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

Randomized Experiments

Randomized Experiments

The randomization process involves assigning study participants randomly to experimental or control groups based on their probability of being equally assigned. Randomization is meant to eliminate selection bias and balance known and unknown confounding factors so that the control group is similar to the treatment group as much as possible. A computer program and a random number generator can be used to assign participants to groups in a way that minimizes bias.
Simple randomization
Simple...

Random and Systematic Errors

Random and Systematic Errors

Scientists always try their best to record measurements with the utmost accuracy and precision. However, sometimes errors do occur. These errors can be random or systematic. Random errors are observed due to the inconsistency or fluctuation in the measurement process, or variations in the quantity itself that is being measured. Such errors fluctuate from being greater than or less than the true value in repeated measurements. Consider a scientist measuring the length of an earthworm using a...

You might also read

Related Articles

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

Sort by

Same author

RNA-binding protein ZMAT3 protects against MASLD by regulating SEPT11 mRNA stability.

Cellular signalling·2026

Same author

Catecholamine precursor modulation of human exploration: Evidence from a large gender-balanced sample.

PLoS computational biology·2026

Same author

Uncoupling tumor immunogenicity from cell death with platinum(IV)-antibody conjugates.

National science review·2026

Same author

Regio- and Stereoselective Synthesis of Imidazolidinones by Diamination of Alkenyl Thianthrenium Salts with Urea.

Organic letters·2026

Same author

The earlier you know, the smoother you act: anticipatory control in solo and dyadic juggling.

Experimental brain research·2026

Same author

Exploration Strategies and Feature Prioritisation in Contour-based Haptic Perception of 2D Shape.

IEEE transactions on haptics·2026

Same journal

Editorial: Synergizing large language models and computational intelligence for advanced robotic systems.

Frontiers in robotics and AI·2026

Same journal

Editorial: Innovations in industry 4.0: advancing mobility and manipulation in robotics.

Frontiers in robotics and AI·2026

Same journal

MPM-based simulation and bounded-error compression of material points for magnetic tactile sensors.

Frontiers in robotics and AI·2026

Same journal

Torque-sensorless control of a high-ratio, backdrivable Wolfrom-gearbox for safe human-centered robotics.

Frontiers in robotics and AI·2026

Same journal

The implications of robot navigation in social space: perceptual effects of socially aware and baseline navigation.

Frontiers in robotics and AI·2026

Same journal

DPTG: diffusion policy with tactile feasibility guidance.

Frontiers in robotics and AI·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 25, 2025

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

Robot Learning From Randomized Simulations: A Review.

Fabio Muratore^1,2, Fabio Ramos^3,4, Greg Turk⁵

¹Intelligent Autonomous Systems Group, Technical University of Darmstadt, Darmstadt, Germany.

Frontiers in Robotics and AI

|May 2, 2022

Summary

This summary is machine-generated.

Deep learning in robotics requires extensive data, often gathered via simulation. Domain randomization in simulations helps bridge the reality gap for improved robot control policies.

Keywords:

domain randomization reality gap reinforcement learning robotics sim-to-real simulation simulation optimization bias

More Related Videos

Designing and Implementing Nervous System Simulations on LEGO Robots

Designing and Implementing Nervous System Simulations on LEGO Robots

Published on: May 25, 2013

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

Related Experiment Videos

Last Updated: Sep 25, 2025

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

Designing and Implementing Nervous System Simulations on LEGO Robots

Designing and Implementing Nervous System Simulations on LEGO Robots

Published on: May 25, 2013

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

Area of Science:

Robotics
Machine Learning
Artificial Intelligence

Background:

Deep learning in robotics necessitates large datasets, which are costly to acquire on physical platforms.
Simulation offers an efficient alternative for data generation in robotics research.
The discrepancy between simulated and real-world environments, known as the "reality gap," poses a challenge for sim-to-real transfer.

Purpose of the Study:

To review sim-to-real research in robotics.
To explore methods for overcoming the reality gap in robot learning.
To focus on domain randomization as a key technique.

Main Methods:

Comprehensive literature review of sim-to-real techniques in robotics.
Analysis of domain randomization as a method for learning robot control policies.
Examination of how randomized simulations facilitate knowledge transfer.

Main Results:

Domain randomization is a powerful technique for learning robot control policies in simulation.
Randomized simulations can effectively mitigate the reality gap.
Knowledge transfer from simulation to real robots is enhanced through domain randomization.

Conclusions:

Domain randomization is crucial for successful sim-to-real transfer in robotics.
Modifying simulations with domain randomization is key to overcoming the reality gap.
This review highlights the importance of domain randomization for advancing robotic learning.