A Framework for Learning Declarative Structure

Abstract

This paper provides a framework with which a humanoid robot can efficiently learn complex behavior. In this framework, a robot is rewarded by learning how to generate novel sensorimotor feedback a form of native motivation. This intrinsic drive biases the robot to learn increasingly complex knowledge about itself and its effect on the environment. The framework includes a mechanism for uncovering hidden state in a well-structured state and action space. We present an example wherein the robot, Dexter, learns a sequence of manual skills: (1) searching for and grasping an object, (2) the length of its arms, and (3) how to portray its intentions to human teachers in order to induce them to help.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2006
Accession Number
ADA459921

Entities

People

  • John Sweeney
  • Rod Grupen
  • Shichao Ou
  • Stephen Hart

Organizations

  • University of Massachusetts Amherst

Tags

Communities of Interest

  • Air Platforms
  • Autonomy
  • Human Systems
  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Abstracts
  • Acquisition
  • Algorithms
  • Artificial Intelligence
  • Boundaries
  • Computer Programs
  • Computer Science
  • Control
  • Data Sets
  • Feedback
  • Instructors
  • Learning
  • Load Cells
  • Probability
  • Probability Distributions
  • Supervised Machine Learning
  • Transitions

Fields of Study

  • Computer science

Readers

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

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • Autonomy
  • Space
  • Space - Spacecraft Maneuvers