Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jul 25, 2025

Investigating Motor Skill Learning Processes with a Robotic Manipulandum
07:52

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

8.8K

A High-Efficient Reinforcement Learning Approach for Dexterous Manipulation.

Jianhua Zhang1, Xuanyi Zhou2, Jinyu Zhou2

  • 1College of Mechanical Engineering, Beijing University of Science and Technology, Beijing 100083, China.

Biomimetics (Basel, Switzerland)
|June 27, 2023
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Study on Auxiliary Rehabilitation System of Hand Function Based on Machine Learning with Visual Sensors.

Sensors (Basel, Switzerland)·2026
Same author

Design of a Hierarchical Control Architecture for Fully-Driven Multi-Fingered Dexterous Hand.

Biomimetics (Basel, Switzerland)·2025
Same author

Structural and Experimental Study of a Multi-Finger Synergistic Adaptive Humanoid Dexterous Hand.

Biomimetics (Basel, Switzerland)·2025
Same author

Design and Control of a Tendon-Driven Robotic Finger Based on Grasping Task Analysis.

Biomimetics (Basel, Switzerland)·2024
Same author

A Semi-Autonomous Hierarchical Control Framework for Prosthetic Hands Inspired by Dual Streams of Human.

Biomimetics (Basel, Switzerland)·2024
Same author

Dynamic and Real-Time Object Detection Based on Deep Learning for Home Service Robots.

Sensors (Basel, Switzerland)·2023
Same journal

Multiphysics Investigation on Thermal Characteristics of Internal Bio-Inspired V-Ribbed Cooling Channels for Outer Rotor PMSM.

Biomimetics (Basel, Switzerland)·2026
Same journal

Smart Logistics Model for Supply Chain Management via Brain-Inspired Geometric Deep Networks.

Biomimetics (Basel, Switzerland)·2026
Same journal

A Systematic Taxonomy of the Sunflower Optimization Algorithm: Variants, Hybridization Strategies, Applications, and Research Directions.

Biomimetics (Basel, Switzerland)·2026
Same journal

Toward a Compositional Theory of Trust in Embodied Intelligence: A QNLP Framework for Modeling Context, Interaction, and Trustworthiness.

Biomimetics (Basel, Switzerland)·2026
Same journal

Empirical Logic for Bio-Inspired Soft Computing: Illustrative Applications in Control Engineering and Cluster Analysis.

Biomimetics (Basel, Switzerland)·2026
Same journal

A Modified Multi-Strategy Dhole Optimization Algorithm and Its Engineering Applications.

Biomimetics (Basel, Switzerland)·2026
See all related articles
This summary is machine-generated.

This study introduces a new dynamic model and adaptive trajectory planning for robotic hands, improving control and reducing errors. The enhanced reinforcement learning algorithm achieves better training efficiency and performance with fewer samples.

Area of Science:

  • Robotics
  • Artificial Intelligence
  • Control Systems

Background:

  • Dexterous robotic hands, inspired by biological designs, face challenges in modeling, planning, and control for complex tasks.
  • Current robotic end effectors exhibit limited dexterity and clumsy motions due to unresolved control challenges.

Purpose of the Study:

  • To develop an advanced dynamic model for dexterous robotic hands.
  • To create an adaptive trajectory planning method for improved control.
  • To enhance a reinforcement learning algorithm for efficient robotic hand manipulation.

Main Methods:

  • A generative adversarial architecture was used to create a dynamic model for learning dexterous hand states and reducing prediction errors.
  • An adaptive trajectory planning kernel generated High-Value Area Trajectory (HVAT) data, with adjustments via Levenberg-Marquardt (LM) and linear searching coefficients.
Keywords:
adaptive trajectory planning kerneldynamic modelgenerative adversarial architecturereinforcement learning

More Related Videos

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories
07:52

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Published on: July 10, 2019

14.3K
Acquisition of a High-precision Skilled Forelimb Reaching Task in Rats
08:59

Acquisition of a High-precision Skilled Forelimb Reaching Task in Rats

Published on: June 22, 2015

10.4K

Related Experiment Videos

Last Updated: Jul 25, 2025

Investigating Motor Skill Learning Processes with a Robotic Manipulandum
07:52

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

8.8K
Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories
07:52

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Published on: July 10, 2019

14.3K
Acquisition of a High-precision Skilled Forelimb Reaching Task in Rats
08:59

Acquisition of a High-precision Skilled Forelimb Reaching Task in Rats

Published on: June 22, 2015

10.4K
  • An improved Soft Actor-Critic (SAC) algorithm was developed, integrating maximum entropy and HVAT value iterations.

    • Main Results:

    • The proposed dynamic model effectively learned the state mode of the dexterous hand, minimizing long-span prediction errors.
    • The adaptive trajectory planning kernel successfully generated HVAT data, enabling precise trajectory adjustments.
    • The enhanced SAC algorithm demonstrated superior training efficiency and required fewer samples for satisfactory control performance.

    Conclusions:

    • The integrated approach of a novel dynamic model, adaptive trajectory planning, and an improved SAC algorithm significantly enhances robotic hand control.
    • The developed method offers a promising solution for achieving more dexterous and efficient manipulation in robotic systems.
    • Experimental validation confirmed the algorithm's effectiveness in improving training efficiency and control performance for complex tasks.