• DocumentCode
    2647308
  • Title

    Fusing binaural sonar information for object recognition

  • Author

    Kuc, Roman

  • Author_Institution
    Dept. of Electr. Eng., Yale Univ., New Haven, CT, USA
  • fYear
    1996
  • fDate
    8-11 Dec 1996
  • Firstpage
    727
  • Lastpage
    735
  • Abstract
    An active binaural sonar using Polaroid electrostatic transducers positioned at the end of a robot arm is described, which adaptively changes its location and configuration in response to the echoes it observes in order to recognize an object. The sonar mimics biological echolocation systems, such as bats and dolphins. Using information in the echoes, the sonar translates in a horizontal plane and rotates about vertical and horizontal axes to position an object at a standard location within the beam patterns. The transmitter points at the object to maximize the incident acoustic intensity and the receivers rotate to maximize the echo-amplitude and bandwidth and to minimize the echo-producing region. The system can recognize a collection of ball bearings, machine washers and rubber O-rings of different sizes ranging from 0.45 to 2.54 cm some differing by less than 1 mm in diameter. Recognition is accomplished by extracting 32 values from the binaural echo patterns and searching a database. Fusing the information from the two ears allows efficient determination of the object bearing
  • Keywords
    adaptive signal processing; echo; object recognition; robots; sensor fusion; sonar imaging; sonar target recognition; Polaroid electrostatic transducers; acoustic beam patterns; adaptive sonar systems; binaural sonar; echoes; incident acoustic intensity; object recognition; robot arm; sensor fusion; Acoustic beams; Ball bearings; Bandwidth; Dolphins; Electrostatics; Object recognition; Robots; Sonar; Transducers; Transmitters;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Multisensor Fusion and Integration for Intelligent Systems, 1996. IEEE/SICE/RSJ International Conference on
  • Conference_Location
    Washington, DC
  • Print_ISBN
    0-7803-3700-X
  • Type

    conf

  • DOI
    10.1109/MFI.1996.572309
  • Filename
    572309