B
Bogdan Trasnea
Researcher at Transilvania University of Brașov
Publications - 22
Citations - 1147
Bogdan Trasnea is an academic researcher from Transilvania University of Brașov. The author has contributed to research in topics: Deep learning & Artificial neural network. The author has an hindex of 5, co-authored 22 publications receiving 350 citations.
Papers
More filters
Journal ArticleDOI
A survey of deep learning techniques for autonomous driving
TL;DR: In this article, the authors survey the current state-of-the-art on deep learning technologies used in autonomous driving, including convolutional and recurrent neural networks, as well as the deep reinforcement learning paradigm.
Journal ArticleDOI
A Survey of Deep Learning Techniques for Autonomous Driving
TL;DR: The objective of this paper is to survey the current state‐of‐the‐art on deep learning technologies used in autonomous driving, by presenting AI‐based self‐driving architectures, convolutional and recurrent neural networks, as well as the deep reinforcement learning paradigm.
Journal ArticleDOI
NeuroTrajectory: A Neuroevolutionary Approach to Local State Trajectory Learning for Autonomous Vehicles
TL;DR: NeuroTrajectory is introduced, which is a multiobjective neuroevolutionary approach to local state trajectory learning for autonomous driving, where the desired state trajectory of the ego-vehicle is estimated over a finite prediction horizon by a perception-planning deep neural network.
Proceedings ArticleDOI
Deep Grid Net (DGN): A Deep Learning System for Real-Time Driving Context Understanding
Liviu A. Marina,Bogdan Trasnea,Tiberiu T. Cocias,Andrei Vasilcoi,Florin Moldoveanu,Sorin Mihai Grigorescu +5 more
Patent
Generating training images for machine learning-based object recognition systems
TL;DR: In this article, a method, performed by a computing device, for generating training image data for a machine learning-based object recognition system is described, which comprises receiving generic image data of an object type, receiving recorded image data related to the object type and modifying the generic image with respect to at least one imaging-related parameter.