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 Videos

Adaptive critic neural network-based object grasping control using a three-finger gripper.

S Jagannathan1, Gustavo Galan

  • 1Department of Electrical and Computer Enginering, The University of Missouri-Rolla, Rolla, MO 65401, USA. sarangap@umr.edu

IEEE Transactions on Neural Networks
|September 24, 2004
PubMed
Summary
This summary is machine-generated.

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

Microbiologically influenced corrosion dynamics and technological innovations in monitoring and control.

Journal of microbiological methods·2026
Same author

Online lifelong optimal tracking control of uncertain nonlinear continuous-time strict-feedback systems using deep neural networks.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Status of disinfection byproducts research in India.

Chemosphere·2023
Same author

A deep learning approach to detect blood vessels in basal cell carcinoma.

Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging (ISSI)·2022
Same author

Random lasing from optical fibers with phase separated glass cores.

Optics express·2020
Same author

Direct Error-Driven Learning for Deep Neural Networks With Applications to Big Data.

IEEE transactions on neural networks and learning systems·2019

This study introduces an adaptive critic neural network (NN) controller for robotic grasping. The novel approach enables precise object manipulation and force control without prior knowledge of object or gripper dynamics.

Area of Science:

  • Robotics
  • Control Systems
  • Artificial Intelligence

Background:

  • Robotic grasping is complex, involving object contact control and manipulation.
  • Accurate trajectory following and force application are crucial for successful grasping.
  • Grasping without prior knowledge of object properties and dynamics is challenging.

Purpose of the Study:

  • To develop a sophisticated controller for robotic grasping tasks.
  • To address the challenges of unknown object properties, gripper dynamics, and contact dynamics.
  • To enable precise trajectory tracking and force control during manipulation.

Main Methods:

  • An adaptive critic neural network (NN)-based hybrid position/force control scheme is proposed.
  • A feedforward action-generating NN compensates for nonlinear dynamics.

Related Experiment Videos

  • On-line learning of the action-generating NN is driven by a critic NN output signal.
  • Novel NN weight tuning updates ensure Lyapunov-based stability.

    • Main Results:

    • The proposed controller allows a three-finger gripper to track desired trajectories and apply desired forces.
    • The system successfully secures objects without prior knowledge of gripper and contact dynamics.
    • Simulation results validate the effectiveness of the adaptive critic NN controller.

    Conclusions:

    • The adaptive critic NN controller provides a robust solution for complex robotic grasping.
    • This method enhances robotic manipulation capabilities by overcoming limitations of unknown dynamics.
    • The approach demonstrates significant improvements over conventional control schemes in simulation.