An interactive learning approach for visual guidance of mobile robot

Qiuming Zhu, Dahuan Shi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

An Interactive learning approach is applied to train a mobile robot to navigate in unexplored environments. The robot system is trained to acquire knowledge about path planning and motion control in generic environmental settings, rather than specifically designated situation. The learning process utilizes a pattern matching technique based on a meta- scene modeling of the environment A genetic rule- modification scheme is implemented. The system is capable of gaining and augmenting its operation skills and apply them to the environments which bear certain degrees of similarity with the training environment.

Original languageEnglish (US)
Title of host publicationIROS 1992 - Proceedings of the 1992 IEEE/RSJ International Conference on Intelligent Robots and Systems
Subtitle of host publicationSensor-Based Robotics and Opportunties for its Industrial Applications
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1829-1836
Number of pages8
ISBN (Electronic)0780307372
DOIs
StatePublished - 1992
Event1992 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 1992 - Raleigh, United States
Duration: Jul 7 1992Jul 10 1992

Publication series

NameIEEE International Conference on Intelligent Robots and Systems
Volume3
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Conference

Conference1992 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 1992
Country/TerritoryUnited States
CityRaleigh
Period7/7/927/10/92

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'An interactive learning approach for visual guidance of mobile robot'. Together they form a unique fingerprint.

Cite this