Efficient Neural Network Implementations on Parallel Embedded Platforms Applied to Real-Time Torque-Vectoring Optimization Using Predictions for Multi-Motor Electric Vehicles

Simple item page
dc.contributor.authorDendaluce Jahnke, Martin
dc.contributor.authorCosco, Francesco
dc.contributor.authorNovickis, Rihards
dc.contributor.authorPérez Rastelli, Joshué
dc.contributor.authorGomez-Garay, Vicente
dc.contributor.institutionTecnalia Research & Innovation
dc.contributor.institutionCCAM
dc.date.issued2019-02
dc.descriptionPublisher Copyright: © 2019 by the authors. Licensee MDPI, Basel, Switzerland.
dc.description.abstractThe 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.en
dc.description.statusPeer reviewed
dc.format.extent1
dc.format.extent3931233
dc.identifier.citationDendaluce Jahnke , M , Cosco , F , Novickis , R , Pérez Rastelli , J & Gomez-Garay , V 2019 , ' Efficient Neural Network Implementations on Parallel Embedded Platforms Applied to Real-Time Torque-Vectoring Optimization Using Predictions for Multi-Motor Electric Vehicles ' , Electronics , vol. 8 , no. 2 , 250 , pp. 250 . https://doi.org/10.3390/electronics8020250
dc.identifier.doi10.3390/electronics8020250
dc.identifier.issn2079-9292
dc.identifier.otherresearchoutputwizard: 11556/701
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85063511260&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofElectronics
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subject.keywordsMachine learning
dc.subject.keywordsNeural networks
dc.subject.keywordsPredictive
dc.subject.keywordsVehicle dynamics
dc.subject.keywordsElectric vehicles
dc.subject.keywordsFPGA
dc.subject.keywordsGPU
dc.subject.keywordsParallel architectures
dc.subject.keywordsOptimization
dc.subject.keywordsMachine learning
dc.subject.keywordsNeural networks
dc.subject.keywordsPredictive
dc.subject.keywordsVehicle dynamics
dc.subject.keywordsElectric vehicles
dc.subject.keywordsFPGA
dc.subject.keywordsGPU
dc.subject.keywordsParallel architectures
dc.subject.keywordsOptimization
dc.subject.keywordsControl and Systems Engineering
dc.subject.keywordsSignal Processing
dc.subject.keywordsHardware and Architecture
dc.subject.keywordsComputer Networks and Communications
dc.subject.keywordsElectrical and Electronic Engineering
dc.subject.keywordsSDG 7 - Affordable and Clean Energy
dc.subject.keywordsProject ID
dc.subject.keywordsinfo:eu-repo/grantAgreement/EC/H2020/662192/EU/Integrated Components for Complexity Control in affordable electrified cars/3Ccar
dc.subject.keywordsinfo:eu-repo/grantAgreement/EC/H2020/692455/EU/European Initiative to Enable Validation for Highly Automated Safe and Secure Systems/ENABLE-S3
dc.subject.keywordsinfo:eu-repo/grantAgreement/EC/H2020/662192/EU/Integrated Components for Complexity Control in affordable electrified cars/3Ccar
dc.subject.keywordsinfo:eu-repo/grantAgreement/EC/H2020/692455/EU/European Initiative to Enable Validation for Highly Automated Safe and Secure Systems/ENABLE-S3
dc.subject.keywordsFunding Info
dc.subject.keywordsSome of the results presented in this work are related to activities within the 3Ccar project, which has_x000D_ received funding from ECSEL Joint Undertaking under grant agreement No. 662192. This Joint Undertaking_x000D_ received support from the European Union’s Horizon 2020 research and innovation programme and Germany,_x000D_ Austria, Czech Republic, Romania, Belgium, United Kingdom, France, Netherlands, Latvia, Finland, Spain, Italy,_x000D_ Lithuania. This work was also partly supported by the project ENABLES3, which received funding from ECSEL_x000D_ Joint Undertaking under grant agreement No. 692455-2.
dc.subject.keywordsSome of the results presented in this work are related to activities within the 3Ccar project, which has_x000D_ received funding from ECSEL Joint Undertaking under grant agreement No. 662192. This Joint Undertaking_x000D_ received support from the European Union’s Horizon 2020 research and innovation programme and Germany,_x000D_ Austria, Czech Republic, Romania, Belgium, United Kingdom, France, Netherlands, Latvia, Finland, Spain, Italy,_x000D_ Lithuania. This work was also partly supported by the project ENABLES3, which received funding from ECSEL_x000D_ Joint Undertaking under grant agreement No. 692455-2.
dc.titleEfficient Neural Network Implementations on Parallel Embedded Platforms Applied to Real-Time Torque-Vectoring Optimization Using Predictions for Multi-Motor Electric Vehiclesen
dc.typejournal article
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
electronics-08-00250.pdf
Size:
3.75 MB
Format:
Adobe Portable Document Format
Download