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 5, 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

8.7K

Robot Grasp Planning: A Learning from Demonstration-Based Approach.

Kaimeng Wang1, Yongxiang Fan1, Ichiro Sakuma2

  • 1FANUC Advanced Research Laboratory, FANUC America Corporation, Union City, CA 94587, USA.

Sensors (Basel, Switzerland)
|January 23, 2024
PubMed
Summary

This study introduces a new robot grasping method using human demonstrations to learn contact regions and approach directions. This approach enhances grasp stability for complex industrial tasks.

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

Investigating the structural responses of medial collagen and elastin to traction to elucidate mechanical property differences in porcine aorta and pulmonary artery.

Acta biomaterialia·2026
Same author

Computed tomography-based prediction of commissural positions facilitates valve-sparing aortic root replacement.

JTCVS techniques·2026
Same author

Developing a quality index and an evaluation indicator system for the National Food Safety Standard Framework in China.

Journal of public health policy·2026
Same author

Phase Variance Analysis for Identifying Heterogeneous Conduction Regions in Persistent Atrial Fibrillation: Impact of Recording Duration.

Journal of arrhythmia·2025
Same author

Validation of an intraoperative plantar pressure system in anesthetized patients.

Foot and ankle surgery : official journal of the European Society of Foot and Ankle Surgeons·2025
Same author

Calculated Excess-Triglyceride Based on the Friedewald Formula is a Possible Surrogate Marker for the Production of Large Very-Low Density Lipoprotein, A Post-Hoc Analysis of the PROUD48 Study.

Journal of atherosclerosis and thrombosis·2025

Area of Science:

  • Robotics
  • Artificial Intelligence
  • Machine Learning

Background:

  • Robot grasping is crucial for industrial automation but faces challenges due to object geometry and task diversity.
  • Existing methods often struggle with implicit skill learning or kinematic mapping between human and robot hands.

Purpose of the Study:

  • To develop a novel learning from demonstration (LfD) framework for robot grasp planning.
  • To extract intuitive human grasp skills, specifically contact regions and approach direction, from single demonstrations.
  • To generate stable grasps by optimizing these extracted human skills.

Main Methods:

  • Extracting contact regions and approach direction from a single human grasp demonstration.
  • Formulating an optimization problem integrating extracted human skills to generate a stable grasp.
Keywords:
grasp synthesislearning from demonstrationrobot learningskill transfer

More Related Videos

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
11:53

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

Published on: October 14, 2017

11.6K
SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots
11:01

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

13.2K

Related Experiment Videos

Last Updated: Jul 5, 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

8.7K
The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
11:53

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

Published on: October 14, 2017

11.6K
SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots
11:01

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

13.2K
  • Minimizing surface fitting error and penalizing misalignment between demonstrated and gripper approach directions.

    • Main Results:

    • The proposed framework effectively extracts human grasp intent (contact regions, approach direction).
    • Optimization successfully generates stable grasps by aligning with human intent.
    • Experiments in simulation and real-world scenarios validate the algorithm's effectiveness.

    Conclusions:

    • The LfD framework successfully captures intuitive human grasp skills.
    • The approach improves grasp stability by learning from human intent, not just kinematics.
    • This method offers a promising direction for advancing robot grasping capabilities in industrial settings.