Grounding Vision through Experimental Manipulation

Abstract

Experimentation is crucial to human progress at all scales, from society as a whole to a young infant in its cradle/ It allows us to elicit learning episodes suited to our own needs and limitations. This paper develops active strategies for a robot to acquire visual experience through simple experimental manipulation. The experiments are oriented towards determining what parts of the environment are physically coherent- that is, which parts will move together, and which are more or less independent. We argue that following causal chains of events out from the robot's body into the environment allows for a very natural developmental progression of visual competence, and relate this idea to results in neuroscience.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2002
Accession Number
ADA434758

Entities

People

  • Giorgio Metta
  • Paul Fitzpatrick

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Automata Theory
  • Brain
  • Cognitive Science
  • Computer Languages
  • Computer Vision
  • Computers
  • Electrical Engineering
  • Image Processing
  • Neurons
  • Neurosciences
  • Object Recognition
  • Pattern Recognition
  • Physical Properties
  • Psychology
  • Recognition

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • Autonomy