{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T08:28:46Z","timestamp":1771230526269,"version":"3.50.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T00:00:00Z","timestamp":1721865600000},"content-version":"vor","delay-in-days":54,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"University of Miskolc"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Des Autom Embed Syst"],"published-print":{"date-parts":[[2024,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>With the increase in the non-linearity and complexity of the driving system\u2019s environment, developing and optimizing related applications is becoming more crucial and remains an open challenge for researchers and automotive companies alike. Model predictive control (MPC) is a well-known classic control strategy used to solve online optimization problems. MPC is computationally expensive and resource-consuming. Recently, machine learning has become an effective alternative to classical control systems. This paper provides a developed deep neural network (DNN)-based control strategy for automated steering deployed on FPGA. The DNN model was designed and trained based on the behavior of the traditional MPC controller. The performance of the DNN model is evaluated compared to the performance of the designed MPC which already proved its merit in automated driving task. A new automatic intellectual property generator based on the Xilinx system generator (XSG) has been developed, not only to perform the deployment but also to optimize it. The performance was evaluated based on the ability of the controllers to drive the lateral deviation and yaw angle of the vehicle to be as close as possible to zero. The DNN model was implemented on FPGA using two different data types, fixed-point and floating-point, in order to evaluate the efficiency in the terms of performance and resource consumption. The obtained results show that the suggested DNN model provided a satisfactory performance and successfully imitated the behavior of the traditional MPC with a very small root mean square error (RMSE = 0.011228 rad). Additionally, the results show that the deployments using fixed-point data greatly reduced resource consumption compared to the floating-point data type while maintaining satisfactory performance and meeting the safety conditions<\/jats:p>","DOI":"10.1007\/s10617-024-09287-x","type":"journal-article","created":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T16:01:38Z","timestamp":1722009698000},"page":"139-153","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Model predictive-based DNN control model for automated steering deployed on FPGA using an automatic IP generator tool"],"prefix":"10.1007","volume":"28","author":[{"given":"Ahmad","family":"Reda","sequence":"first","affiliation":[]},{"given":"Afulay Ahmed","family":"Bouzid","sequence":"additional","affiliation":[]},{"given":"Alhasan","family":"Zghaibe","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Dr\u00f3tos","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7328-6877","authenticated-orcid":false,"given":"V\u00e1s\u00e1rhelyi","family":"J\u00f3zsef","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,7,25]]},"reference":[{"key":"9287_CR1","doi-asserted-by":"publisher","first-page":"58443","DOI":"10.1109\/ACCESS.2020.2983149","volume":"8","author":"E Yurtsever","year":"2020","unstructured":"Yurtsever E, Lambert J, Carballo A, Takeda K (2020) A survey of autonomous driving: common practices and emerging technologies. IEEE Access 8:58443\u201358469. https:\/\/doi.org\/10.1109\/ACCESS.2020.2983149","journal-title":"IEEE Access"},{"key":"9287_CR2","doi-asserted-by":"publisher","unstructured":"Best A, Narang S, Barber D, Manocha D (2017) AutonoVi: autonomous vehicle planning with dynamic maneuvers and traffic constraints. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp 2629\u20132636. https:\/\/doi.org\/10.1109\/IROS.2017.8206087","DOI":"10.1109\/IROS.2017.8206087"},{"issue":"1","key":"9287_CR3","doi-asserted-by":"publisher","first-page":"6","DOI":"10.3390\/machines5010006","volume":"5","author":"SD Pendleton","year":"2017","unstructured":"Pendleton SD et al (2017) Perception planning control and coordination for autonomous vehicles. Machines 5(1):6","journal-title":"Machines"},{"key":"9287_CR4","doi-asserted-by":"publisher","unstructured":"Swief A, El-Zawawi A, El-Habrouk M, Eldin AN (2020) Approximate neural network model for adaptive model predictive control. In: 6th international computer engineering conference (ICENCO), pp 135\u2013140. https:\/\/doi.org\/10.1109\/ICENCO49778.2020.9357373","DOI":"10.1109\/ICENCO49778.2020.9357373"},{"key":"9287_CR5","doi-asserted-by":"publisher","unstructured":"Masmoudi M, Ghazzai H, Frikha M, Massoud Y (2019) Object detection learning techniques for autonomous vehicle applications. In: 2019 IEEE international conference on vehicular electronics and safety (ICVES), pp 1\u20135. https:\/\/doi.org\/10.1109\/ICVES.2019.8906437","DOI":"10.1109\/ICVES.2019.8906437"},{"key":"9287_CR6","doi-asserted-by":"publisher","unstructured":"Lamouik I, Yahyaouy A, Sabri MA (2018) Deep neural network dynamic traffic routing system for vehicles. In: 2018 international conference on intelligent systems and computer vision (ISCV), pp 1\u20134. https:\/\/doi.org\/10.1109\/ISACV.2018.8354012","DOI":"10.1109\/ISACV.2018.8354012"},{"key":"9287_CR7","doi-asserted-by":"publisher","unstructured":"Rausch V, Hansen A, Solowjow E, Liu C, Kreuzer E, Hedrick JK (2017) Learning a deep neural net policy for end-to-end control of autonomous vehicles. In: 2017 American control conference (ACC), pp 4914\u20134919. https:\/\/doi.org\/10.23919\/ACC.2017.7963716","DOI":"10.23919\/ACC.2017.7963716"},{"key":"9287_CR8","doi-asserted-by":"publisher","unstructured":"Li Q, Xiao Q, Liang Y (2017) Enabling high performance deep learning networks on embedded systems. In: IECON 2017\u201443rd annual conference of the IEEE industrial electronics society, pp 8405\u20138410. https:\/\/doi.org\/10.1109\/IECON.2017.8217476","DOI":"10.1109\/IECON.2017.8217476"},{"key":"9287_CR9","unstructured":"Bin Khalid SA, Liegmann E, Karamanakos P, Kennel R (2020)High-level synthesis of a long horizon model predictive control algorithm for an FPGA. In: PCIM Eur. digit days 2020, Int. Exhib. Conf. Power Electronics, Intell. Motion, Renewable Energy and Energy Manage, pp 1\u20138"},{"issue":"2","key":"9287_CR10","doi-asserted-by":"publisher","first-page":"2066","DOI":"10.1109\/JESTPE.2020.2999267","volume":"9","author":"VK Singh","year":"2021","unstructured":"Singh VK, Tripathi RN, Hanamoto T (2021) Implementation strategy for resource optimization of FPGA-based adaptive finite control set-MPC using XSG for a VSI system. IEEE J Emerg Sel Top Power Electron 9(2):2066\u20132078","journal-title":"IEEE J Emerg Sel Top Power Electron"},{"key":"9287_CR11","doi-asserted-by":"publisher","unstructured":"Ingole D, Holaza J, Tak\u00c3ics B, Kvasnica M (2015)FPGA-based explicit model predictive control for closed-loop control of intravenous anesthesia. In: 20th international conference on process control (PC), pp 42\u201347. https:\/\/doi.org\/10.1109\/PC.2015.7169936","DOI":"10.1109\/PC.2015.7169936"},{"key":"9287_CR12","unstructured":"Kumar K, Davim JP (2019) Brief review of mathematical optimization. International Society for Technology in Education (ISTE)"},{"issue":"12","key":"9287_CR13","doi-asserted-by":"publisher","first-page":"2200","DOI":"10.3390\/electronics9122200","volume":"9","author":"A Ghaffari","year":"2020","unstructured":"Ghaffari A, Savaria Y (2020) CNN2Gate: an implementation of convolutional neural networks inference on FPGAS with automated design space exploration. Electronics 9(12):2200. https:\/\/doi.org\/10.3390\/electronics9122200","journal-title":"Electronics"},{"key":"9287_CR14","unstructured":"Deep Learning HDL Toolbox. MathWorks [Online]. https:\/\/www.mathworks.com\/help\/pdf_doc\/deep-learning-hdl\/dlhdl_ug.pdf"},{"key":"9287_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2020.101887","author":"D Moolchandani","year":"2021","unstructured":"Moolchandani D, Kumar A, Sarangi SR (2021) Accelerating CNN inference on ASICs: a survey. J Syst Architect. https:\/\/doi.org\/10.1016\/j.sysarc.2020.101887","journal-title":"J Syst Architect"},{"key":"9287_CR16","doi-asserted-by":"publisher","DOI":"10.36227\/techrxiv.14060954.v1","author":"DG Moreno","year":"2021","unstructured":"Moreno DG, Garcia AAD, Botella G, Hasler J (2021) A cluster of FPAAs to recognize images using neural networks. IEEE Trans Circuits Syst Exp Briefs. https:\/\/doi.org\/10.36227\/techrxiv.14060954.v1","journal-title":"IEEE Trans Circuits Syst Exp Briefs"},{"issue":"1","key":"9287_CR17","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1109\/JETCAS.2017.2777784","volume":"8","author":"S Shah","year":"2018","unstructured":"Shah S, Hasler J (2018) SOC FPAA hardware implementation of a VMM+WTA embedded learning classifier. IEEE J Emerg Sel Top Circuits Syst 8(1):28\u201337","journal-title":"IEEE J Emerg Sel Top Circuits Syst"},{"key":"9287_CR18","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10091025","author":"R Wu","year":"2021","unstructured":"Wu R, Guo X, Du J, Li J (2021) Accelerating neural network inference on FPGA-based platforms\u2014a survey. Electronics. https:\/\/doi.org\/10.3390\/electronics10091025","journal-title":"Electronics"},{"key":"9287_CR19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3043292","author":"MS Diab","year":"2020","unstructured":"Diab MS, Mahmoud SA (2020) Survey on field programmable analog array architectures eliminating routing network. IEEE Access. https:\/\/doi.org\/10.1109\/ACCESS.2020.3043292","journal-title":"IEEE Access"},{"issue":"9","key":"9287_CR20","doi-asserted-by":"publisher","first-page":"13384","DOI":"10.1364\/OE.391050","volume":"28","author":"J Lee","year":"2021","unstructured":"Lee J, He J, Wang K (2021) FPGA-based neural network accelerators for millimeter-wave radio-over-fiber systems. Opt Express 28(9):13384\u201313400","journal-title":"Opt Express"},{"key":"9287_CR21","unstructured":"Hern\u00c3indez WC, Pelcat M, Berry F (2021) Why is FPGA-GPU heterogeneity the best option for embedded deep neural networks. In: Workshop system-level design methods for deep learning on heterogeneous architectures (SLOHA)"},{"key":"9287_CR22","doi-asserted-by":"publisher","unstructured":"Shi S, Wang Q, Xu P, Chu X (2016) Benchmarking state-of-the-art deep learning software tools. In: International conference on cloud computing and big data (CCBD), pp 99\u2013104. https:\/\/doi.org\/10.1109\/CCBD.2016.029","DOI":"10.1109\/CCBD.2016.029"},{"issue":"9","key":"9287_CR23","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1007\/s11265-020-01549-8","volume":"92","author":"Z Que","year":"2020","unstructured":"Que Z, Zhu Y, Fan H, Meng J, Niu X, Luk W (2020) Mapping large LSTMs to FPGAs with weight reuse. J. Signal Process. Syst. 92(9):965\u2013979","journal-title":"J. Signal Process. Syst."},{"key":"9287_CR24","unstructured":"Colbert I, Daly J, Kreutz-Delgado K, Das S (2021) A competitive edge: can FPGAs beat GPUs at DCNN inference acceleration in resource-limited edge computing applications?. Preprint arXiv:2102.00294"},{"key":"9287_CR25","doi-asserted-by":"publisher","unstructured":"Shahshahani M, Sabri M, Khabbazan B, Bhatia D (2021) An automated tool for implementing deep neural networks on FPGA. In: 34th International conference on VLSI design and 2021 20th international conference on embedded systems (VLSID), pp 322\u2013327. https:\/\/doi.org\/10.1109\/VLSID51830.2021.00060","DOI":"10.1109\/VLSID51830.2021.00060"},{"key":"9287_CR26","doi-asserted-by":"publisher","first-page":"7823","DOI":"10.1109\/ACCESS.2018.2890150","volume":"7","author":"A Shawahna","year":"2019","unstructured":"Shawahna A, Sait SM, El-Maleh A (2019) FPGA-based accelerators of deep learning networks for learning and classification: a review. IEEE Access 7:7823\u20137859. https:\/\/doi.org\/10.1109\/ACCESS.2018.2890150","journal-title":"IEEE Access"},{"key":"9287_CR27","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.vlsi.2017.12.009","volume":"62","author":"Y Ma","year":"2018","unstructured":"Ma Y, Suda N, Cao Y, Vrudhula S, Seo JS (2018) ALAMO: FPGA acceleration of deep learning algorithms with a modularized RTL compiler. Integration 62:14\u201323","journal-title":"Integration"},{"key":"9287_CR28","doi-asserted-by":"publisher","unstructured":"Zhang X et al, (2018) DNNBuilder: an automated tool for building high-performance DNN hardware accelerators for FPGAs. In 2018 IEEE\/international conference on computer-aided design (ICCAD), pp 1\u20138. https:\/\/doi.org\/10.1145\/3240765.3240801","DOI":"10.1145\/3240765.3240801"},{"key":"9287_CR29","doi-asserted-by":"publisher","unstructured":"Guan Y et al, (2017)\u201cFP-DNN: An Automated Framework for Mapping Deep Neural Networks onto FPGAs with RTL-HLS Hybrid Templates,\u201d in 2017 IEEE 25th Annu. Int. Sympo. Field-Programmable Custom Comput. Machines (FCCM), pp. 152-159 ,https:\/\/doi.org\/10.1109\/FCCM.2017.25,","DOI":"10.1109\/FCCM.2017.25,"},{"key":"9287_CR30","doi-asserted-by":"publisher","unstructured":"Riazati M, Daneshtalab M, Sj\u00f6din M, Lisper B (2020) DeepHLS: a complete toolchain for automatic synthesis of deep neural networks to FPGA. In: 2020 27th IEEE international conference on electronics, circuits and systems (ICECS), pp 1\u20134. https:\/\/doi.org\/10.1109\/ICECS49266.2020.9294881","DOI":"10.1109\/ICECS49266.2020.9294881"}],"container-title":["Design Automation for Embedded Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10617-024-09287-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10617-024-09287-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10617-024-09287-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T06:10:42Z","timestamp":1724825442000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10617-024-09287-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":30,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["9287"],"URL":"https:\/\/doi.org\/10.1007\/s10617-024-09287-x","relation":{},"ISSN":["0929-5585","1572-8080"],"issn-type":[{"value":"0929-5585","type":"print"},{"value":"1572-8080","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]},"assertion":[{"value":"4 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no any potential Conflict of interest (financial or non-financial).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"To ensure objectivity and transparency in research and to ensure that accepted principles of ethical and professional conduct have been followed, authors declare.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The research did not involved any human participant nor animals.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human participant nor animals"}},{"value":"There is no need for any person informed consent.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}