A Biologically Inspired Learning to Grasp System

Abstract

We propose and implement a learning to grasp system inspired from the development of reaching and grasping in infants, and the neurophysiology of the monkey premotor cortex. The system is composed of a virtual 19 DOF kinematics arm/hand and a learning mechanism that enables it to perform a successful grasp. The learning is based on "motor babbling". The model performs open hand reaches to the vicinity of the targets, which human infants younger than 4 moths of age appear to do. The contact of the hand with the object triggers an enclosure of the hand simulating the palmer reflex, characteristic to infants that are younger than 6 months of age. The varying degree of enclosure of each finger and the randomness in the reaching phase enables the system to explore the grasp configuration space. The learning scheme employed is a Hebbian one.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 25, 2001
Accession Number
ADA410502

Entities

People

  • E. Oztop
  • M. A. Arbib

Organizations

  • University of Southern California

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Classification
  • Computer Science
  • Computer Simulations
  • Computers
  • Engineering
  • Hybrid Systems
  • Joints (Anatomy)
  • Kinematics
  • Language
  • Learning
  • Military Research
  • Neural Networks
  • Precision
  • Simulations
  • Simulators
  • User Interface
  • Visual Perception

Readers

  • Neuroscience
  • Robotics and Automation.

Technology Areas

  • Space
  • Space - Spacecraft Maneuvers