Resumen
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.
Idioma original | Inglés |
---|---|
Número de artículo | 250 |
Páginas (desde-hasta) | 250 |
Número de páginas | 1 |
Publicación | Electronics |
Volumen | 8 |
N.º | 2 |
DOI | |
Estado | Publicada - feb 2019 |
Palabras clave
- Machine learning
- Neural networks
- Predictive
- Vehicle dynamics
- Electric vehicles
- FPGA
- GPU
- Parallel architectures
- Optimization
Project and Funding Information
- Project ID
- info:eu-repo/grantAgreement/EC/H2020/662192/EU/Integrated Components for Complexity Control in affordable electrified cars/3Ccar
- info:eu-repo/grantAgreement/EC/H2020/692455/EU/European Initiative to Enable Validation for Highly Automated Safe and Secure Systems/ENABLE-S3
- Funding Info
- Some 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.