Open-Source Educational Platform for FPGA Accelerated AI in Robotics

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

11 Downloads (Pure)

Abstract

Artificial Intelligence (AI) using neural networks is growing rapidly in the area of robotics and many tools have been developed in the last few years to utilize these networks. However, these tools are very abstract and do not provide deep knowledge on how the neural networks perform their computations. This makes it difficult for roboticists to understand and fully harness the power of AI. In this work, we present an open-source framework for designing and implementing a simple neural network targeting edge computing platforms. The framework goes step-by-step through the training, synthesis, and hardware implementation on a Zynq platform. The final hardware implementation is evaluated against a classical implementation in software. The platform was used in the Embedded Systems Course at the University of Southern Denmark.

Original languageEnglish
Title of host publication2022 8th International Conference on Mechatronics and Robotics Engineering, ICMRE 2022
PublisherIEEE
Publication date2022
Pages112-115
ISBN (Electronic)9781665483773
DOIs
Publication statusPublished - 2022
Event8th International Conference on Mechatronics and Robotics Engineering, ICMRE 2022 - Virtual, Munich, Germany
Duration: 10. Feb 202212. Feb 2022

Conference

Conference8th International Conference on Mechatronics and Robotics Engineering, ICMRE 2022
Country/TerritoryGermany
CityVirtual, Munich
Period10/02/202212/02/2022

Keywords

  • FPGA acceleration
  • high-level synthesis
  • neural network

Fingerprint

Dive into the research topics of 'Open-Source Educational Platform for FPGA Accelerated AI in Robotics'. Together they form a unique fingerprint.

Cite this