Position Estimation Using Principal Components of Range Data

Describes an approach to mobile robot position estimation based on principal component analysis of laser range data. An eigenspace is constructed from the principal components of a large number of range data sets. The structure of an environment, as seen by a range sensor, is represented as a family of surfaces in this space. Subsequent range data sets from the environment project as a point in this space. Associating this point to the family of surfaces gives a set of candidate positions and orientations (poses) for the sensor. These candidate poses correspond to positions and orientations in the environment which have similar range profiles. A Kalman filter can used to select the most likely candidate pose based on coherence with small movements. The first part of this paper describes how a relatively small number of depth profiles of an environment can be used to generate a complete eigenspace. This space is used to build a representation of the range scan profiles obtained from a regular grid of positions and orientations (poses). This representation has the form of a family of surfaces (a manifold). This representation converts the problem of associating a range profile to possible positions and orientations into a table lookup. As a side benefit, the method provides a simple means to detect obstacles in a range profile. The final section of the paper reviews the use of estimation theory to determine the correct pose hypothesis by tracking.

Authors

• James L. Crowley
• Frank Wallner
• Bernt Schiele

Keywords

• Intelligent sensors
• Principal component analysis
• Navigation
• Mobile robots
• Motion control
• Computer vision
• Sensor phenomena and characterization
• Table lookup
• Estimation theory
• Motion estimation
• Position Estimation
• Points In Space
• Kalman Filter
• Lookup Table
• Mobile Robot
• Range Of Sensors
• Approximation Theory
• Range Profile
• Grid Position
• Interpolation
• Covariance Matrix
• Diagonal Matrix
• Tetrahedral
• Maximum Velocity
• Linear Approximation
• Multiple Hypothesis
• Pose Estimation
• Error Vector
• Nearest Point
• Adjacent Measurements
• Number Of Hypotheses
• Nearest Neighbor Search
• Surface Projection
• Sufficient Memory
• Eigenvectors
• Set Of Scans
• Dense Grid
• Orientation Estimation