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

Learning visuomotor transformations for gaze-control and grasping.

Heiko Hoffmann1, Wolfram Schenck, Ralf Möller

  • 1Department of Psychology, Max Planck Institute for Human Cognitive and Brain Sciences, Cognitive Robotics, 80799, Munich, Germany. mpi@heikohoffmann.de

Biological Cybernetics
|July 20, 2005
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

H-NGPCA: Hierarchical clustering of data streams with adaptive number of clusters and adaptive dimensionality.

PloS one·2026
Same author

Earth's most needed uncultivated aquatic prokaryotes.

Water research·2024
Same author

Image restoration in frequency space using complex-valued CNNs.

Frontiers in artificial intelligence·2024
Same author

Computational model of layer 2/3 in mouse primary visual cortex explains observed visuomotor mismatch response.

Journal of computational neuroscience·2024
Same author

Active Learning for Handling Missing Data.

IEEE transactions on neural networks and learning systems·2024
Same author

Evaluation of Swin Transformer and knowledge transfer for denoising of super-resolution structured illumination microscopy data.

GigaScience·2024
Same journal

Harmonic memory in phasor neural networks.

Biological cybernetics·2026
Same journal

Correction: Decreased spinal inhibition leads to undiversified locomotor patterns.

Biological cybernetics·2026
Same journal

Foundational issues of network models in biology.

Biological cybernetics·2026
Same journal

Dynamical mechanisms for coordinating long-term working memory based on the precision of spike-timing in cortical neurons.

Biological cybernetics·2026
Same journal

Distinct dopaminergic spike-timing-dependent plasticity rules are suited to different functional roles.

Biological cybernetics·2026
Same journal

Fluctuation-response relations for a two-stage population of spiking neurons stimulated by common noise.

Biological cybernetics·2026
See all related articles

This study introduces a robot model for visually guided reaching and grasping, mimicking human brain pathways. The model successfully grasps objects using two visual processing routes and unsupervised learning for arm control.

Area of Science:

  • Robotics
  • Computational Neuroscience
  • Computer Vision

Background:

  • Visually guided reaching and grasping require transforming visual information into motor commands.
  • Human brains likely use multiple pathways for processing visual-motor tasks.

Purpose of the Study:

  • To present a robot model for visually guided reaching and grasping.
  • To mimic two alternative visual processing pathways found in the human brain.
  • To develop novel learning methods for robot control.

Main Methods:

  • The model employs two grasping pathways: direct retinal activation and gaze-direction based on a saccade controller.
  • A novel staged learning method trains the saccade controller without motor commands.
  • An arm controller uses unsupervised learning based on a density model for sensorimotor data.

Related Experiment Videos

Main Results:

  • The model successfully fixated and grasped an elongated object with arbitrary orientation and position in 94% of trials.
  • The arm controller effectively handles redundant arm postures for a given target.
  • The staged learning method for saccade control is effective.

Conclusions:

  • The presented robot model effectively performs visually guided reaching and grasping.
  • The dual-pathway approach and unsupervised learning are viable for complex motor tasks.
  • The model demonstrates robust performance in handling object variability.