Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Obstacle avoidance for power wheelchair using bayesian neural network.

Hoang T Trieu1, Hung T Nguyen, Keith Willey

  • 1Faculty of Engineering, University of Technology, Sydney, Broadway, NSW 2007, Australia. thtrieu@eng.uts.edu.au

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
|November 16, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Temperature-dependent ion migration underlies sequence-specific collapse of unstructured RNA.

Biophysical journal·2026
Same author

Poly(ADP-ribose) (PAR) exhibits ion-dependent structural properties distinct from RNA.

Nucleic acids research·2026
Same author

Small-Molecule Drug Discovery Targeting RNAs: Hope or Hype?

Journal of medicinal chemistry·2026
Same author

RNA Structural Complexity Dictates Its Ion Atmosphere.

The journal of physical chemistry letters·2025
Same author

Minimal models for RNA simulations.

Current opinion in structural biology·2025
Same author

Sizes, conformational fluctuations, and SAXS profiles for intrinsically disordered proteins.

Protein science : a publication of the Protein Society·2025

This study introduces a real-time obstacle avoidance algorithm using Bayesian neural networks for laser-based wheelchairs. The system effectively navigates autonomous tasks, demonstrating potential for assistive technology.

Area of Science:

  • Robotics and Artificial Intelligence
  • Assistive Technology
  • Machine Learning

Background:

  • Developing real-time obstacle avoidance is crucial for autonomous wheelchair navigation.
  • Laser-based systems offer precise environmental sensing capabilities.
  • Bayesian neural networks provide a probabilistic approach to machine learning, suitable for complex decision-making.

Purpose of the Study:

  • To present a novel real-time obstacle avoidance algorithm for laser-based wheelchair systems.
  • To leverage Bayesian neural networks for enhanced autonomous navigation.
  • To evaluate the effectiveness of the proposed algorithm in practical applications.

Main Methods:

  • Real-time processing of laser data, adapted for wheelchair dimensions to determine free space.

Related Experiment Videos

  • Data acquisition for training a neural network with relevant navigation patterns.
  • Application of a Bayesian framework to optimize neural network architecture.
  • Supervised training of the Bayesian neural network using Bayesian rules for the obstacle avoidance task.

    • Main Results:

    • The algorithm successfully processed laser data in real-time to identify navigable free space.
    • The Bayesian framework facilitated the determination of an optimal neural network structure.
    • The trained Bayesian neural network effectively performed the obstacle avoidance task for the wheelchair system.

    Conclusions:

    • The proposed Bayesian neural network approach offers an effective solution for real-time obstacle avoidance in laser-based wheelchairs.
    • This method demonstrates significant potential for improving autonomous navigation in assistive technologies.
    • Bayesian neural networks are a promising tool for developing advanced assistive robotic systems.