Vicente Gómez-Garay

Vicente Gómez-Garay

Auto-generated profile, based on publicly available information

Vicente Gómez-Garay

University of the Basque Country (UPV/EHU), ETSI

Research Focus & Metrics

Academic Career Length

27Years (2000-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2012 in Expert Systems with Applications
Verified
Journal Article
Closed access
JVJuan Jose Valera
Juan Jose Valera
VGVicente Gómez Garay
Vicente Gómez Garay
Eloy IrigoyenEloy Irigoyen
Eloy Irigoyen
FFFernando Artaza Fano
Fernando Artaza Fano
MLMikel Larrea
Mikel Larrea

22 February 2019 in Electronics
Verified
Journal Article
Open access
PDF file
MJMartin Dendaluce Jahnke
Martin Dendaluce Jahnke
Francesco CoscoFrancesco Cosco
Francesco Cosco
Rihards NovickisRihards Novickis
Rihards Novickis
JRJoshué Manuel Perez Rastelli
Joshué Manuel Perez Rastelli
VGVicente Gomez-Garay
Vicente Gomez-Garay
The combination of machine learning and heterogeneous embedded platforms enables new potential for developing sophisticated control concepts which are applicable to the field of vehicle dynamics and ADAS. This interdisciplinary work provides enabler solutions -ultimately implementing fast predictions using neural networks (NNs) on field programmable gate arrays (FPGAs) and graphical processing units (GPUs)- while applying them to a challenging application: Torque Vectoring on a multi-electric-motor vehicle for enhanced vehicle dynamics. The foundation motivating this work is provided by discussing multiple domains of the technological context as well as the constraints related to the automotive field, which contrast with the attractiveness of exploiting the capabilities of new embedded platforms to apply advanced control algorithms for complex control problems. In this particular case we target enhanced vehicle dynamics on a multi-motor electric vehicle benefiting from the greater degrees of freedom and controllability offered by such powertrains. Considering the constraints of the application and the implications of the selected multivariable optimization challenge, we propose a NN to provide batch predictions for real-time optimization. This leads to the major contribution of this work: efficient NN implementations on two intrinsically parallel embedded platforms, a GPU and a FPGA, following an analysis of theoretical and practical implications of their different operating paradigms, in order to efficiently harness their computing potential while gaining insight into their peculiarities. The achieved results exceed the expectations and additionally provide a representative illustration of the strengths and weaknesses of each kind of platform. Consequently, having shown the applicability of the proposed solutions, this work contributes valuable enablers also for further developments following similar fundamental principles.

1 February 2000 in Finite Elements in Analysis and Design
Verified
Journal Article
Closed access
RARafael Avilés
Rafael Avilés
GAGoizalde Ajuria
Goizalde Ajuria
EAEnrique Amezua
Enrique Amezua
VGVicente Gómez-Garay
Vicente Gómez-Garay

1 August 2000 in Mechanism and Machine Theory
Verified
Journal Article
Closed access
RARafael Avilés
Rafael Avilés
GAGoizalde Ajuria
Goizalde Ajuria
VGVicente Gómez-Garay
Vicente Gómez-Garay
SNSantiago Navalpotro
Santiago Navalpotro

1 January 2014
Verified
Book Chapter
Closed access
PDF file
MDMartin Dendaluce
Martin Dendaluce
JVJuan Jose Valera
Juan Jose Valera
VGVicente Gómez-Garay
Vicente Gómez-Garay
Eloy IrigoyenEloy Irigoyen
Eloy Irigoyen
ELEkaitz Larzabal
Ekaitz Larzabal

1 September 2010
Verified
Conference Paper
Closed access
MLMikel Larrea
Mikel Larrea
Eloy IrigoyenEloy Irigoyen
Eloy Irigoyen
VGVicente Gómez
Vicente Gómez
FAFernando Artaza
Fernando Artaza
This paper presents an Adaptive Predictive Control strategy based on Neural Networks for nonlinear systems. In order to train the Neural Network controller, an identification of the system is carried out by the Neural Network Identifier. This second Neural Network provides the training terms related to the nonlinear system dynamics. In this way it is possible to train the Neural Network controller online. The simulation results show a correct online adaptation of the NN controller and the validity of the proposed control strategy.