Visual homing in environments with anisotropic landmark distribution

Authors:
Ralf Möller;Andrew Vardy;Sven Kreft;Sebastian Ruwisch
Affiliations:
Computer Engineering, Faculty of Technology, Bielefeld University, Bielefeld, Germany 33594;Computer Science/Engineering & Applied Science, Memorial University of Newfoundland, St. John's, Canada A1B 3X5;Computer Engineering, Faculty of Technology, Bielefeld University, Bielefeld, Germany 33594;Computer Engineering, Faculty of Technology, Bielefeld University, Bielefeld, Germany 33594
Venue:
Autonomous Robots
Year:
2007

Citing 4
Cited 4

Learning View Graphs for Robot Navigation

Autonomous Robots - Special issue on autonomous agents
Integration of Metric Place Relations in a Landmark Graph

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Local visual homing by matched-filter descent in image distances

Biological Cybernetics
Adaptation of Controllers for Image-Based Homing

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems

Optical Rails

Proceedings of the 30th DAGM symposium on Pattern Recognition
Local visual homing by warping of two-dimensional images

Robotics and Autonomous Systems
Three 2D-warping schemes for visual robot navigation

Autonomous Robots
Angle-based homing from a reference image set using the 1D trifocal tensor

Autonomous Robots

Quantified Score

Hi-index	0.00

Visualization

Abstract

Gradient descent in image distances can lead a navigating agent to the goal location, but in environments with an anisotropic distribution of landmarks, gradient home vectors deviate from the true home direction. These deviations can be reduced by applying Newton's method to matched-filter descent in image distances (MFDID). Based on several image databases we demonstrate that the home vectors produced by the Newton-based MFDID method are usually closer to the true home direction than those obtained from the original MFDID method. The greater accuracy of Newton-MFDID home vectors in the vicinity of the goal location would allow a navigating agent to approach the goal on straighter trajectories, improve the results of triangulation procedures, and enhance a robot's ability to detect its arrival at a goal.