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

Task-level object grasping for simulated agents.

B Douville1, L Levison, N I Badler

  • 1Department of Computer and Information Science, University of Pennsylvania, Philadelphia 19104, USA.

Presence (Cambridge, Mass.)
|October 1, 1996
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

How the Ocean personality model affects the perception of crowds.

IEEE computer graphics and applications·2014
Same author

Where to look? Automating attending behaviors of virtual human characters.

Autonomous agents and multi-agent systems·2002
Same author

Real-time inverse kinematics techniques for anthropomorphic limbs.

Graphical models·2002
Same author

Animation control for real-time virtual humans.

Communications of the ACM·2001
Same author

Simulated casualties and medics for emergency training.

Studies in health technology and informatics·1996
Same author

Casualty modeling for real-time medical training.

Presence (Cambridge, Mass.)·1996
Same journal

Effect of Visuo-Motor Co-location on 3D Fitts' Task Performance in Physical and Virtual Environments.

Presence (Cambridge, Mass.)·2013
Same journal

A Physics-driven Neural Networks-based Simulation System (PhyNNeSS) for multimodal interactive virtual environments involving nonlinear deformable objects.

Presence (Cambridge, Mass.)·2012
Same journal

Lessons about Virtual-Environment Software Systems from 20 years of VE building.

Presence (Cambridge, Mass.)·2010
Same journal

Modeling of Tool-Tissue Interactions for Computer-Based Surgical Simulation: A Literature Review.

Presence (Cambridge, Mass.)·2010
Same journal

Effects of characteristics of image quality in an immersive environment.

Presence (Cambridge, Mass.)·2002
Same journal

Perceived orientation in physical and virtual environments: changes in perceived orientation as a function of idiothetic information available.

Presence (Cambridge, Mass.)·2002
See all related articles

This study introduces a system for realistic human figure animation, enabling high-level task commands for object grasping by simulated agents. It bridges the gap between general instructions and specific joint motions for improved animation control.

Area of Science:

  • Computer Graphics
  • Human-Computer Interaction
  • Robotics

Background:

  • Realistic human figure animation requires agents to interact with objects naturally.
  • Current animation systems lack high-level command interfaces for detailed object manipulation.
  • Bridging high-level task planning and low-level joint motion control is crucial for efficient animation.

Purpose of the Study:

  • To develop a system for task-level, general-purpose object grasping in simulated human agents.
  • To enable concise, high-level commands for controlling complex manual tasks in animation.
  • To generate realistic object interaction by inferring missing grasp parameters.

Main Methods:

  • Introduction of the Object-Specific Reasoner (OSR) module for inferring grasp parameters based on object knowledge.

Related Experiment Videos

  • Implementation of the Grasp Behavior for managing coordinated hand, wrist, and arm motions.
  • Hierarchical composition of OSR and Grasp Behavior to interpret task-level commands.

    • Main Results:

    • The OSR module successfully generates values for underspecified grasp parameters.
    • The Grasp Behavior effectively manages simultaneous joint motions for realistic grasping.
    • The integrated system translates high-level commands into specific animation system motions.

    Conclusions:

    • The developed system provides an efficient connection between high-level task specifications and low-level animation control.
    • This approach enhances the realism and ease of controlling manual tasks for simulated human agents.
    • The OSR and Grasp Behavior modules, within the Jack system, offer a robust solution for object interaction animation.