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 Concept Videos

One-Degree-of-Freedom System01:24

One-Degree-of-Freedom System

In mechanical engineering, one-degree-of-freedom systems form the basis of a wide range of electrical and mechanical components. Using these models, engineers can predict the behavior of various parts in a larger system, which gives them insight into how different forces interact with each other.
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...

You might also read

Related Articles

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

Sort by
Same author

The neurobench framework for benchmarking neuromorphic computing algorithms and systems.

Nature communications·2025
Same author

Tracking Single Molecule Dynamics in the Adult <i>Drosophila</i> Brain.

eNeuro·2021
Same author

A Method for Evaluating and Selecting Suitable Hardware for Deployment of Embedded System on UAVs.

Sensors (Basel, Switzerland)·2020
Same author

Automating analysis of vegetation with computer vision: Cover estimates and classification.

Ecology and evolution·2018

Related Experiment Video

Updated: Jun 27, 2026

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.4K

A compact neuromorphic system for ultra-energy-efficient, on-device robot localization.

Adam D Hines1, Michael Milford1, Tobias Fischer1

  • 1QUT Centre for Robotics, Queensland University of Technology, 2 George St, Brisbane, QLD 4001, Australia.

Science Robotics
|June 18, 2025
PubMed
Summary

Neuromorphic computing enables efficient robotic localization. A new system, LENS, uses spiking neural networks for accurate, low-power visual place recognition on edge devices, outperforming conventional methods.

More Related Videos

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS
05:25

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Published on: June 7, 2024

1.4K
A Real-Time Wearable Electromyography Measurement System for Small Animals
05:00

A Real-Time Wearable Electromyography Measurement System for Small Animals

Published on: November 15, 2024

866

Related Experiment Videos

Last Updated: Jun 27, 2026

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.4K
Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS
05:25

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Published on: June 7, 2024

1.4K
A Real-Time Wearable Electromyography Measurement System for Small Animals
05:00

A Real-Time Wearable Electromyography Measurement System for Small Animals

Published on: November 15, 2024

866

Area of Science:

  • Robotics
  • Neuromorphic Engineering
  • Computer Vision

Background:

  • Edge robotic localization and navigation face significant computational and energy constraints.
  • Conventional visual place recognition systems are resource-intensive, limiting their use on small, long-endurance platforms.
  • Biorealistic neuromorphic networks are complex for real-time edge deployment.

Purpose of the Study:

  • To develop an energy-efficient neuromorphic localization system for edge robotics.
  • To demonstrate competitive place recognition performance with reduced model size and power consumption.
  • To enable accurate, on-device localization for resource-constrained robots.

Main Methods:

  • Integration of spiking neural networks, event-based vision sensors, and neuromorphic processors on a SynSense Speck chip.
  • Development of the locational encoding with neuromorphic systems (LENS) for visual place recognition.
  • Real-time deployment on a hexapod robot for large-scale traversal testing.

Main Results:

  • LENS achieved competitive place recognition over 8 km of traversal.
  • Models used were small (180 KB, 44,000 parameters) and consumed <8% of conventional methods' energy.
  • LENS demonstrated comparable precision to the sum of absolute differences benchmark.

Conclusions:

  • LENS offers an accurate, fully neuromorphic solution for energy-efficient robotic localization.
  • The system enables large-scale, on-device deployment for resource-constrained robots.
  • Hardware-algorithm fusion is key for efficient neuromorphic edge computing.