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: Feb 25, 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

10.9K

Obstacle Avoidance and Target Acquisition for Robot Navigation Using a Mixed Signal Analog/Digital Neuromorphic

Moritz B Milde1, Hermann Blum1, Alexander Dietmüller1

  • 1Institute of Neuroinformatics, University of Zurich and ETH ZurichZurich, Switzerland.

Frontiers in Neurorobotics
|July 28, 2017
PubMed
Summary

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

Algorithm-hardware co-design of neuromorphic networks with dual memory pathways.

Nature machine intelligence·2026
Same author

Spiking neural network decoders of finger forces from high-density intramuscular microelectrode arrays.

Nature communications·2026
Same author

Bioinspired spiking architecture enables energy constrained touch encoding.

Nature communications·2026
Same author

How heterogeneity shapes dynamics and computation in the brain.

Neuron·2025
Same author

Biological fidelity: The engine driving the neuromorphic renaissance.

Proceedings of the National Academy of Sciences of the United States of America·2025
Same author

SNI-SLAM++: Tightly-Coupled Semantic Neural Implicit SLAM.

IEEE transactions on pattern analysis and machine intelligence·2025

This study demonstrates autonomous obstacle avoidance and target acquisition in robots using neuromorphic hardware. The developed system efficiently processes sensor data for real-time navigation, overcoming device variability challenges.

Area of Science:

  • Robotics
  • Neuroscience
  • Computer Engineering

Background:

  • Neuromorphic hardware offers low-power, parallel, and event-driven computing, mimicking biological neural networks.
  • This architecture presents an alternative to traditional von Neumann computing for energy-efficient, low-latency robotic control.
  • Analog circuits in neuromorphic processors introduce device variability, a challenge for reliable implementation.

Purpose of the Study:

  • To develop an autonomous neuromorphic agent for obstacle avoidance and target acquisition.
  • To interface a neuromorphic processor (ROLLS) with a dynamic vision sensor (DVS) on a robotic vehicle.
  • To create a neural network architecture resilient to device variability for robust robotic navigation.

Main Methods:

  • Interfacing a mixed-signal analog-digital neuromorphic processor (ROLLS) with a neuromorphic dynamic vision sensor (DVS).
Keywords:
dynamic neural fieldsdynamic vision sensorneuromorphic controllerneuroroboticsobstacle avoidancetarget acquisition

More Related Videos

A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents
06:25

A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents

Published on: May 16, 2025

1.5K
An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
10:51

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

Published on: March 10, 2011

14.3K

Related Experiment Videos

Last Updated: Feb 25, 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

10.9K
A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents
06:25

A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents

Published on: May 16, 2025

1.5K
An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
10:51

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

Published on: March 10, 2011

14.3K
  • Developing a neural network architecture designed to tolerate device variability.
  • Implementing biologically-inspired dynamics for obstacle avoidance and a Dynamic Neural Field for target acquisition.

    • Main Results:

    • Demonstrated a robust neuromorphic agent capable of obstacle avoidance and target acquisition in diverse environmental conditions.
    • Verified the network's resilience to device variability and performance in scenarios with moving obstacles, targets, clutter, and poor lighting.
    • Successfully implemented obstacle avoidance using biologically-inspired dynamics and target acquisition via a Dynamic Neural Field on spiking neuromorphic hardware.

    Conclusions:

    • Neuromorphic hardware, combined with DVS, enables efficient and low-latency robotic navigation tasks like obstacle avoidance and target acquisition.
    • The developed neural network architecture effectively addresses device variability challenges inherent in analog neuromorphic circuits.
    • This work showcases a practical implementation of autonomous robotic behaviors using mixed-signal analog/digital neuromorphic hardware.