Vision-based Mobile Robot Localization And Mapping using Scale-Invariant Features

A key component of a mobile robot system is the ability to localize itself accurately and build a map of the environment simultaneously. In this paper, a vision-based mobile robot localization and mapping algorithm is described which uses scale-invariant image features as landmarks in unmodified dynamic environments. These 3D landmarks are localized and robot ego-motion is estimated by matching them, taking into account the feature viewpoint variation. With our Triclops stereo vision system, experiments show that these features are robustly matched between views, 3D landmarks are tracked, robot pose is estimated and a 3D map is built.

Authors

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

Keywords

• Mobile robots
• Stereo vision
• Robot vision systems
• Sonar navigation
• Cameras
• Robot sensing systems
• Computer science
• Robustness
• Simultaneous localization and mapping
• Machine vision
• Scale-invariant
• Mobile Robot
• Robot Localization
• Mobile Mapping
• Mobile Robot Localization
• Image Features
• Dynamic Environment
• Stereopsis
• Robot Pose
• 3D Landmarks
• Laser Scanning
• Expectation Maximization
• Current Position
• Kalman Filter
• 3D Coordinates
• Consecutive Frames
• Feature Matching
• Pose Estimation
• Object Parts
• Scale-invariant Feature Transform
• Stereo Matching
• Top Image
• Left Image
• Robot Navigation
• View Direction
• Image Coordinates
• Position Of The Robot
• Laser Ranging
• Occupancy Map