Global localization using distinctive visual features

We have previously developed a mobile robot system which uses scale invariant visual landmarks to localize and simultaneously build a 3D map of the environment In this paper, we look at global localization, also known as the kidnapped robot problem, where the robot localizes itself globally, without any prior location estimate. This is achieved by matching distinctive landmarks in the current frame to a database map. A Hough transform approach and a random sample consensus (RANSAC) approach for global localization are compared, showing that RANSAC is much more efficient. Moreover, robust global localization can be achieved by matching a small sub-map of the local region built from multiple frames.

Authors

• Stephen Se
• David G. Lowe
• James J. Little

Keywords

• Mobile robots
• Simultaneous localization and mapping
• Robot sensing systems
• Intelligent robots
• Intelligent sensors
• Semiconductor device modeling
• Airports
• Databases
• Robustness
• Navigation
• Global Localization
• Distinct Visual Features
• Scale-invariant
• Mobile Robot
• Current Frame
• Multiple Frames
• Hough Transform
• Visual Landmarks
• Laser Scanning
• Probability Sampling
• Object Recognition
• Local Image
• Local Vector
• 3D Coordinates
• Pose Estimation
• Database Size
• Landmark Localization
• Odometry
• Scale-invariant Feature Transform
• Robot Pose
• Multiple Robots
• Robot Localization
• Map Alignment
• Occupancy Map
• Robot Navigation