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...

Avoidance Learning and Learned Helplessness

Avoidance Learning and Learned Helplessness

Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...

You might also read

Related Articles

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

Sort by

Same author

Late-spring vertical profiles in atmospheric water vapor stable isotopes reveal westerlies moisture transport across the Himalaya into the Asian Water Towers.

Science bulletin·2026

Same author

High-precision micro-thrust measurement instrument: Dynamic structural design and virtual diagnosis optimization.

The Review of scientific instruments·2026

Same author

High-performance RT-DETR model for industrial defect detection with semantic guidance and hierarchical attention.

PloS one·2026

Same author

Vertical conveyor driving the integration of moisture transported by the westerlies to the Asian water towers' atmospheric water cycle.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same author

Early Remaining Useful Life Prediction of Lithium-Ion Batteries Based on a Hybrid Machine Learning Method with Time Series Augmentation.

Sensors (Basel, Switzerland)·2026

Same author

Corrosion Resistance Study of Cyclocarboxypropyl Oleic Acid-Doped Polyaniline/Epoxy Composite Coatings.

Nanomaterials (Basel, Switzerland)·2025

Search research articles

Related Experiment Video

Updated: Mar 29, 2026

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

Robot End-Effectors Adaptive Design Method Based on Embedding Domain Knowledge into Reinforcement Learning.

Yong Zhu¹, Taihua Zhang^1,2,3, Yao Lu^1,3

¹School of Mechanical and Electrical Engineering, Guizhou Normal University, Guiyang 550025, China.

Sensors (Basel, Switzerland)

|March 28, 2026

Summary

This summary is machine-generated.

This study introduces a novel adaptive robot end-effector design method using knowledge graph embedding proximal policy optimization (KGPPO). KGPPO significantly enhances design accuracy and efficiency by integrating domain knowledge and environmental feedback for adaptive parameter optimization.

Keywords:

adaptive design environmental interaction knowledge graph reinforcement learning robot end-effector

More Related Videos

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

Manufacturing, Control, and Performance Evaluation of a Gecko-Inspired Soft Robot

Manufacturing, Control, and Performance Evaluation of a Gecko-Inspired Soft Robot

Published on: June 10, 2020

Related Experiment Videos

Last Updated: Mar 29, 2026

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

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

Manufacturing, Control, and Performance Evaluation of a Gecko-Inspired Soft Robot

Manufacturing, Control, and Performance Evaluation of a Gecko-Inspired Soft Robot

Published on: June 10, 2020

Area of Science:

Robotics
Artificial Intelligence
Mechanical Engineering

Background:

Current robot end-effector design methods lack structured domain knowledge and environmental interaction, limiting design accuracy.
Adaptive optimization is crucial for improving the performance and reliability of robotic systems.

Purpose of the Study:

To propose an adaptive design method for robot end-effectors that embeds domain knowledge and optimizes parameters using reinforcement learning.
To enhance the accuracy, efficiency, and stability of end-effector design through an integrated knowledge graph and reinforcement learning approach.

Main Methods:

Developed an adaptive design method embedding domain knowledge into end-effector design processes.
Utilized reinforcement learning algorithms for adaptive optimization of key design parameters, treating them as environmental variables.
Implemented a simulation environment combining a knowledge graph with a two-finger translational gripper for data acquisition and parameter optimization.

Main Results:

The knowledge graph embedding proximal policy optimization (KGPPO) algorithm demonstrated significant improvements in average reward for gripper length (63.96%) and gripper force (43.09%) when grasping eggs, compared to standard proximal policy optimization (PPO).
KGPPO achieved superior average reward and stability over other algorithms in simulation experiments across three typical tasks.
Identified optimal parameter ranges for the robot end-effector through adaptive optimization.

Conclusions:

The proposed adaptive design method, leveraging knowledge graph embedding and reinforcement learning, substantially improves the efficiency, stability, and accuracy of robot end-effector design parameter optimization.
This approach offers a robust framework for designing complex robotic components by integrating prior knowledge with adaptive learning.
The findings highlight the potential of KGPPO for advancing robotic system design and performance.