Interactive Task Learning

Abstract

Our research on interactive task learning has emphasized the continued development of a natural language understanding system that interfaces with a human instructor, and the underlying task learning system. The language system uniquely combined relevant research: a construction grammar approach to representing linguistic knowledge; an incremental, single-path processing algorithm with local repair; a cognitive architecture as the computational platform; and embodiment in the robotic agent for grounding language to the agents perception, action capabilities, and knowledge of the world. We extended this to process real world task instructions and the ability to handle multiple forms of ambiguity. The task learning research led to the development of an agent for learning all aspects of tasks, with emphasis on handling ambiguous scenarios. The agent can interactively learning over 55 games and puzzles, and transfers knowledge learned in one game to a similar game.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 12, 2019
Accession Number
AD1096957

Entities

People

  • John E. Laird

Organizations

  • Board of Regents of the University of Michigan

Tags

DTIC Thesaurus Topics

  • Air Force Research Laboratories
  • Algorithms
  • Ambiguity
  • Artificial Intelligence
  • Cognitive Science
  • Computer Languages
  • Computer Science
  • Construction
  • Grammars
  • Instructions
  • Instructors
  • Language
  • Linguistics
  • Models
  • Natural Languages
  • Prototypes
  • Test Sets

Fields of Study

  • Computer science
  • Education

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Artificial Intelligence

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation
  • Autonomy
  • Autonomy - Human-Robot Interaction