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

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

Improving Translational Accuracy

Improving Translational Accuracy

Ampere-Maxwell's Law: Problem-Solving

Ampere-Maxwell's Law: Problem-Solving

A parallel-plate capacitor with capacitance C, whose plates have area A and separation distance d, is connected to a resistor R and a battery of voltage V. The current starts to flow at t = 0. What is the displacement current between the capacitor plates at time t? From the properties of the capacitor, what is the corresponding real current?
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of the...

You might also read

Related Articles

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

Sort by

Same author

Oracle-Guided Masked Contrastive Reinforcement Learning for Visuomotor Policies.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Vision-Based Learning for Drones: A Survey.

IEEE transactions on neural networks and learning systems·2025

Same author

Agile perching maneuvers in birds and morphing-wing drones.

Nature communications·2024

Same author

A Physics-Informed Neural Network Approach to Augmented Dynamics Visual Servoing of Multirotors.

IEEE transactions on cybernetics·2024

Same author

Collaborative Target Search With a Visual Drone Swarm: An Adaptive Curriculum Embedded Multistage Reinforcement Learning Approach.

IEEE transactions on neural networks and learning systems·2023

Same author

Bioinspired wing and tail morphing extends drone flight capabilities.

Science robotics·2020

Search research articles

Related Experiment Video

Updated: Jan 14, 2026

Real-time Electrophysiology: Using Closed-loop Protocols to Probe Neuronal Dynamics and Beyond

Real-time Electrophysiology: Using Closed-loop Protocols to Probe Neuronal Dynamics and Beyond

Published on: June 24, 2015

Physics-Embedded Networks: Improving Convergence and Precision of Physics-Informed Neural Networks for Real-Time

Archit Krishna Kamath, Mir Feroskhan

IEEE Transactions on Cybernetics

|January 12, 2026

Summary

This study introduces physics-embedded neural networks (PENN) for multirotor visual servoing, improving upon physics-informed neural networks (PINN). PENN enhances training efficiency and predictive accuracy, outperforming traditional methods in experiments.

More Related Videos

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

Related Experiment Videos

Last Updated: Jan 14, 2026

Real-time Electrophysiology: Using Closed-loop Protocols to Probe Neuronal Dynamics and Beyond

Real-time Electrophysiology: Using Closed-loop Protocols to Probe Neuronal Dynamics and Beyond

Published on: June 24, 2015

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

Area of Science:

Robotics
Artificial Intelligence
Control Systems

Background:

Classical physics-informed neural networks (PINNs) offer interpretability and data efficiency by integrating physical laws.
However, PINNs often face challenges with convergence and sensitivity to initialization and activation functions.
Multirotor visual servoing requires robust and efficient control strategies.

Purpose of the Study:

To introduce novel physics-embedded neural network (PENN) architectures for enhanced visual servoing in multirotors.
To address the limitations of classical PINNs, specifically poor convergence and sensitivity.
To improve training efficiency and predictive accuracy in learning-based control.

Main Methods:

Proposed two enhanced architectures: layer-wise PENN (L-PENN) and neuron-wise PENN (N-PENN).
Embedded nominal physical dynamics directly into the neural network structure.
Conducted spectral analysis of the Hessian matrix to demonstrate improved convergence properties.
Experimentally validated on a multirotor platform for a visual servoing task.

Main Results:

L-PENN and N-PENN demonstrated significantly improved convergence behavior compared to traditional PINNs.
Experimental validation showed superior tracking performance and reduced training time.
The proposed PENN architectures outperformed classical PINNs and other learning-based control strategies.
Benchmarked results confirmed the effectiveness of the novel architectures.

Conclusions:

Physics-embedded neural networks (PENN), specifically L-PENN and N-PENN, offer substantial improvements over classical PINNs for multirotor visual servoing.
The direct embedding of physical dynamics enhances both training efficiency and predictive accuracy.
Selection criteria for L-PENN and N-PENN are provided based on application-specific needs.