Continuous appearance-based trajectory SLAM

This paper describes a novel probabilistic approach to incorporating odometric information into appearance-based SLAM systems, without performing metric map construction or calculating relative feature geometry. The proposed system, dubbed Continuous Appearance-based Trajectory SLAM (CAT-SLAM), represents location as a probability distribution along a trajectory, and represents appearance continuously over the trajectory rather than at discrete locations. The distribution is evaluated using a Rao-Blackwellised particle filter, which weights particles based on local appearance and odometric similarity and explicitly models both the likelihood of revisiting previous locations and visiting new locations. A modified resampling scheme counters particle deprivation and allows loop closure updates to be performed in constant time regardless of map size. We compare the performance of CAT-SLAM to FAB-MAP (an appearance-only SLAM algorithm) in an outdoor environment, demonstrating a threefold increase in the number of correct loop closures detected by CAT-SLAM.

Authors

• Will Maddern
• Michael Milford
• Gordon F. Wyeth

Keywords

• Trajectory
• Simultaneous localization and mapping
• Mathematical model
• Measurement
• Global Positioning System
• History
• Equations
• Continuous Trajectory
• Particle Filter
• Discrete Locations
• Geometry Features
• Nonexpansive Mapping
• Loop Closure
• False Positive
• Maximum Likelihood
• Training Data
• Control Input
• Continuous Model
• Mean-field
• Historical Conditions
• Single Frame
• Motion Model
• Correct Order
• Precision-recall Curve
• High Recall
• Motion Information
• Local Particle
• Number Of Updates
• Continuous Index
• Previous Visit
• Particle Weight
• False Rejection