Mobile robot localization from learned landmarks

Presents an approach to vision-based mobile robot localization. In an attempt to capitalize on the benefits of both image and landmark-based methods, we describe a method that combines their strengths. Images are encoded as a set of visual features called landmarks. Potential landmarks are detected using an attention mechanism implemented as a measure of uniqueness. They are then selected and represented by an appearance-based encoding. Localization is performed using a landmark tracking and interpolation method which obtains an estimate accurate to a fraction of the environment sampling density. Experimental results are shown to confirm the feasibility and accuracy of the method.

Authors

• Robert Sim
• Gregory Dudek

Keywords

• Mobile robots
• Encoding
• Interpolation
• Sampling methods
• Object recognition
• Computational geometry
• Kalman filters
• Filtering
• Robot localization
• Cameras
• Mobile Robot Localization
• Learned Landmarks
• Kalman Filter
• Local Method
• Visual Attention
• Median Filter
• Position Estimation
• Pose Estimation
• Image Position
• Camera Position
• Landmark Localization
• Camera Pose
• Local Extrema
• Grid Position
• Landmark Detection