Biologically inspired mobile robot vision localization

  • Authors:

  • Christian Siagian;Laurent Itti

  • Affiliations:

  • Departments of Computer Science, Psychology, and Neuroscience Program, University of Southern California, Los Angeles, CA;Departments of Computer Science, Psychology, and Neuroscience Program, University of Southern California, Los Angeles, CA

  • Venue:
  • IEEE Transactions on Robotics
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present a robot localization system using biologically inspired vision. Our system models two extensively studied human visual capabilities: 1) extracting the "gist" of a scene to produce a coarse localization hypothesis and 2) refining it by locating salient landmark points in the scene. Gist is computed here as a holistic statistical signature of the image, thereby yielding abstract scene classification and layout. Saliency is computed as a measure of interest at every image location, which efficiently directs the time-consuming landmark-identification process toward the most likely candidate locations in the image. The gist features and salient regions are then further processed using aMonte Carlo localization algorithm to allow the robot to generate its position. We test the system in three different outdoor environments--building complex (38.4m × 54.86 m area, 13 966 testing images), vegetation-filled park (82.3m × 109.73m area, 26 397 testing images), and openfield park (137.16m × 178.31m area, 34 711 testing images)--each with its own challenges. The system is able to localize, on average, within 0.98, 2.63, and 3.46 m, respectively, even with multiple kidnapped-robot instances.