Search research articles

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

Related Concept Videos

Prismatic Beams: Problem Solving

Prismatic Beams: Problem Solving

In the design of a supported timber beam subjected to a distributed load, both the beam's physical dimensions and the timber's characteristics, such as its grade and species, are critical. These factors determine the allowable stress values, which are crucial for calculating the necessary beam depth to ensure structural integrity and safety.
The design begins with analyzing the beam as a free body to identify moments and force balances, thereby determining support reactions. Next, the...

Residuals and Least-Squares Property

Residuals and Least-Squares Property

The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...

You might also read

Related Articles

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

Sort by

Same author

Decoding orbital angular momentum in turbid tissue-like scattering medium with deep learning.

Scientific reports·2026

Same author

CAT-GAN-UKF: category-aware online adaptive unscented kalman filtering for trajectory-level multi-object state estimation.

Scientific reports·2026

Same author

Synergistic microscopic platform for probing molecular interaction on mitochondria-lysosome contact membrane.

Biomedical optics express·2026

Same author

Visual cortex speckle imaging for shape recognition.

Scientific reports·2025

Same author

Integrating GAN-based machine learning with nonlinear Kalman filtering for enhanced state estimation.

Scientific reports·2025

Same author

Non-contact optical sensing of vocal fold paralysis using speckle pattern analysis.

Biomedical optics express·2025

Same journal

DNA origami snaps into place.

Science robotics·2026

Same journal

A high-endurance DNA origami snap-through switch for functional nanoscale control.

Science robotics·2026

Same journal

Learning flight navigation like a honey bee.

Science robotics·2026

Same journal

Is your robot vacuum cleaner spying on you?

Science robotics·2026

Same journal

Do people feel safe in a robot's presence?

Science robotics·2026

Same journal

Stop chasing identical outcomes in HRI replication: Learn from the differences.

Science robotics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Oct 10, 2025

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Published on: February 12, 2014

Coherent, super-resolved radar beamforming using self-supervised learning.

Itai Orr^1,2, Moshik Cohen², Harel Damari²

¹Faculty of Engineering and the Institute for Nanotechnology and Advanced Materials, Bar Ilan University, Ramat-Gan, Israel.

Science Robotics

|December 15, 2021

Summary

This summary is machine-generated.

This study introduces Radar signal Reconstruction using Self Supervision (R2S2), a novel deep learning method enhancing automotive radar angular resolution by 4x without adding hardware. This breakthrough addresses autonomous vehicle sensing limitations effectively.

More Related Videos

Shaping the Amplitude and Phase of Laser Beams by Using a Phase-only Spatial Light Modulator

Shaping the Amplitude and Phase of Laser Beams by Using a Phase-only Spatial Light Modulator

Published on: January 28, 2019

Differential Imaging of Biological Structures with Doubly-resonant Coherent Anti-stokes Raman Scattering CARS

Differential Imaging of Biological Structures with Doubly-resonant Coherent Anti-stokes Raman Scattering CARS

Published on: October 17, 2010

Related Experiment Videos

Last Updated: Oct 10, 2025

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Published on: February 12, 2014

Shaping the Amplitude and Phase of Laser Beams by Using a Phase-only Spatial Light Modulator

Shaping the Amplitude and Phase of Laser Beams by Using a Phase-only Spatial Light Modulator

Published on: January 28, 2019

Differential Imaging of Biological Structures with Doubly-resonant Coherent Anti-stokes Raman Scattering CARS

Differential Imaging of Biological Structures with Doubly-resonant Coherent Anti-stokes Raman Scattering CARS

Published on: October 17, 2010

Area of Science:

Automotive Engineering
Signal Processing
Artificial Intelligence

Background:

High-resolution automotive radar is crucial for autonomous vehicles but current systems face angular resolution limitations.
Increasing physical channels to improve resolution leads to higher complexity, cost, and reduced robustness.
A technological gap exists between autonomous vehicle demands and existing radar capabilities.

Purpose of the Study:

To introduce Radar signal Reconstruction using Self Supervision (R2S2) for enhancing automotive radar angular resolution.
To provide an alternative to increasing physical channels, thereby reducing system complexity and cost.
To demonstrate a significant improvement in angular resolution using a self-supervised deep learning approach.

Main Methods:

Developed R2S2, a family of algorithms utilizing deep neural networks (DNNs).
Employed complex range-Doppler radar data as input for the DNN.
Utilized a self-supervised training method with a multi-representation space loss function.

Main Results:

Achieved a 4x improvement in angular resolution.
Validated performance using real-world datasets from urban and highway environments.
Demonstrated effectiveness in both clear and rainy weather conditions.

Conclusions:

R2S2 substantially improves automotive radar angular resolution without increasing physical channels.
The self-supervised DNN approach offers a cost-effective and robust solution for autonomous vehicle sensing.
This method bridges the technological gap in radar sensing for autonomous driving.