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

Machines: Problem Solving II

Machines: Problem Solving II

Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. Consider a lifting tong carrying a 100 kg load. It comprises movable sections DAF and CBG linked together with member AB.

One-Degree-of-Freedom System

One-Degree-of-Freedom System

In mechanical engineering, one-degree-of-freedom systems form the basis of a wide range of electrical and mechanical components. Using these models, engineers can predict the behavior of various parts in a larger system, which gives them insight into how different forces interact with each other.
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...

You might also read

Related Articles

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

Sort by

Same author

Editorial: Language, affordance and physics in robot cognition and intelligent systems.

Frontiers in robotics and AI·2024

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 27, 2025

Operation of the Collaborative Composite Manufacturing CCM System

Operation of the Collaborative Composite Manufacturing CCM System

Published on: October 1, 2019

Learning to Centralize Dual-Arm Assembly.

Marvin Alles¹, Elie Aljalbout¹

¹Technical University of Munich, Munich, Germany.

Frontiers in Robotics and AI

|April 11, 2022

Summary

This summary is machine-generated.

This study introduces a novel reinforcement learning (RL) framework for dual-arm robotic manipulation, enabling robots to perform complex assembly tasks in unstructured environments with minimal prior modeling. The approach demonstrates successful real-world transfer and robustness.

Keywords:

assembly centralized control dual-arm manipulation peg-in-hole reinforcement learning robotics sim-to-real transfer

More Related Videos

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

Robotic Mirror Therapy System for Functional Recovery of Hemiplegic Arms

Robotic Mirror Therapy System for Functional Recovery of Hemiplegic Arms

Published on: August 15, 2016

Related Experiment Videos

Last Updated: Sep 27, 2025

Operation of the Collaborative Composite Manufacturing CCM System

Operation of the Collaborative Composite Manufacturing CCM System

Published on: October 1, 2019

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

Robotic Mirror Therapy System for Functional Recovery of Hemiplegic Arms

Robotic Mirror Therapy System for Functional Recovery of Hemiplegic Arms

Published on: August 15, 2016

Area of Science:

Robotics
Artificial Intelligence
Machine Learning

Background:

Robotic manipulators are crucial in manufacturing but struggle in unstructured environments.
Dual-arm manipulation research using reinforcement learning (RL) is limited.
Classical control for dual-arm tasks requires complex modeling.

Purpose of the Study:

To explore model-free reinforcement learning for dual-arm assembly tasks.
To develop a flexible framework with minimal environmental assumptions.
To enable general dual-arm manipulation beyond specific assembly tasks.

Main Methods:

A modular approach using two decentralized single-arm controllers.
Coupling controllers with a single centralized learned policy.
Utilizing sparse rewards to minimize modeling efforts.

Main Results:

Successful dual-arm assembly demonstrated, particularly in peg-in-hole tasks.
Effective transfer of trained policies from simulation to the real world (zero-shot).
Robustness shown against disturbances and position uncertainties.

Conclusions:

The proposed modular RL framework is effective for dual-arm manipulation.
Reduced modeling and sparse rewards facilitate adaptability and real-world deployment.
The approach shows promise for complex robotic tasks in unstructured settings.