publisher Copyright: © 2000-2011 IEEE.
NO This work was supported by Institute of Information & Communications Technology Planning & Evaluation (IITP) Grant funded by the Korea Government (MSIT) (2019-0-00136, Development of AI-Convergence Technologies for Smart City Industry Productivity Innovation); The work of Javier Del Ser was supported by the Basque Government through the EMAITEK and ELKARTEK Programs, as well as by the Department of Education of this institution (Consolidated Research Group MATHMODE, IT1294-19); VHCA received support from the Brazilian National Council for Research and Development (CNPq, Grant #304315/2017-6 and #430274/2018-1). Manuscript received November 8, 2019; revised March 24, 2020 and July 21, 2020; accepted October 9, 2020. Date of publication December 7, 2020; date of current version July 12, 2021. This work was supported by Institute of Information & Communications Technology Planning & Evaluation (IITP) Grant funded by the Korea Government (MSIT) (2019-0-00136, Development of AI-Convergence Technologies for Smart City Industry Productivity Innovation); The work of Javier Del Ser was supported by the Basque Government through the EMAITEK and ELKARTEK Programs, as well as by the Department of Education of this institution (Consolidated Research Group MATHMODE, IT1294-19); VHCA received support from the Brazilian National Council for Research and Development (CNPq, Grant #304315/2017-6 and #430274/2018-1). The Associate Editor for this article was K. Kant. (Corresponding author: Khan Muhammad.) Khan Muhammad is with the Department of Software, Sejong University, Seoul 143-747, South Korea (e-mail: khan.muhammad@ieee.org).
DS TECNALIA Publications
RD 28 sept 2024