Search research articles

Search research articles

Related Experiment Video

Updated: Jun 26, 2026

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

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

Published on: March 2, 2015

Comparison between analog and digital neural network implementations for range-finding applications.

Laurent Gatet¹, Hélène Tap-Béteille, Francis Bony

¹Laboratory of Optoelectronics for Embedded Systems, Electronics, Electrotechnology, Computer Science, Hydraulics, and Telecommunications Engineering School, National Polytechnic Institute, Université de Toulouse, Toulouse Cedex 7, France. gatet@enseeiht.fr

IEEE Transactions on Neural Networks

|January 31, 2009

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

Disappearance of fringes in the self-mixing interferometry sensing scheme: impact of the initial laser mode solution.

Optics letters·2021

Same author

Speckle-insensitive fringe detection method based on Hilbert transform for self-mixing interferometry.

Applied optics·2014

Same author

Laser dynamics in sawtooth-like self-mixing signals.

Optics letters·2012

Same author

MEMS accelerometer embedded in a self-mixing displacement sensor for parasitic vibration compensation.

Optics letters·2011

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

A neural network (NN) was developed to enhance laser range finder capabilities. This system triples distance range and enables surface recognition, improving optoelectronic measurements.

Area of Science:

Optoelectronics
Artificial Intelligence
Embedded Systems

Background:

Phase-shift laser range finders have limited distance range and lack surface recognition.
Traditional systems require analog-to-digital conversions, increasing complexity and power consumption.

Purpose of the Study:

To develop a neural network (NN) for extending the distance range and enabling surface recognition in phase-shift laser range finders.
To compare analog and digital implementations of the NN for optoelectronic measurements.
To propose an optimized mixed architecture for improved performance.

Main Methods:

Developed a multilayer perceptron (MLP) neural network with two inputs, three hidden neurons, and one output.
Implemented the NN using analog complementary metal-oxide-semiconductor (CMOS) technology for optoelectronic measurements.

More Related Videos

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jun 26, 2026

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

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

Published on: March 2, 2015

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Tested the system's performance in terms of distance range, surface discrimination, and laser beam angle variations.

Main Results:

Achieved a threefold increase in distance range compared to systems limited by phase-shift measurement alone.
Successfully discriminated between four different surface types (plastic, glossy paper, painted wall, porous surface).
Demonstrated effective operation at distances from 0.5 m to 1.25 m with beam angles from -pi/6 to pi/6.

Conclusions:

Analog NN implementation offers advantages like small silicon area, low power consumption, and no need for ADCs.
Digital NN implementation provides ease of design, reconfigurability, and embedded weight/bias updates.
A mixed architecture combining analog and digital techniques is proposed for an optimized solution.