Repositorio Digital UPCT
Publicación
Artículo científico (JournalArticle)
End-to-End deep neural network architectures for speed and steering wheel angle prediction in autonomous driving
The complex decision-making systems used for autonomous vehicles or advanced driverassistance systems (ADAS) are being replaced by end-to-end (e2e) architectures based on deep-neuralnetworks (DNN). DNNs can learn complex driving actions from datasets containing thousands of
images and data obtained from the vehicle perception system. This work presents the classification,
design and implementation of six e2e architectures capable of generating the driving actions of speed
and steering wheel angle directly on the vehicle control elements. The work details the design stages
and optimization process of the convolutional networks to develop six e2e architectures. In the
metric analysis the architectures have been tested with different data sources from the vehicle, such
as images, XYZ accelerations and XYZ angular speeds. The best results were obtained with a mixed
data e2e architecture that used front images from the vehicle and angular speeds to predict the speed
and steering wheel angle with a mean error of 1.06%. An exhaustive optimization process of the
convolutional blocks has demonstrated that it is possible to design lightweight e2e architectures with
high performance more suitable for the final implementation in autonomous driving., This work was partially supported by DGT (ref.SPIP2017-02286) and GenoVision
(ref.BFU2017-88300-C2-2-R) Spanish Government projects, and the “Research Programe for Groups
of Scientific Excellence in the Region of Murcia” of the Seneca Foundation (Agency for Science and
Technology in the Region of Murcia—19895/GERM/15).