Design and Implementation of Artificial Intelligence Models Using Deep Neural Networks on Reconfigurable VLSI Systems for Autonomous Driving
Autonomous vehicles use object detection in real time, which is an important aspect of navigation and decision-making systems. Nevertheless, conventional computing architecture like CPUs and GPUs are usually inadequate to support the required latency, power consumption, and real-time demands within...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , , , , |
| التنسيق: | article |
| منشور في: |
2025
|
| الوصول للمادة أونلاين: | http://hdl.handle.net/11675/14492 https: |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1870679722517594113 |
|---|---|
| author | Bostani, Ali |
| author2 | Jacob, Mary Kumar, Anil Muruganantham, S. Santhosh Kumar, C. Sathishkumar, K. Zukhra, Ismailova |
| author2_role | author author author author author author |
| author_facet | Bostani, Ali Jacob, Mary Kumar, Anil Muruganantham, S. Santhosh Kumar, C. Sathishkumar, K. Zukhra, Ismailova |
| author_role | author |
| dc.creator.none.fl_str_mv | Bostani, Ali Jacob, Mary Kumar, Anil Muruganantham, S. Santhosh Kumar, C. Sathishkumar, K. Zukhra, Ismailova |
| dc.date.none.fl_str_mv | 2025-08-01 2026-06-03T10:09:32Z 2026-06-03T10:09:32Z |
| dc.identifier.none.fl_str_mv | 10.31838/JVCS/07.01.16 http://hdl.handle.net/11675/14492 https: www.scopus.com/pages/publications/105014546150 |
| dc.publisher.none.fl_str_mv | Society for Communication and Computer Technologies |
| dc.relation.none.fl_str_mv | Electrical and Computer Engineering Journal of VLSI Circuits and Systems |
| dc.title.none.fl_str_mv | Design and Implementation of Artificial Intelligence Models Using Deep Neural Networks on Reconfigurable VLSI Systems for Autonomous Driving |
| dc.type.none.fl_str_mv | Article info:eu-repo/semantics/publishedVersion info:eu-repo/semantics/article |
| description | Autonomous vehicles use object detection in real time, which is an important aspect of navigation and decision-making systems. Nevertheless, conventional computing architecture like CPUs and GPUs are usually inadequate to support the required latency, power consumption, and real-time demands within embedded automotive systems. This paper gives details of a generic design and implementation of object detection models using deep neural networks on reconfigurable very large-scale integration (VLSI) systems including field-programmable gate arrays (FPGAs). The quantized and compressed architecture of DNN are shown as combining a system-level co-design approach with an FPGA platform by means of optimized mapping of hardware and parallel dataflow design. The framework has been proposed based on low-latency, high-throughput, energy-efficient inference, which can be brought to the edge when safety is required. The process of simulation and hardware synthesis entails MATLAB, Simulink, HDL Coder, and Xilinx Vivado, with experimental analysis being carried out on real datasets, such as KITTI or BDD100K. Experiments show that indeed there is a huge gain in the number of inferences per second and resource consumption as well as power generations when compared to typical CPU/GPU deployment. The results support the conclusion on the usefulness of reconfigurable VLSI platforms as an alternative hardware solution to building autonomous driving systems by AI in the future. |
| format | article |
| id | AUKR_2bf92d806be71508cef5114dc68eafd6 |
| identifier_str_mv | 10.31838/JVCS/07.01.16 www.scopus.com/pages/publications/105014546150 |
| network_acronym_str | AUKR |
| network_name_str | AU Kuwait Rep |
| oai_identifier_str | oai:dspace.auk.edu.kw:11675/14492 |
| publishDate | 2025 |
| publisher.none.fl_str_mv | Society for Communication and Computer Technologies |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| spelling | Design and Implementation of Artificial Intelligence Models Using Deep Neural Networks on Reconfigurable VLSI Systems for Autonomous DrivingBostani, AliJacob, MaryKumar, AnilMuruganantham, S.Santhosh Kumar, C.Sathishkumar, K.Zukhra, IsmailovaAutonomous vehicles use object detection in real time, which is an important aspect of navigation and decision-making systems. Nevertheless, conventional computing architecture like CPUs and GPUs are usually inadequate to support the required latency, power consumption, and real-time demands within embedded automotive systems. This paper gives details of a generic design and implementation of object detection models using deep neural networks on reconfigurable very large-scale integration (VLSI) systems including field-programmable gate arrays (FPGAs). The quantized and compressed architecture of DNN are shown as combining a system-level co-design approach with an FPGA platform by means of optimized mapping of hardware and parallel dataflow design. The framework has been proposed based on low-latency, high-throughput, energy-efficient inference, which can be brought to the edge when safety is required. The process of simulation and hardware synthesis entails MATLAB, Simulink, HDL Coder, and Xilinx Vivado, with experimental analysis being carried out on real datasets, such as KITTI or BDD100K. Experiments show that indeed there is a huge gain in the number of inferences per second and resource consumption as well as power generations when compared to typical CPU/GPU deployment. The results support the conclusion on the usefulness of reconfigurable VLSI platforms as an alternative hardware solution to building autonomous driving systems by AI in the future.Society for Communication and Computer Technologies2026-06-03T10:09:32Z2026-06-03T10:09:32Z2025-08-01Articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article10.31838/JVCS/07.01.16http://hdl.handle.net/11675/14492https:www.scopus.com/pages/publications/105014546150Electrical and Computer EngineeringJournal of VLSI Circuits and Systemsoai:dspace.auk.edu.kw:11675/144922026-06-03T12:38:00Z |
| spellingShingle | Design and Implementation of Artificial Intelligence Models Using Deep Neural Networks on Reconfigurable VLSI Systems for Autonomous Driving Bostani, Ali |
| status_str | publishedVersion |
| title | Design and Implementation of Artificial Intelligence Models Using Deep Neural Networks on Reconfigurable VLSI Systems for Autonomous Driving |
| title_full | Design and Implementation of Artificial Intelligence Models Using Deep Neural Networks on Reconfigurable VLSI Systems for Autonomous Driving |
| title_fullStr | Design and Implementation of Artificial Intelligence Models Using Deep Neural Networks on Reconfigurable VLSI Systems for Autonomous Driving |
| title_full_unstemmed | Design and Implementation of Artificial Intelligence Models Using Deep Neural Networks on Reconfigurable VLSI Systems for Autonomous Driving |
| title_short | Design and Implementation of Artificial Intelligence Models Using Deep Neural Networks on Reconfigurable VLSI Systems for Autonomous Driving |
| title_sort | Design and Implementation of Artificial Intelligence Models Using Deep Neural Networks on Reconfigurable VLSI Systems for Autonomous Driving |
| url | http://hdl.handle.net/11675/14492 https: |