Bayesian network for online global pose estimation

We cast the location estimation problem in vision-based robotic navigation in a Bayesian framework. We derive an efficient online algorithm for updating the trajectory of a robot as new frames of data become available. For each new frame, the algorithm computes the pose of the robot relative to past frames and combines these relative pose changes to obtain a robust estimate of its trajectory. The complexity of this algorithm grows linearly with the number of frames so far processed. Since it is effectively tracking against an appearance-based map, our algorithm provides consistent results in circular environments, where the robot returns to places already visited.

Authors

• Ali Rahimi
• Trevor Darrell

Keywords

• Bayesian methods
• Robot sensing systems
• Robot vision systems
• Navigation
• Cameras
• Trajectory
• Buildings
• Solid modeling
• Artificial intelligence
• Robustness
• Global Estimates
• Pose Estimation
• Global Pose
• Global Pose Estimation
• Bayesian Framework
• Robot Navigation
• Robot Trajectory
• Pose Changes
• Past Frames
• Markov Chain
• Probabilistic Model
• Parametrized
• Kalman Filter
• Root Node
• Linear Time
• Large Loop
• Hidden Variables
• Missing Piece
• World Map
• Environment Map
• Pose Of Frame
• Global Consistency
• Scan Pairs
• Base Frame
• Trajectory Estimation
• Iterative Closest Point