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

Observational Learning

Observational Learning

Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning because...

You might also read

Related Articles

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

Sort by

Same author

Artificial neural network modeling and optimization of an electrochemical biosensor for plasma miR-155-based breast cancer detection.

Scientific reports·2026

Same author

Microfluidic-based nanocarriers for overcoming biological barriers in therapeutic delivery systems.

Nanoscale·2025

Same author

A deep learning model with machine vision system for recognizing type of the food during the food consumption.

Scientific reports·2025

Same author

Extensive vs. intensive sugar beet production: Energy and environmental performance in Hamadan, Iran (a fuzzy clustering approach).

Journal of environmental management·2025

Same author

Improved food recognition using a refined ResNet50 architecture with improved fully connected layers.

Current research in food science·2025

Same author

Comparative analysis of Escherichia coli Nissle 1917 ghosts quality: a study of two chemical methods.

Archives of microbiology·2024

Search research articles

Related Experiment Video

Updated: Jun 30, 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

Intelligent Navigation of a Magnetic Microrobot with Model-Free Deep Reinforcement Learning in a Real-World

Amar Salehi¹, Soleiman Hosseinpour¹, Nasrollah Tabatabaei²

¹Department of Mechanical Engineering of Agricultural Machinery, Faculty of Agriculture, University of Tehran, Karaj 31587-77871, Iran.

|January 23, 2024

Summary

This study demonstrates model-free deep reinforcement learning for autonomous microrobot navigation. Magnetic microrobots achieved precise control and optimal pathfinding in fluid environments, showcasing high success rates.

Keywords:

autonomous navigation deep reinforcement learning intelligent microrobot model-free control

More Related Videos

Utilizing a Reconfigurable Maze System to Enhance the Reproducibility of Spatial Navigation Tests in Rodents

Utilizing a Reconfigurable Maze System to Enhance the Reproducibility of Spatial Navigation Tests in Rodents

Published on: December 2, 2022

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

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

Published on: May 16, 2025

Related Experiment Videos

Last Updated: Jun 30, 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

Utilizing a Reconfigurable Maze System to Enhance the Reproducibility of Spatial Navigation Tests in Rodents

Utilizing a Reconfigurable Maze System to Enhance the Reproducibility of Spatial Navigation Tests in Rodents

Published on: December 2, 2022

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

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

Published on: May 16, 2025

Area of Science:

Robotics
Artificial Intelligence
Control Systems

Background:

Microrobotics offers significant potential in medicine, but faces challenges in autonomous navigation.
Precise control of microrobots in fluid environments is crucial for optimal performance.
Model-free approaches are needed for microrobot control when system models are unavailable.

Purpose of the Study:

To implement and evaluate model-free deep reinforcement learning algorithms for autonomous microrobot navigation.
To assess the performance of Soft Actor-Critic (SAC) and Trust Region Policy Optimization (TRPO) algorithms.
To demonstrate intelligent and precise control of magnetic microrobots in real-world fluid environments.

Main Methods:

Two model-free deep reinforcement learning algorithms, off-policy SAC and on-policy TRPO, were employed.
A disk-shaped magnetic microrobot was utilized for experiments in a real-world fluid environment.
The algorithms were trained to enable the microrobot to navigate to random target positions autonomously.

Main Results:

Both TRPO and SAC algorithms enabled the microrobot to learn optimal paths to target locations.
TRPO demonstrated superior sample efficiency and stability during the training phase.
In the evaluation phase, TRPO achieved a 100% success rate, while SAC achieved a 97.5% success rate.

Conclusions:

Model-free deep reinforcement learning provides effective intelligent and autonomous navigation control for microrobots.
The study highlights the potential of TRPO and SAC algorithms for advancing microrobot capabilities.
These findings contribute to the development of microrobots for diverse applications, particularly in medicine.