MPDrone: FPGA-based Platform for Intelligent Real-time Autonomous Drone Operations

Balint Barna Kövari, Emad Ebeid*

*Corresponding author for this work

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

205 Downloads (Pure)

Abstract

AI-based autonomous onboard drone applications are evolving rapidly and demand dedicated hardware resources to perform effectively. Currently, CPUs and GPUs are commonly used to run these applications.
This paper presents a novel drone platform called MPDrone based on the cutting-edge MPSoC boards that combine FPGA, CPU, and GPU in a single chip.
The proposed platform utilizes the reconfigurable FPGA chip to run heavy AI algorithms and the CPU to execute ROS for processing communication with the drone flight controller and onboard sensors.
The paper introduces the design and implementation of the MPDrone platform, which is validated in simulation and real-world testing through an intelligent object detection and landing use case. The testing results proved the applicability of the proposed FPGA-based platform for AI applications.
Original languageEnglish
Title of host publication2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)
PublisherIEEE
Publication date2021
Pages71-76
ISBN (Electronic)978-1-6654-1764-8
DOIs
Publication statusPublished - 2021
Event2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) - New York University, Manhattan Campus, New York, United States
Duration: 25. Oct 202127. Oct 2021
https://wp.nyu.edu/ssrr2021/

Conference

Conference2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)
LocationNew York University, Manhattan Campus
Country/TerritoryUnited States
CityNew York
Period25/10/202127/10/2021
Internet address

Keywords

  • AI
  • Drone platform
  • FPGA
  • MPSoC
  • ROS
  • simulation
  • testing

Fingerprint

Dive into the research topics of 'MPDrone: FPGA-based Platform for Intelligent Real-time Autonomous Drone Operations'. Together they form a unique fingerprint.

Cite this