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 Video

Updated: Oct 18, 2025

Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches
07:23

Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches

Published on: August 4, 2014

23.3K

Bioinspired solution to finding passageways in foliage with sonar.

Ruihao Wang1, Rolf Müller1

  • 1Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA 24061, United States of America.

Bioinspiration & Biomimetics
|September 29, 2021
PubMed
Summary

Bats inspire a new method for autonomous navigation systems to find gaps in foliage. A deep-learning approach using echo spectrograms significantly improved gap detection compared to traditional echo energy methods.

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

The Scutulum and the Pre-Auricular Aponeurosis in Bats.

Journal of morphology·2024
Same author

Bioinspiration from bats and new paradigms for autonomy in natural environments.

Bioinspiration & biomimetics·2024
Same author

A validation study for a bat-inspired sonar sensing simulator.

PloS one·2023
Same author

Small-scale location identification in natural environments with deep learning based on biomimetic sonar echoes.

Bioinspiration & biomimetics·2023
Same author

Detection of passageways in natural foliage using biomimetic sonar.

Bioinspiration & biomimetics·2022
Same author

Large-scale recognition of natural landmarks with deep learning based on biomimetic sonar echoes.

Bioinspiration & biomimetics·2022

Area of Science:

  • Bioacoustics
  • Robotics
  • Artificial Intelligence

Background:

  • Autonomous navigation in dense vegetation requires effective gap detection.
  • Traditional methods rely on high-resolution data, unlike bat biosonar.
  • Bats in dense habitats navigate using low-resolution angular sonar.

Purpose of the Study:

  • Investigate bat-like gap detection capabilities using biomimetic sonar.
  • Compare traditional echo energy detection with deep learning approaches.
  • Identify key acoustic features for foliage gap detection.

Main Methods:

  • Utilized a biomimetic sonar head to ensonify artificial hedges.
  • Implemented a conventional echo energy detection algorithm.
  • Applied a deep-learning approach using convolutional neural networks (CNNs) on echo spectrograms.
Keywords:
biosonarclass activation mappingconvolutional neural networkdeep learningfoliage passageway detectiontransparent AI

More Related Videos

Harmonic Radar Tags for Insect Tracking: Lightweight, Low-cost, and Accessible
14:44

Harmonic Radar Tags for Insect Tracking: Lightweight, Low-cost, and Accessible

Published on: May 13, 2025

1.4K
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.7K

Related Experiment Videos

Last Updated: Oct 18, 2025

Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches
07:23

Using Insect Electroantennogram Sensors on Autonomous Robots for Olfactory Searches

Published on: August 4, 2014

23.3K
Harmonic Radar Tags for Insect Tracking: Lightweight, Low-cost, and Accessible
14:44

Harmonic Radar Tags for Insect Tracking: Lightweight, Low-cost, and Accessible

Published on: May 13, 2025

1.4K
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.7K
  • Analyzed results using receiver operating characteristic (ROC) curves and class activation mapping.

    • Main Results:

    • Conventional echo energy detection yielded poor gap detection performance (AUC 0.69-0.75).
    • Deep learning (CNN) on echo spectrograms achieved high performance (AUC 0.94-0.97).
    • Class activation mapping identified the rising flank of echoes as crucial for detection.
    • A simple threshold-crossing time code nearly replicated CNN performance (AUC 0.9-0.95).

    Conclusions:

    • Echo waveforms contain subtle patterns indicative of foliage gaps, even with low-resolution sonar.
    • Deep learning effectively extracts these patterns, outperforming traditional methods.
    • Simple acoustic features, like first threshold-crossing times, can approximate advanced AI performance for this task.