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

Balint  Barna Kövari; Emad Ebeid

doi:10.1109/SSRR53300.2021.9597857

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 proceeding › Article in proceedings › Research › peer-review

938 Downloads (Pure)

https://www.youtube.com/watch?v=haIMd0PNrdU

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 language	English
Title of host publication	2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)
Publisher	IEEE
Publication date	2021
Pages	71-76
ISBN (Electronic)	978-1-6654-1764-8
DOIs	https://doi.org/10.1109/SSRR53300.2021.9597857
Publication status	Published - 2021
Event	2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) - New York University, Manhattan Campus, New York, United States Duration: 25. Oct 2021 → 27. Oct 2021 https://wp.nyu.edu/ssrr2021/

Conference

Conference	2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)
Location	New York University, Manhattan Campus
Country/Territory	United States
City	New York
Period	25/10/2021 → 27/10/2021
Internet address	https://wp.nyu.edu/ssrr2021/

Keywords

AI
Drone platform
FPGA
MPSoC
ROS
simulation
testing

Documents & Links

10.1109/SSRR53300.2021.9597857

Open Access VersionAccepted manuscript, 1.45 MB

Cite this

@inproceedings{cf229477e1314b7e9bbe7afa54dc4169,

title = "MPDrone: FPGA-based Platform for Intelligent Real-time Autonomous Drone Operations",

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.",

keywords = "AI, Drone platform, FPGA, MPSoC, ROS, simulation, testing",

author = "{Barna K{\"o}vari}, Balint and Emad Ebeid",

year = "2021",

doi = "10.1109/SSRR53300.2021.9597857",

language = "English",

pages = "71--76",

booktitle = "2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)",

publisher = "IEEE",

address = "United States",

note = "2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) ; Conference date: 25-10-2021 Through 27-10-2021",

url = "https://wp.nyu.edu/ssrr2021/",

}

Barna Kövari, B & Ebeid, E 2021, MPDrone: FPGA-based Platform for Intelligent Real-time Autonomous Drone Operations. in 2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR). IEEE, pp. 71-76, 2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), New York, United States, 25/10/2021. https://doi.org/10.1109/SSRR53300.2021.9597857

TY - GEN

T1 - MPDrone

T2 - 2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)

AU - Barna Kövari, Balint

AU - Ebeid, Emad

PY - 2021

Y1 - 2021

N2 - 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.

AB - 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.

KW - AI

KW - Drone platform

KW - FPGA

KW - MPSoC

KW - ROS

KW - simulation

KW - testing

UR - https://www.youtube.com/watch?v=haIMd0PNrdU

U2 - 10.1109/SSRR53300.2021.9597857

DO - 10.1109/SSRR53300.2021.9597857

M3 - Article in proceedings

SP - 71

EP - 76

BT - 2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)

PB - IEEE

Y2 - 25 October 2021 through 27 October 2021

ER -

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

Abstract

Conference

Keywords

Documents & Links

Other files and links

Fingerprint

EU H2020: Drones4Safety

Cite this

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

Abstract

Conference

Keywords

Documents & Links

Other files and links

Fingerprint

Related projects

EU H2020: Drones4Safety

Cite this