FEATURE DETECTION AND MAP BUILDING USING RANGING SENSORS

In this paper, the authors describe two methods for feature extraction in mapping. The objective is to interpret the data that is obtained from sonar measurements of a robot's environment as geometric map primitives. The extracted primitives can then be used to update the robot position and the global map. In the first method, sonar measurements are gathered into a sensor-based map, followed by the extraction of the geometric description of detected obstacles using computer vision techniques. The second method uses raw sonar data as the input while using a border tracking process to detect obstacle borders. The methods were verified using an experimental mobile robot.

• Supplemental Notes:
  • Publication Date: 1999 IEEE Service Center, Piscataway NJ
• Corporate Authors:

  Nippon Shingo Kabushiki Kaisha

  ,    

  Ruhr-Universitat Bochum. Institut fur Neuroinformatik

  ,    

  Universitat-Gesamthochschule-Siegen

  ,    

  Hitachi Seisakujo

  ,    

  Osaka Daigaku

  ,    

  Keisatsu Daigakko

  ,    
• Authors:
  • Kulich, Miroslav
  • Stepan, Petr
  • Preucil, Libor
• Conference:
  • IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems (1999 : Tokyo, Japan). Proceedings : 1999 IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems
• Publication Date: 1999

Language

• English

Media Info

• Pagination: p. 201-206

Subject/Index Terms

• TRT Terms: Computer vision; Digital mapping; Robotics
• Subject Areas: Design;

Filing Info

• Accession Number: 00801260
• Record Type: Publication
• Source Agency: UC Berkeley Transportation Library
• Files: PATH
• Created Date: Nov 7 2000 12:00AM