COMPUTER VISION ALGORITHMS FOR AUTONOMOUS MOBILE ROBOT MAP BUILDING AND PATH PLANNING

This paper describes a new algorithm for autonomous mobile robot (AMR) map building and path planning in an unknown environment. The algorithm allows the AMR to learn an unknown environment without the need for internal distance measurements, using only feature observations. The algorithm also allows the AMR to learn a new environment with a single passing and once the environment has been mapped, its topology can be inferred from the stored map. Additionally, using a limited amount of real-world distance information, the robot is able to construct a robust internal representation of its position and thus perform accurate intra-region localization.

• Supplemental Notes:
  • Publication Date: 1997 Published By: IEEE Service Center, Piscataway NJ
• Authors:
  • Meikle, Stuart
  • Yates, Rob
  • Harris, Anthony
• Conference:
  • IEEE Conference on Intelligent Transportation Systems (1997 : Boston Mass.). IEEE Conference on Intelligent Transportation Systems
• Publication Date: 1997

Language

• English

Media Info

• Pagination: p. 99-104

Subject/Index Terms

• TRT Terms: Computer vision; Robotics

Filing Info

• Accession Number: 00776484
• Record Type: Publication
• Source Agency: UC Berkeley Transportation Library
• Files: PATH
• Created Date: Nov 17 1999 12:00AM