EUVIMEDEUVIMED entdecken
Crossref

Development and Mobile Deployment of a Stair Recognition System for Human–Robot Locomotion

Andrew Garrett Kurbis, Alex Mihailidis, Brokoslaw Laschowski

IEEE Transactions on Medical Robotics and Bionics · 2024-02 · 6 (1) · 271-280

DOI: 10.1109/tmrb.2024.3349602 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Robotics and Bionics, 2024-02. Verfasst von Andrew Garrett Kurbis und 2 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: AGEWELL Networks of Centres of Excellence (NCE) Program, Vector Institute for Artificial Intelligence, Canada.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Environment sensing and recognition can improve the safety and autonomy of human-robot locomotion, especially during transitions between environmental states such as walking to and from stairs. However, accurate and real-time perception on edge devices with limited computational resources is an open problem. Here we present the development and mobile deployment of StairNet - a vision-based automated stair recognition system powered by deep learning. Building on ExoNet - the largest open-source dataset of egocentric images of real-world walking environments - we designed a new dataset specifically for stair recognition with over 515,000 images. We then developed a lightweight and efficient convolutional neural network for image classification, which accurately predicted complex stair environments with 98.4% accuracy. We also studied different model compression and optimization methods and deployed our system on several mobile devices running a custom-designed iOS application with onboard accelerators using CPU, GPU, and/or NPU backend computing. Of the designs that we tested, our highest performing system showed negligible reductions in classification accuracy due to the model conversion for mobile deployment and achieved an inference time of 2.75 ms on an iPhone 11. The high speed and accuracy of the StairNet system on edge devices opens new opportunities for autonomous control and planning of robotic prosthetic legs, exoskeletons, and other assistive technologies for human locomotion.

Förderung

  • AGEWELL Networks of Centres of Excellence (NCE) Program
  • Vector Institute for Artificial Intelligence, Canada

Zitieren

APA

Kurbis, A. G., Mihailidis, A., & Laschowski, B. (2024). Development and Mobile Deployment of a Stair Recognition System for Human–Robot Locomotion. IEEE Transactions on Medical Robotics and Bionics, 6(1), 271-280. https://doi.org/10.1109/tmrb.2024.3349602

Vancouver

Kurbis AG, Mihailidis A, Laschowski B. Development and Mobile Deployment of a Stair Recognition System for Human–Robot Locomotion. IEEE Transactions on Medical Robotics and Bionics. 2024;6(1):271-280. doi:10.1109/tmrb.2024.3349602

BibTeX
@article{Kurbis2024,
  author = {Kurbis, Andrew Garrett and Mihailidis, Alex and Laschowski, Brokoslaw},
  title = {Development and Mobile Deployment of a Stair Recognition System for Human–Robot Locomotion},
  journal = {IEEE Transactions on Medical Robotics and Bionics},
  year = {2024},
  volume = {6},
  number = {1},
  pages = {271--280},
  doi = {10.1109/tmrb.2024.3349602}
}
Kostenlos starten →