A survey of deep learning techniques for autonomous driving
-
- Sorin Grigorescu
- Artificial Intelligence, Elektrobit Automotive Robotics, Vision and Control Laboratory, Transilvania University of Brasov Brasov Romania
-
- Bogdan Trasnea
- Artificial Intelligence, Elektrobit Automotive Robotics, Vision and Control Laboratory, Transilvania University of Brasov Brasov Romania
-
- Tiberiu Cocias
- Artificial Intelligence, Elektrobit Automotive Robotics, Vision and Control Laboratory, Transilvania University of Brasov Brasov Romania
-
- Gigel Macesanu
- Artificial Intelligence, Elektrobit Automotive Robotics, Vision and Control Laboratory, Transilvania University of Brasov Brasov Romania
Description
<jats:title>Abstract</jats:title><jats:p>The last decade witnessed increasingly rapid progress in self‐driving vehicle technology, mainly backed up by advances in the area of deep learning and artificial intelligence (AI). The objective of this paper is to survey the current state‐of‐the‐art on deep learning technologies used in autonomous driving. We start by presenting AI‐based self‐driving architectures, convolutional and recurrent neural networks, as well as the deep reinforcement learning paradigm. These methodologies form a base for the surveyed driving scene perception, path planning, behavior arbitration, and motion control algorithms. We investigate both the modular perception‐planning‐action pipeline, where each module is built using deep learning methods, as well as End2End systems, which directly map sensory information to steering commands. Additionally, we tackle current challenges encountered in designing AI architectures for autonomous driving, such as their safety, training data sources, and computational hardware. The comparison presented in this survey helps gain insight into the strengths and limitations of deep learning and AI approaches for autonomous driving and assist with design choices.</jats:p>
Journal
-
- Journal of Field Robotics
-
Journal of Field Robotics 37 (3), 362-386, 2019-11-14
Wiley
- Tweet
Details 詳細情報について
-
- CRID
- 1363670321292497536
-
- ISSN
- 15564967
- 15564959
-
- Data Source
-
- Crossref