Subpixel localization and uncertainty estimation using occupancy grids
- 20 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 1987-1992
- https://doi.org/10.1109/robot.1999.770399
Abstract
We describe techniques for performing mobile robot localization using occupancy grids that enable both sub- pixel localization to be performed and uncertainty es- timates to be computed. The uncertainty is addressed with respect to both the standard deviation of the lo- calization estimate and the probability of a qualita- tive failure. The techniques are based on a localiza- tion method that performs matching between the visible landmarks at the current robot position and a previ- ously generated map of the environment. We first es- timate the probability distribution of the distance from each feature in the local map to the closest feature an the larger map. Subpixel localization and uncertainty estimation are then perform by fitting the likelihood function over the space of possible robot positions with a parameterized surface. Synthetic experiments are described and an example of the performance of this method is given using the Rocky 7 Mars rover proto- type.Keywords
This publication has 8 references indexed in Scilit:
- A multi-resolution technique for comparing images using the Hausdorff distancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Maximum likelihood rover localization by matching range mapsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A probabilistic formulation for Hausdorff matchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The Rocky 7 rover: a Mars sciencecraft prototypePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- EFFICIENT ALGORITHMS FOR THE EUCLIDEAN DISTANCE TRANSFORMParallel Processing Letters, 1995
- Stereo vision for planetary rovers: Stochastic modeling to near real-time implementationInternational Journal of Computer Vision, 1992
- High-resolution terrain map from multiple sensor dataPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Sonar-based real-world mapping and navigationIEEE Journal on Robotics and Automation, 1987