DogSurf: Quadruped Robot Capable of GRU-based Surface Recognition for Blind Person Navigation
Name
3610978.3640606.pdf
Size
1.98 MB
Format
Adobe PDF
Checksum (MD5)
836edc30af529979a2e8ebcf9e783a65
Author(s)
Bazhenov, Artem
Berman, Vladimir
Satsevich, Sergei
Shalopanova, Olga
Cabrera, Miguel
Lykov, Artem
Tsetserukou, Dzmitry
Date Issued
March 11, 2024
Publisher
ACM|Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction
Citation
Bazhenov, Artem, Berman, Vladimir, Satsevich, Sergei, Shalopanova, Olga, Cabrera, Miguel et al. 2024. "DogSurf: Quadruped Robot Capable of GRU-based Surface Recognition for Blind Person Navigation."
Version
Final published version
Abstract
This paper introduces DogSurf - a newapproach of using quadruped robots to help visually impaired people navigate in real world. The presented method allows the quadruped robot to detect slippery surfaces, and to use audio and haptic feedback to inform the user when to stop. A state-of-the-art GRU-based neural network architecture with mean accuracy of 99.925% was proposed for the task of multiclass surface classification for quadruped robots. A dataset was collected on a Unitree Go1 Edu robot. The dataset and code have been posted to the public domain.
Description
HRI 2024, March 11–14, 2024, Boulder, Colorado, USA
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3610978.3640606
