Martin Dendaluce Jahnke, Francesco Cosco, Rihards Novickis, Joshué Pérez Rastelli, Vicente Gomez-Garay. 2019. Efficient Neural Network Implementations on Parallel Embedded Platforms applied to Real-Time Torque-Vectoring Optimization using Predictions for Multi-Motor Electric Vehicles. Electronics (Switzerland), 8(2), 250 pp. https://www.mdpi.com/2079-9292/8/2/250

Bibtex citation:
@article{1798_2019,
author = {Martin Dendaluce Jahnke and Francesco Cosco and Rihards Novickis and Joshué Pérez Rastelli and Vicente Gomez-Garay},
title = {Efficient Neural Network Implementations on Parallel Embedded Platforms applied to Real-Time Torque-Vectoring Optimization using Predictions for Multi-Motor Electric Vehicles},
journal = {Electronics (Switzerland)},
volume = {8},
issue = {2},
pages = {250},
url = {https://www.mdpi.com/2079-9292/8/2/250},
year = {2019}
}

Abstract: 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. © 2019 by the authors. Licensee MDPI, Basel, Switzerland.

Full text: Efficient Neural Network Implementations on

Scopus search