Skill augmentation via interactive learning for visual guidance of mobile robots

Qiuming Zhu, Dahuan Shi

Research output: Contribution to journalArticle

Abstract

A computer learning system is presented, which is capable of gaining and augmenting the operational skills for a mobile robot to navigate in unexplored environments. Rather than having the robot programmed to work in a designated environment, it is trained to acquire generic knowledge about visual guidance and motion control in the environments which bear some common features of the learning environment. In the training process, the robot learns to make decisions under different circumstances, represented as meta-scenes. The learning process applies an interactive instruction method and a generic rule modification scheme. An explanation-based reasoning approach and a pattern-matching technique for knowledge induction are implemented. The learning system structure and computer simulations are illustrated.

Original languageEnglish (US)
Pages (from-to)101-112
Number of pages12
JournalEngineering Applications of Artificial Intelligence
Volume5
Issue number2
DOIs
StatePublished - Mar 1992

Fingerprint

Electronic guidance systems
Mobile robots
Learning systems
Robots
Pattern matching
Motion control
Computer simulation

Keywords

  • Computer learning
  • knowledge acquisition
  • meta-scene
  • pattern-matching
  • robot motion
  • visual guidance

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

Skill augmentation via interactive learning for visual guidance of mobile robots. / Zhu, Qiuming; Shi, Dahuan.

In: Engineering Applications of Artificial Intelligence, Vol. 5, No. 2, 03.1992, p. 101-112.

Research output: Contribution to journalArticle

@article{1c5e747226e74288817f2faba7e8c65e,
title = "Skill augmentation via interactive learning for visual guidance of mobile robots",
abstract = "A computer learning system is presented, which is capable of gaining and augmenting the operational skills for a mobile robot to navigate in unexplored environments. Rather than having the robot programmed to work in a designated environment, it is trained to acquire generic knowledge about visual guidance and motion control in the environments which bear some common features of the learning environment. In the training process, the robot learns to make decisions under different circumstances, represented as meta-scenes. The learning process applies an interactive instruction method and a generic rule modification scheme. An explanation-based reasoning approach and a pattern-matching technique for knowledge induction are implemented. The learning system structure and computer simulations are illustrated.",
keywords = "Computer learning, knowledge acquisition, meta-scene, pattern-matching, robot motion, visual guidance",
author = "Qiuming Zhu and Dahuan Shi",
year = "1992",
month = "3",
doi = "10.1016/0952-1976(92)90050-T",
language = "English (US)",
volume = "5",
pages = "101--112",
journal = "Engineering Applications of Artificial Intelligence",
issn = "0952-1976",
publisher = "Elsevier Limited",
number = "2",

}

TY - JOUR

T1 - Skill augmentation via interactive learning for visual guidance of mobile robots

AU - Zhu, Qiuming

AU - Shi, Dahuan

PY - 1992/3

Y1 - 1992/3

N2 - A computer learning system is presented, which is capable of gaining and augmenting the operational skills for a mobile robot to navigate in unexplored environments. Rather than having the robot programmed to work in a designated environment, it is trained to acquire generic knowledge about visual guidance and motion control in the environments which bear some common features of the learning environment. In the training process, the robot learns to make decisions under different circumstances, represented as meta-scenes. The learning process applies an interactive instruction method and a generic rule modification scheme. An explanation-based reasoning approach and a pattern-matching technique for knowledge induction are implemented. The learning system structure and computer simulations are illustrated.

AB - A computer learning system is presented, which is capable of gaining and augmenting the operational skills for a mobile robot to navigate in unexplored environments. Rather than having the robot programmed to work in a designated environment, it is trained to acquire generic knowledge about visual guidance and motion control in the environments which bear some common features of the learning environment. In the training process, the robot learns to make decisions under different circumstances, represented as meta-scenes. The learning process applies an interactive instruction method and a generic rule modification scheme. An explanation-based reasoning approach and a pattern-matching technique for knowledge induction are implemented. The learning system structure and computer simulations are illustrated.

KW - Computer learning

KW - knowledge acquisition

KW - meta-scene

KW - pattern-matching

KW - robot motion

KW - visual guidance

UR - http://www.scopus.com/inward/record.url?scp=44049123278&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44049123278&partnerID=8YFLogxK

U2 - 10.1016/0952-1976(92)90050-T

DO - 10.1016/0952-1976(92)90050-T

M3 - Article

AN - SCOPUS:44049123278

VL - 5

SP - 101

EP - 112

JO - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

SN - 0952-1976

IS - 2

ER -