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.
Highlights
As vehicle electrification moves forward [1,2], new powertrain topologies are appearing and attractive research and innovation opportunities for developing enhanced propulsion systems can be identified [3]
The bottom-line of the above discussed topics leads to the motivation already anticipated in the introduction: we aim to provide enabler solutions targeting advanced Torque-Vectoring algorithms with real-time optimization, which represent a challenging application and a restrictive domain
This illustrates that the neural networks (NNs) provides sufficient capacity to adapt to highly dynamic situations, including those of which only few fragments are present in the training dataset
Summary
As vehicle electrification moves forward [1,2], new powertrain topologies are appearing and attractive research and innovation opportunities for developing enhanced propulsion systems can be identified [3]. Electronics 2019, 8, 250 powertrains driven by multiple electric motors can be unleashed by exploiting several enabler technologies which are addressed in this work, aiming to implement sophisticated Torque-Vectoring techniques [4,5,6] This kind of advanced active chassis control systems can be eventually categorized inside the field of ADAS by themselves but they can be exploited to support further ADAS -or even automated driving- functionalities, such as active support in critical evasive manoeuvres or to provide predictions and estimations of unmeasurable variables to take corresponding actions. While keeping reasonable cost points and power consumption, they are bringing vast computing power and intrinsic parallelism (for performance) and redundancy (for safety) This power can be harnessed to implement complex algorithms, including Machine Learning, in both the cited application fields [7,8,9,10,11,12,13,14,15,16,17,18]. Major challenges appear on the notably complex technical layers and in the regulatory layer addressing safety-critical applications [19,20]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
