Autonomous driving system with feature extraction using a binarized autoencoder

Kota Hisafuru, Ryotaro Negishi, Soma Kawakami, Dai Sato, Kazuki Yamashita, Keisuke Fukada, Nozomu Togawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this study, we present an autonomous driving sys-tem that utilizes a binarized autoencoder implemented on a Field Programmable Gate Array (FPGA). The binarized autoencoder compresses the image into optimal features in this system. The recurrent neural network then determines the following control based on the feature values extracted from the autoencoder and the rotation speed of the motor. We reduced the model size by binarizing the autoencoder because of the limited on-chip memory of the FPGA. We implemented the system on an Ultra96-V2, a board with a programmable logic and processing system. The robot employing our implemented system exhibits robust control by recognizing the entire road marking and road edge line as a feature and drives autonomously along the specified route.

Original languageEnglish
Title of host publicationFPT 2022 - 21st International Conference on Field-Programmable Technology, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665453363
DOIs
Publication statusPublished - 2022
Event21st International Conference on Field-Programmable Technology, FPT 2022 - Hong Kong, Hong Kong
Duration: 2022 Dec 52022 Dec 9

Publication series

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

Conference

Conference21st International Conference on Field-Programmable Technology, FPT 2022
Country/TerritoryHong Kong
CityHong Kong
Period22/12/522/12/9

Keywords

  • autoencoder
  • autonomous driving
  • bina-rized neural network
  • FPGA

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software
  • Computer Science Applications
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Autonomous driving system with feature extraction using a binarized autoencoder'. Together they form a unique fingerprint.

Cite this