Desgin and Implementation of ROS2-based Autonomous Tiny Robot Car with Integration of Multiple ROS2 FPGA Nodes

Hayato Mori; Hayato Amano; Akinobu Mizutani; Eisuke Okazaki; Yuki Konno; Kohei Sada; Tomohiro Ono; Yuma Yoshimoto; Hakaru Tamukoh; Takeshi Ohkawa; Midori Sugaya

doi:10.1109/ICFPT56656.2022.9974433

Desgin and Implementation of ROS2-based Autonomous Tiny Robot Car with Integration of Multiple ROS2 FPGA Nodes

Hayato Mori, Hayato Amano, Akinobu Mizutani, Eisuke Okazaki, Yuki Konno, Kohei Sada, Tomohiro Ono, Yuma Yoshimoto, Hakaru Tamukoh, Takeshi Ohkawa, Midori Sugaya

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper introduces an autonomous tiny robot car equipped with a camera-based lane detection function and a traffic signal/obstacle, pedestrian recognition function. Each function is integrated by Robot Operating System 2 (ROS2), a middleware for robot system development. Autonomous driving without the need for a driver requires not only lane-following driving but also traffic signal recognition and obstacle recognition. These functions are implemented on FPGA, and we evaluated them. According to these results, the execution time of traffic signal recognition by FPGA was 1.2 to 3.4 times faster than CPU execution. YOLOv4 is used for obstacle recognition, which improved mAP by 3.79 points compared to YOLO v3-Tiny.

Original language	English
Title of host publication	FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665453363
DOIs	https://doi.org/10.1109/ICFPT56656.2022.9974433
Publication status	Published - 2022
Event	21st International Conference on Field-Programmable Technology, FPT 2022 - Hong Kong, Hong Kong Duration: 2022 Dec 5 → 2022 Dec 9

Publication series

Name	FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings

Conference

Conference	21st International Conference on Field-Programmable Technology, FPT 2022
Country/Territory	Hong Kong
City	Hong Kong
Period	22/12/5 → 22/12/9

Keywords

FPGA
Robot Operating System 2
YOLOv4-tiny

ASJC Scopus subject areas

Hardware and Architecture
Software
Computer Science Applications
Control and Optimization

Access to Document

10.1109/ICFPT56656.2022.9974433

Cite this

Mori, H., Amano, H., Mizutani, A., Okazaki, E., Konno, Y., Sada, K., Ono, T., Yoshimoto, Y., Tamukoh, H., Ohkawa, T., & Sugaya, M. (2022). Desgin and Implementation of ROS2-based Autonomous Tiny Robot Car with Integration of Multiple ROS2 FPGA Nodes. In FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings (FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICFPT56656.2022.9974433

Desgin and Implementation of ROS2-based Autonomous Tiny Robot Car with Integration of Multiple ROS2 FPGA Nodes. / Mori, Hayato; Amano, Hayato; Mizutani, Akinobu et al.
FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. (FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Mori, H, Amano, H, Mizutani, A, Okazaki, E, Konno, Y, Sada, K, Ono, T, Yoshimoto, Y, Tamukoh, H, Ohkawa, T & Sugaya, M 2022, Desgin and Implementation of ROS2-based Autonomous Tiny Robot Car with Integration of Multiple ROS2 FPGA Nodes. in FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings. FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings, Institute of Electrical and Electronics Engineers Inc., 21st International Conference on Field-Programmable Technology, FPT 2022, Hong Kong, Hong Kong, 22/12/5. https://doi.org/10.1109/ICFPT56656.2022.9974433

Mori H, Amano H, Mizutani A, Okazaki E, Konno Y, Sada K et al. Desgin and Implementation of ROS2-based Autonomous Tiny Robot Car with Integration of Multiple ROS2 FPGA Nodes. In FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2022. (FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings). doi: 10.1109/ICFPT56656.2022.9974433

Mori, Hayato ; Amano, Hayato ; Mizutani, Akinobu et al. / Desgin and Implementation of ROS2-based Autonomous Tiny Robot Car with Integration of Multiple ROS2 FPGA Nodes. FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. (FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings).

@inproceedings{d3d32d96159b4487bc17c6f8c456c26f,

title = "Desgin and Implementation of ROS2-based Autonomous Tiny Robot Car with Integration of Multiple ROS2 FPGA Nodes",

abstract = "This paper introduces an autonomous tiny robot car equipped with a camera-based lane detection function and a traffic signal/obstacle, pedestrian recognition function. Each function is integrated by Robot Operating System 2 (ROS2), a middleware for robot system development. Autonomous driving without the need for a driver requires not only lane-following driving but also traffic signal recognition and obstacle recognition. These functions are implemented on FPGA, and we evaluated them. According to these results, the execution time of traffic signal recognition by FPGA was 1.2 to 3.4 times faster than CPU execution. YOLOv4 is used for obstacle recognition, which improved mAP by 3.79 points compared to YOLO v3-Tiny.",

keywords = "FPGA, Robot Operating System 2, YOLOv4-tiny",

author = "Hayato Mori and Hayato Amano and Akinobu Mizutani and Eisuke Okazaki and Yuki Konno and Kohei Sada and Tomohiro Ono and Yuma Yoshimoto and Hakaru Tamukoh and Takeshi Ohkawa and Midori Sugaya",

note = "Funding Information: ACKNOWLEDGMENT This work was partly supported by JST CREST Grant Number JPMJCR19K1, Japan. Publisher Copyright: {\textcopyright} 2022 IEEE.; 21st International Conference on Field-Programmable Technology, FPT 2022 ; Conference date: 05-12-2022 Through 09-12-2022",

year = "2022",

doi = "10.1109/ICFPT56656.2022.9974433",

language = "English",

series = "FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings",

}

TY - GEN

T1 - Desgin and Implementation of ROS2-based Autonomous Tiny Robot Car with Integration of Multiple ROS2 FPGA Nodes

AU - Mori, Hayato

AU - Amano, Hayato

AU - Mizutani, Akinobu

AU - Okazaki, Eisuke

AU - Konno, Yuki

AU - Sada, Kohei

AU - Ono, Tomohiro

AU - Yoshimoto, Yuma

AU - Tamukoh, Hakaru

AU - Ohkawa, Takeshi

AU - Sugaya, Midori

PY - 2022

Y1 - 2022

N2 - This paper introduces an autonomous tiny robot car equipped with a camera-based lane detection function and a traffic signal/obstacle, pedestrian recognition function. Each function is integrated by Robot Operating System 2 (ROS2), a middleware for robot system development. Autonomous driving without the need for a driver requires not only lane-following driving but also traffic signal recognition and obstacle recognition. These functions are implemented on FPGA, and we evaluated them. According to these results, the execution time of traffic signal recognition by FPGA was 1.2 to 3.4 times faster than CPU execution. YOLOv4 is used for obstacle recognition, which improved mAP by 3.79 points compared to YOLO v3-Tiny.

AB - This paper introduces an autonomous tiny robot car equipped with a camera-based lane detection function and a traffic signal/obstacle, pedestrian recognition function. Each function is integrated by Robot Operating System 2 (ROS2), a middleware for robot system development. Autonomous driving without the need for a driver requires not only lane-following driving but also traffic signal recognition and obstacle recognition. These functions are implemented on FPGA, and we evaluated them. According to these results, the execution time of traffic signal recognition by FPGA was 1.2 to 3.4 times faster than CPU execution. YOLOv4 is used for obstacle recognition, which improved mAP by 3.79 points compared to YOLO v3-Tiny.

KW - FPGA

KW - Robot Operating System 2

KW - YOLOv4-tiny

UR - http://www.scopus.com/inward/record.url?scp=85145559746&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85145559746&partnerID=8YFLogxK

U2 - 10.1109/ICFPT56656.2022.9974433

DO - 10.1109/ICFPT56656.2022.9974433

M3 - Conference contribution

AN - SCOPUS:85145559746

T3 - FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings

BT - FPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 21st International Conference on Field-Programmable Technology, FPT 2022

Y2 - 5 December 2022 through 9 December 2022

ER -

Desgin and Implementation of ROS2-based Autonomous Tiny Robot Car with Integration of Multiple ROS2 FPGA Nodes

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this